default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDStefano Soatto
Person information
- affiliation: University of California, Los Angeles, USA
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
[j68]Yue Zhao
, Yantao Shen, Yuanjun Xiong, Shuo Yang, Wei Xia, Zhuowen Tu, Bernt Schiele, Stefano Soatto:
Elodi: Ensemble Logit Difference Inhibition for Positive-Congruent Training. IEEE Trans. Pattern Anal. Mach. Intell. 46(12): 7529-7541 (2024)- [c273]Hao Li, Yang Zou, Ying Wang, Orchid Majumder, Yusheng Xie, R. Manmatha, Ashwin Swaminathan, Zhuowen Tu, Stefano Ermon, Stefano Soatto:
On the Scalability of Diffusion-based Text-to-Image Generation. CVPR 2024: 9400-9409 - [c272]Ziyao Zeng, Daniel Wang, Fengyu Yang, Hyoungseob Park, Stefano Soatto, Dong Lao, Alex Wong:
WorDepth: Variational Language Prior for Monocular Depth Estimation. CVPR 2024: 9708-9719 - [c271]Alessandro Achille, Greg Ver Steeg, Tian Yu Liu, Matthew Trager, Carson Klingenberg, Stefano Soatto:
Interpretable Measures of Conceptual Similarity by Complexity-Constrained Descriptive Auto-Encoding. CVPR 2024: 11062-11071 - [c270]Aditya Golatkar, Alessandro Achille, Luca Zancato, Yu-Xiang Wang, Ashwin Swaminathan, Stefano Soatto:
CPR: Retrieval Augmented Generation for Copyright Protection. CVPR 2024: 12374-12384 - [c269]Yuan Gao, Kunyu Shi, Pengkai Zhu, Edouard Belval, Oren Nuriel, Srikar Appalaraju, Shabnam Ghadar, Zhuowen Tu, Vijay Mahadevan, Stefano Soatto:
Enhancing Vision-Language Pre-Training with Rich Supervisions. CVPR 2024: 13480-13491 - [c268]Kunyu Shi, Qi Dong, Luis Goncalves, Zhuowen Tu, Stefano Soatto:
Non-autoregressive Sequence-to-Sequence Vision-Language Models. CVPR 2024: 13603-13612 - [c267]Alessandro Favero, Luca Zancato, Matthew Trager, Siddharth Choudhary, Pramuditha Perera, Alessandro Achille, Ashwin Swaminathan, Stefano Soatto:
Multi-Modal Hallucination Control by Visual Information Grounding. CVPR 2024: 14303-14312 - [c266]Dong Lao, Congli Wang, Alex Wong, Stefano Soatto:
Diffeomorphic Template Registration for Atmospheric Turbulence Mitigation. CVPR 2024: 25107-25116 - [c265]Prannay Kaul, Zhizhong Li, Hao Yang, Yonatan Dukler, Ashwin Swaminathan, C. J. Taylor, Stefano Soatto:
THRONE: An Object-Based Hallucination Benchmark for the Free-Form Generations of Large Vision-Language Models. CVPR 2024: 27218-27228 - [c264]Benjamin Biggs, Arjun Seshadri, Yang Zou, Achin Jain, Aditya Golatkar, Yusheng Xie, Alessandro Achille, Ashwin Swaminathan, Stefano Soatto:
Diffusion Soup: Model Merging for Text-to-Image Diffusion Models. ECCV (63) 2024: 257-274 - [c263]Yangchao Wu, Tian Yu Liu, Hyoungseob Park, Stefano Soatto, Dong Lao, Alex Wong:
AugUndo: Scaling Up Augmentations for Monocular Depth Completion and Estimation. ECCV (64) 2024: 274-293 - [c262]Dong Lao, Fengyu Yang, Daniel Wang, Hyoungseob Park, Samuel Lu, Alex Wong, Stefano Soatto:
On the Viability of Monocular Depth Pre-training for Semantic Segmentation. ECCV (37) 2024: 340-357 - [c261]Sungnyun Kim, Haofu Liao, Srikar Appalaraju, Peng Tang, Zhuowen Tu, Ravi Kumar Satzoda, R. Manmatha, Vijay Mahadevan, Stefano Soatto:
DocKD: Knowledge Distillation from LLMs for Open-World Document Understanding Models. EMNLP 2024: 3167-3193 - [c260]Michael Kleinman, Alessandro Achille, Stefano Soatto:
Critical Learning Periods Emerge Even in Deep Linear Networks. ICLR 2024 - [c259]Tian Yu Liu, Aditya Golatkar, Stefano Soatto:
Tangent Transformers for Composition, Privacy and Removal. ICLR 2024 - [c258]Tian Yu Liu, Matthew Trager, Alessandro Achille, Pramuditha Perera, Luca Zancato, Stefano Soatto:
Meaning Representations from Trajectories in Autoregressive Models. ICLR 2024 - [c257]Hantian Ding, Zijian Wang, Giovanni Paolini, Varun Kumar, Anoop Deoras, Dan Roth, Stefano Soatto:
Fewer Truncations Improve Language Modeling. ICML 2024 - [c256]Dong Lao, Yangchao Wu, Tian Yu Liu, Alex Wong, Stefano Soatto:
Sub-token ViT Embedding via Stochastic Resonance Transformers. ICML 2024 - [i172]Alessandro Achille, Greg Ver Steeg, Tian Yu Liu, Matthew Trager, Carson Klingenberg, Stefano Soatto:
Interpretable Measures of Conceptual Similarity by Complexity-Constrained Descriptive Auto-Encoding. CoRR abs/2402.08919 (2024) - [i171]Xiaohan Fei, Chethan Parameshwara, Jiawei Mo, Xiaolong Li, Ashwin Swaminathan, CJ Taylor, Paolo Favaro, Stefano Soatto:
A Quantitative Evaluation of Score Distillation Sampling Based Text-to-3D. CoRR abs/2402.18780 (2024) - [i170]Kunyu Shi, Qi Dong, Luis Goncalves, Zhuowen Tu, Stefano Soatto:
Non-autoregressive Sequence-to-Sequence Vision-Language Models. CoRR abs/2403.02249 (2024) - [i169]Yuan Gao, Kunyu Shi, Pengkai Zhu, Edouard Belval, Oren Nuriel, Srikar Appalaraju, Shabnam Ghadar, Vijay Mahadevan, Zhuowen Tu, Stefano Soatto:
Enhancing Vision-Language Pre-training with Rich Supervisions. CoRR abs/2403.03346 (2024) - [i168]Ziqi Lu, Jianbo Ye, Xiaohan Fei, Xiaolong Li, Jiawei Mo, Ashwin Swaminathan, Stefano Soatto:
Fast Sparse View Guided NeRF Update for Object Reconfigurations. CoRR abs/2403.11024 (2024) - [i167]Alessandro Favero, Luca Zancato, Matthew Trager, Siddharth Choudhary, Pramuditha Perera, Alessandro Achille, Ashwin Swaminathan, Stefano Soatto:
Multi-Modal Hallucination Control by Visual Information Grounding. CoRR abs/2403.14003 (2024) - [i166]Aditya Golatkar, Alessandro Achille, Luca Zancato, Yu-Xiang Wang, Ashwin Swaminathan, Stefano Soatto:
CPR: Retrieval Augmented Generation for Copyright Protection. CoRR abs/2403.18920 (2024) - [i165]Matteo Marchi, Stefano Soatto, Pratik Chaudhari, Paulo Tabuada:
Heat Death of Generative Models in Closed-Loop Learning. CoRR abs/2404.02325 (2024) - [i164]Hao Li, Yang Zou, Ying Wang, Orchid Majumder, Yusheng Xie, R. Manmatha, Ashwin Swaminathan, Zhuowen Tu, Stefano Ermon, Stefano Soatto:
On the Scalability of Diffusion-based Text-to-Image Generation. CoRR abs/2404.02883 (2024) - [i163]Ziyao Zeng, Daniel Wang, Fengyu Yang, Hyoungseob Park, Yangchao Wu, Stefano Soatto, Byung-Woo Hong, Dong Lao, Alex Wong:
WorDepth: Variational Language Prior for Monocular Depth Estimation. CoRR abs/2404.03635 (2024) - [i162]Pei Wang, Zhaowei Cai, Hao Yang, Ashwin Swaminathan, R. Manmatha, Stefano Soatto:
Mixed-Query Transformer: A Unified Image Segmentation Architecture. CoRR abs/2404.04469 (2024) - [i161]Hantian Ding, Zijian Wang, Giovanni Paolini, Varun Kumar, Anoop Deoras, Dan Roth, Stefano Soatto:
Fewer Truncations Improve Language Modeling. CoRR abs/2404.10830 (2024) - [i160]Xiaolong Li, Jiawei Mo, Ying Wang, Chethan Parameshwara, Xiaohan Fei, Ashwin Swaminathan, CJ Taylor, Zhuowen Tu, Paolo Favaro, Stefano Soatto:
Grounded Compositional and Diverse Text-to-3D with Pretrained Multi-View Diffusion Model. CoRR abs/2404.18065 (2024) - [i159]Benet Oriol Sabat, Alessandro Achille, Matthew Trager, Stefano Soatto:
NeRF-Insert: 3D Local Editing with Multimodal Control Signals. CoRR abs/2404.19204 (2024) - [i158]Dong Lao, Congli Wang, Alex Wong, Stefano Soatto:
Diffeomorphic Template Registration for Atmospheric Turbulence Mitigation. CoRR abs/2405.03662 (2024) - [i157]Prannay Kaul, Zhizhong Li, Hao Yang, Yonatan Dukler, Ashwin Swaminathan, C. J. Taylor, Stefano Soatto:
THRONE: An Object-based Hallucination Benchmark for the Free-form Generations of Large Vision-Language Models. CoRR abs/2405.05256 (2024) - [i156]Tian Yu Liu, Stefano Soatto, Matteo Marchi, Pratik Chaudhari, Paulo Tabuada:
Meanings and Feelings of Large Language Models: Observability of Latent States in Generative AI. CoRR abs/2405.14061 (2024) - [i155]Evan Becker, Stefano Soatto:
Cycles of Thought: Measuring LLM Confidence through Stable Explanations. CoRR abs/2406.03441 (2024) - [i154]Benjamin Biggs, Arjun Seshadri, Yang Zou, Achin Jain, Aditya Golatkar, Yusheng Xie, Alessandro Achille, Ashwin Swaminathan, Stefano Soatto:
Diffusion Soup: Model Merging for Text-to-Image Diffusion Models. CoRR abs/2406.08431 (2024) - [i153]Luca Zancato, Arjun Seshadri, Yonatan Dukler, Aditya Golatkar, Yantao Shen, Benjamin Bowman, Matthew Trager, Alessandro Achille, Stefano Soatto:
B'MOJO: Hybrid State Space Realizations of Foundation Models with Eidetic and Fading Memory. CoRR abs/2407.06324 (2024) - [i152]Matthew Trager, Alessandro Achille, Pramuditha Perera, Luca Zancato, Stefano Soatto:
Compositional Structures in Neural Embedding and Interaction Decompositions. CoRR abs/2407.08934 (2024) - [i151]Chaofan Tao, Gukyeong Kwon, Varad Gunjal, Hao Yang, Zhaowei Cai, Yonatan Dukler, Ashwin Swaminathan, R. Manmatha, Colin J. Taylor, Stefano Soatto:
NAVERO: Unlocking Fine-Grained Semantics for Video-Language Compositionality. CoRR abs/2408.09511 (2024) - [i150]Ziyao Zeng, Yangchao Wu, Hyoungseob Park, Daniel Wang, Fengyu Yang, Stefano Soatto, Dong Lao, Byung-Woo Hong, Alex Wong:
RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language Descriptions. CoRR abs/2410.02924 (2024) - [i149]Sungnyun Kim, Haofu Liao, Srikar Appalaraju, Peng Tang, Zhuowen Tu, Ravi Kumar Satzoda, R. Manmatha, Vijay Mahadevan, Stefano Soatto:
DocKD: Knowledge Distillation from LLMs for Open-World Document Understanding Models. CoRR abs/2410.03061 (2024) - [i148]Tian Yu Liu, Stefano Soatto:
Conjuring Semantic Similarity. CoRR abs/2410.16431 (2024) - 2023
- [j67]Achuta Kadambi, Celso de Melo, Cho-Jui Hsieh, Mani B. Srivastava, Stefano Soatto:
Incorporating physics into data-driven computer vision. Nat. Mac. Intell. 5(6): 572-580 (2023) - [c255]Shay Deutsch, Stefano Soatto:
Graph Spectral Embedding using the Geodesic Betweenness Centrality. AISTATS 2023: 10505-10519 - [c254]Achin Jain, Gurumurthy Swaminathan, Paolo Favaro, Hao Yang, Avinash Ravichandran, Hrayr Harutyunyan, Alessandro Achille, Onkar Dabeer, Bernt Schiele, Ashwin Swaminathan, Stefano Soatto:
A Meta-Learning Approach to Predicting Performance and Data Requirements. CVPR 2023: 3623-3632 - [c253]Hao Li, Charless C. Fowlkes, Hao Yang, Onkar Dabeer, Zhuowen Tu, Stefano Soatto:
Guided Recommendation for Model Fine-Tuning. CVPR 2023: 3633-3642 - [c252]Akash Deep Singh, Yunhao Ba, Ankur Sarker, Howard Zhang, Achuta Kadambi, Stefano Soatto, Mani B. Srivastava, Alex Wong:
Depth Estimation from Camera Image and mmWave Radar Point Cloud. CVPR 2023: 9275-9285 - [c251]Benjamin Bowman, Alessandro Achille, Luca Zancato, Matthew Trager, Pramuditha Perera, Giovanni Paolini, Stefano Soatto:
À-la-carte Prompt Tuning (APT): Combining Distinct Data Via Composable Prompting. CVPR 2023: 14984-14993 - [c250]Luca Zancato, Alessandro Achille, Tian Yu Liu, Matthew Trager, Pramuditha Perera, Stefano Soatto:
Train/Test-Time Adaptation with Retrieval. CVPR 2023: 15911-15921 - [c249]Michael Kleinman, Alessandro Achille, Stefano Soatto:
Critical Learning Periods for Multisensory Integration in Deep Networks. CVPR 2023: 24296-24305 - [c248]Matthew Trager, Pramuditha Perera, Luca Zancato, Alessandro Achille, Parminder Bhatia, Stefano Soatto:
Linear Spaces of Meanings: Compositional Structures in Vision-Language Models. ICCV 2023: 15349-15358 - [c247]Yonatan Dukler, Benjamin Bowman, Alessandro Achille, Aditya Golatkar, Ashwin Swaminathan, Stefano Soatto:
SAFE: Machine Unlearning With Shard Graphs. ICCV 2023: 17062-17072 - [c246]Tian Yu Liu, Stefano Soatto:
Tangent Model Composition for Ensembling and Continual Fine-tuning. ICCV 2023: 18630-18640 - [c245]Gukyeong Kwon, Zhaowei Cai, Avinash Ravichandran, Erhan Bas, Rahul Bhotika, Stefano Soatto:
Masked Vision and Language Modeling for Multi-modal Representation Learning. ICLR 2023 - [c244]Yonatan Dukler, Alessandro Achille, Hao Yang, Varsha Vivek, Luca Zancato, Benjamin Bowman, Avinash Ravichandran, Charless C. Fowlkes, Ashwin Swaminathan, Stefano Soatto:
Your representations are in the network: composable and parallel adaptation for large scale models. NeurIPS 2023 - [c243]Marco Fumero, Florian Wenzel, Luca Zancato, Alessandro Achille, Emanuele Rodolà, Stefano Soatto, Bernhard Schölkopf, Francesco Locatello:
Leveraging sparse and shared feature activations for disentangled representation learning. NeurIPS 2023 - [c242]Michael Kleinman, Alessandro Achille, Stefano Soatto, Jonathan C. Kao:
Gacs-Korner Common Information Variational Autoencoder. NeurIPS 2023 - [c241]Siqi Deng, Yuanjun Xiong, Meng Wang, Wei Xia, Stefano Soatto:
Harnessing Unrecognizable Faces for Improving Face Recognition. WACV 2023: 3413-3422 - [i147]Benjamin Bowman, Alessandro Achille, Luca Zancato, Matthew Trager, Pramuditha Perera, Giovanni Paolini, Stefano Soatto:
À-la-carte Prompt Tuning (APT): Combining Distinct Data Via Composable Prompting. CoRR abs/2302.07994 (2023) - [i146]Matthew Trager, Pramuditha Perera, Luca Zancato, Alessandro Achille, Parminder Bhatia, Bing Xiang, Stefano Soatto:
Linear Spaces of Meanings: the Compositional Language of VLMs. CoRR abs/2302.14383 (2023) - [i145]Achin Jain, Gurumurthy Swaminathan, Paolo Favaro, Hao Yang, Avinash Ravichandran, Hrayr Harutyunyan, Alessandro Achille, Onkar Dabeer, Bernt Schiele, Ashwin Swaminathan, Stefano Soatto:
A Meta-Learning Approach to Predicting Performance and Data Requirements. CoRR abs/2303.01598 (2023) - [i144]Yonatan Dukler, Alessandro Achille, Hao Yang, Varsha Vivek, Luca Zancato, Benjamin Bowman, Avinash Ravichandran, Charless C. Fowlkes, Ashwin Swaminathan, Stefano Soatto:
Introspective Cross-Attention Probing for Lightweight Transfer of Pre-trained Models. CoRR abs/2303.04105 (2023) - [i143]Stephanie Tsuei, Wenjie Mo, Stefano Soatto:
Feature Tracks are not Zero-Mean Gaussian. CoRR abs/2303.14315 (2023) - [i142]Luca Zancato, Alessandro Achille, Tian Yu Liu, Matthew Trager, Pramuditha Perera, Stefano Soatto:
Train/Test-Time Adaptation with Retrieval. CoRR abs/2303.14333 (2023) - [i141]Stephanie Tsuei, Stefano Soatto:
Quantifying VIO Uncertainty. CoRR abs/2303.16386 (2023) - [i140]Dong Lao, Zhengyang Hu, Francesco Locatello, Yanchao Yang, Stefano Soatto:
Divided Attention: Unsupervised Multi-Object Discovery with Contextually Separated Slots. CoRR abs/2304.01430 (2023) - [i139]Alessandro Achille, Michael Kearns, Carson Klingenberg, Stefano Soatto:
AI Model Disgorgement: Methods and Choices. CoRR abs/2304.03545 (2023) - [i138]Marco Fumero, Florian Wenzel, Luca Zancato, Alessandro Achille, Emanuele Rodolà, Stefano Soatto, Bernhard Schölkopf, Francesco Locatello:
Leveraging sparse and shared feature activations for disentangled representation learning. CoRR abs/2304.07939 (2023) - [i137]Yonatan Dukler, Benjamin Bowman, Alessandro Achille, Aditya Golatkar, Ashwin Swaminathan, Stefano Soatto:
SAFE: Machine Unlearning With Shard Graphs. CoRR abs/2304.13169 (2023) - [i136]Zhaoyang Zhang, Yantao Shen, Kunyu Shi, Zhaowei Cai, Jun Fang, Siqi Deng, Hao Yang, Davide Modolo, Zhuowen Tu, Stefano Soatto:
Musketeer (All for One, and One for All): A Generalist Vision-Language Model with Task Explanation Prompts. CoRR abs/2305.07019 (2023) - [i135]Stefano Soatto, Paulo Tabuada, Pratik Chaudhari, Tian Yu Liu:
Taming AI Bots: Controllability of Neural States in Large Language Models. CoRR abs/2305.18449 (2023) - [i134]Pramuditha Perera, Matthew Trager, Luca Zancato, Alessandro Achille, Stefano Soatto:
Prompt Algebra for Task Composition. CoRR abs/2306.00310 (2023) - [i133]Chethan Parameshwara, Alessandro Achille, Matthew Trager, Xiaolong Li, Jiawei Mo, Ashwin Swaminathan, CJ Taylor, Dheera Venkatraman, Xiaohan Fei, Stefano Soatto:
Towards Visual Foundational Models of Physical Scenes. CoRR abs/2306.03727 (2023) - [i132]Tian Yu Liu, Stefano Soatto:
Tangent Model Composition for Ensembling and Continual Fine-tuning. CoRR abs/2307.08114 (2023) - [i131]Tian Yu Liu, Aditya Golatkar, Stefano Soatto:
Tangent Transformers for Composition, Privacy and Removal. CoRR abs/2307.08122 (2023) - [i130]Aditya Golatkar, Alessandro Achille, Ashwin Swaminathan, Stefano Soatto:
Training Data Protection with Compositional Diffusion Models. CoRR abs/2308.01937 (2023) - [i129]Michael Kleinman, Alessandro Achille, Stefano Soatto:
Critical Learning Periods Emerge Even in Deep Linear Networks. CoRR abs/2308.12221 (2023) - [i128]Dong Lao, Yangchao Wu, Tian Yu Liu, Alex Wong, Stefano Soatto:
Sub-token ViT Embedding via Stochastic Resonance Transformers. CoRR abs/2310.03967 (2023) - [i127]Yangchao Wu, Tian Yu Liu, Hyoungseob Park, Stefano Soatto, Dong Lao, Alex Wong:
AugUndo: Scaling Up Augmentations for Unsupervised Depth Completion. CoRR abs/2310.09739 (2023) - [i126]Tian Yu Liu, Matthew Trager, Alessandro Achille, Pramuditha Perera, Luca Zancato, Stefano Soatto:
Meaning Representations from Trajectories in Autoregressive Models. CoRR abs/2310.18348 (2023) - 2022
- [j66]Kensuke Nakamura, Stefano Soatto, Byung-Woo Hong:
Stochastic batch size for adaptive regularization in deep network optimization. Pattern Recognit. 129: 108776 (2022) - [c240]Matthew Wallingford, Hao Li, Alessandro Achille, Avinash Ravichandran, Charless C. Fowlkes, Rahul Bhotika, Stefano Soatto:
Task Adaptive Parameter Sharing for Multi-Task Learning. CVPR 2022: 7551-7560 - [c239]Jiarui Cai, Mingze Xu, Wei Li, Yuanjun Xiong, Wei Xia, Zhuowen Tu, Stefano Soatto:
MeMOT: Multi-Object Tracking with Memory. CVPR 2022: 8080-8090 - [c238]Aditya Golatkar, Alessandro Achille, Yu-Xiang Wang, Aaron Roth, Michael Kearns, Stefano Soatto:
Mixed Differential Privacy in Computer Vision. CVPR 2022: 8366-8376 - [c237]Pei Wang, Zhaowei Cai, Hao Yang, Gurumurthy Swaminathan, Nuno Vasconcelos, Bernt Schiele, Stefano Soatto:
Omni-DETR: Omni-Supervised Object Detection with Transformers. CVPR 2022: 9357-9366 - [c236]Tz-Ying Wu, Gurumurthy Swaminathan, Zhizhong Li, Avinash Ravichandran, Nuno Vasconcelos, Rahul Bhotika, Stefano Soatto:
Class-Incremental Learning with Strong Pre-trained Models. CVPR 2022: 9591-9600 - [c235]Zachary Berger, Parth Agrawal, Tian Yu Liu, Stefano Soatto, Alex Wong:
Stereoscopic Universal Perturbations across Different Architectures and Datasets. CVPR 2022: 15159-15169 - [c234]Zhaowei Cai, Gukyeong Kwon, Avinash Ravichandran, Erhan Bas, Zhuowen Tu, Rahul Bhotika, Stefano Soatto:
X-DETR: A Versatile Architecture for Instance-wise Vision-Language Tasks. ECCV (36) 2022: 290-308 - [c233]Yunhao Ba, Howard Zhang, Ethan Yang, Akira Suzuki, Arnold Pfahnl, Chethan Chinder Chandrappa, Celso M. de Melo, Suya You, Stefano Soatto, Alex Wong, Achuta Kadambi:
Not Just Streaks: Towards Ground Truth for Single Image Deraining. ECCV (7) 2022: 723-740 - [c232]Yonatan Dukler, Alessandro Achille, Giovanni Paolini, Avinash Ravichandran, Marzia Polito, Stefano Soatto:
DIVA: Dataset Derivative of a Learning Task. ICLR 2022 - [c231]Zhaowei Cai, Avinash Ravichandran, Paolo Favaro, Manchen Wang, Davide Modolo, Rahul Bhotika, Zhuowen Tu, Stefano Soatto:
Semi-supervised Vision Transformers at Scale. NeurIPS 2022 - [c230]Mohamad Rida Rammal, Alessandro Achille, Aditya Golatkar, Suhas N. Diggavi, Stefano Soatto:
On Leave-One-Out Conditional Mutual Information For Generalization. NeurIPS 2022 - [i125]Pengkai Zhu, Zhaowei Cai, Yuanjun Xiong, Zhuowen Tu, Luis Goncalves, Vijay Mahadevan, Stefano Soatto:
Contrastive Neighborhood Alignment. CoRR abs/2201.01922 (2022) - [i124]Luca Zancato, Alessandro Achille, Giovanni Paolini, Alessandro Chiuso, Stefano Soatto:
Stacked Residuals of Dynamic Layers for Time Series Anomaly Detection. CoRR abs/2202.12457 (2022) - [i123]Aditya Golatkar, Alessandro Achille, Yu-Xiang Wang, Aaron Roth, Michael Kearns, Stefano Soatto:
Mixed Differential Privacy in Computer Vision. CoRR abs/2203.11481 (2022) - [i122]Dong Lao, Alex Wong, Stefano Soatto:
Does Monocular Depth Estimation Provide Better Pre-training than Classification for Semantic Segmentation? CoRR abs/2203.13987 (2022) - [i121]Pei Wang, Zhaowei Cai, Hao Yang, Gurumurthy Swaminathan, Nuno Vasconcelos, Bernt Schiele, Stefano Soatto:
Omni-DETR: Omni-Supervised Object Detection with Transformers. CoRR abs/2203.16089 (2022) - [i120]Simone Bombari, Alessandro Achille, Zijian Wang, Yu-Xiang Wang, Yusheng Xie, Kunwar Yashraj Singh, Srikar Appalaraju, Vijay Mahadevan, Stefano Soatto:
Towards Differential Relational Privacy and its use in Question Answering. CoRR abs/2203.16701 (2022) - [i119]Matthew Wallingford, Hao Li, Alessandro Achille, Avinash Ravichandran, Charless C. Fowlkes, Rahul Bhotika, Stefano Soatto:
Task Adaptive Parameter Sharing for Multi-Task Learning. CoRR abs/2203.16708 (2022) - [i118]Jiarui Cai, Mingze Xu, Wei Li, Yuanjun Xiong, Wei Xia, Zhuowen Tu, Stefano Soatto:
MeMOT: Multi-Object Tracking with Memory. CoRR abs/2203.16761 (2022) - [i117]Tz-Ying Wu, Gurumurthy Swaminathan, Zhizhong Li, Avinash Ravichandran, Nuno Vasconcelos, Rahul Bhotika, Stefano Soatto:
Class-Incremental Learning with Strong Pre-trained Models. CoRR abs/2204.03634 (2022) - [i116]Zhaowei Cai, Gukyeong Kwon, Avinash Ravichandran, Erhan Bas, Zhuowen Tu, Rahul Bhotika, Stefano Soatto:
X-DETR: A Versatile Architecture for Instance-wise Vision-Language Tasks. CoRR abs/2204.05626 (2022) - [i115]Shay Deutsch, Stefano Soatto:
Graph Spectral Embedding using the Geodesic Betweeness Centrality. CoRR abs/2205.03544 (2022) - [i114]Yue Zhao, Yantao Shen, Yuanjun Xiong, Shuo Yang, Wei Xia, Zhuowen Tu, Bernt Schiele, Stefano Soatto:
ELODI: Ensemble Logit Difference Inhibition for Positive-Congruent Training. CoRR abs/2205.06265 (2022) - [i113]Michael Kleinman, Alessandro Achille, Stefano Soatto, Jonathan C. Kao:
Gacs-Korner Common Information Variational Autoencoder. CoRR abs/2205.12239 (2022) - [i112]Yunhao Ba, Howard Zhang, Ethan Yang, Akira Suzuki, Arnold Pfahnl, Chethan Chinder Chandrappa, Celso de Melo, Suya You, Stefano Soatto, Alex Wong, Achuta Kadambi:
Towards Ground Truth for Single Image Deraining. CoRR abs/2206.10779 (2022) - [i111]Mohamad Rida Rammal, Alessandro Achille, Aditya Golatkar, Suhas N. Diggavi, Stefano Soatto:
On Leave-One-Out Conditional Mutual Information For Generalization. CoRR abs/2207.00581 (2022) - [i110]Alessandro Achille, Stefano Soatto:
On Binding Objects to Symbols: Learning Physical Concepts to Understand Real from Fake. CoRR abs/2207.12186 (2022) - [i109]Gukyeong Kwon, Zhaowei Cai, Avinash Ravichandran, Erhan Bas, Rahul Bhotika, Stefano Soatto:
Masked Vision and Language Modeling for Multi-modal Representation Learning. CoRR abs/2208.02131 (2022) - [i108]Zhaowei Cai, Avinash Ravichandran, Paolo Favaro, Manchen Wang, Davide Modolo, Rahul Bhotika, Zhuowen Tu, Stefano Soatto:
Semi-supervised Vision Transformers at Scale. CoRR abs/2208.05688 (2022) - [i107]Michael Kleinman, Alessandro Achille, Stefano Soatto:
Critical Learning Periods for Multisensory Integration in Deep Networks. CoRR abs/2210.04643 (2022) - [i106]Alexandre Tiard, Alex Wong, David Joon Ho, Yangchao Wu, Eliram Nof, Stefano Soatto, Saad Nadeem:
Stain-invariant self supervised learning for histopathology image analysis. CoRR abs/2211.07590 (2022) - [i105]Tian Yu Liu, Aditya Golatkar, Stefano Soatto, Alessandro Achille:
Integral Continual Learning Along the Tangent Vector Field of Tasks. CoRR abs/2211.13108 (2022) - 2021
- [j65]Michael Kleinman, Alessandro Achille, Stefano Soatto, Jonathan C. Kao:
Redundant Information Neural Estimation. Entropy 23(7): 922 (2021) - [j64]Kensuke Nakamura, Stefano Soatto, Byung-Woo Hong:
Block-cyclic stochastic coordinate descent for deep neural networks. Neural Networks 139: 348-357 (2021) - [j63]Alex Wong, Safa Cicek, Stefano Soatto:
Learning Topology From Synthetic Data for Unsupervised Depth Completion. IEEE Robotics Autom. Lett. 6(2): 1495-1502 (2021) - [j62]Alex Wong, Xiaohan Fei, Byung-Woo Hong, Stefano Soatto:
An Adaptive Framework for Learning Unsupervised Depth Completion. IEEE Robotics Autom. Lett. 6(2): 3120-3127 (2021) - [j61]Alexander Schperberg, Stephanie Tsuei, Stefano Soatto, Dennis W. Hong:
SABER: Data-Driven Motion Planner for Autonomously Navigating Heterogeneous Robots. IEEE Robotics Autom. Lett. 6(4): 8086-8093 (2021) - [c229]Alex Wong, Mukund Mundhra, Stefano Soatto:
Stereopagnosia: Fooling Stereo Networks with Adversarial Perturbations. AAAI 2021: 2879-2888 - [c228]Lanlan Liu, Yuting Zhang, Jia Deng, Stefano Soatto:
Dynamically Grown Generative Adversarial Networks. AAAI 2021: 8680-8687 - [c227]Yuqing Xie, Yi-An Lai, Yuanjun Xiong, Yi Zhang, Stefano Soatto:
Regression Bugs Are In Your Model! Measuring, Reducing and Analyzing Regressions In NLP Model Updates. ACL/IJCNLP (1) 2021: 6589-6602 - [c226]Alex Wong, Allison Chen, Yangchao Wu, Safa Cicek, Alexandre Tiard, Byung-Woo Hong, Stefano Soatto:
Small Lesion Segmentation in Brain MRIs with Subpixel Embedding. BrainLes@MICCAI (1) 2021: 75-87 - [c225]Zhaowei Cai, Avinash Ravichandran, Subhransu Maji, Charless C. Fowlkes, Zhuowen Tu, Stefano Soatto:
Exponential Moving Average Normalization for Self-Supervised and Semi-Supervised Learning. CVPR 2021: 194-203 - [c224]Aditya Golatkar, Alessandro Achille, Avinash Ravichandran, Marzia Polito, Stefano Soatto:
Mixed-Privacy Forgetting in Deep Networks. CVPR 2021: 792-801 - [c223]Xinzhu Bei, Yanchao Yang, Stefano Soatto:
Learning Semantic-Aware Dynamics for Video Prediction. CVPR 2021: 902-912 - [c222]Yanchao Yang, Brian Lai, Stefano Soatto:
DyStaB: Unsupervised Object Segmentation via Dynamic-Static Bootstrapping. CVPR 2021: 2826-2836 - [c221]Rahul Duggal, Hao Zhou, Shuo Yang, Yuanjun Xiong, Wei Xia, Zhuowen Tu, Stefano Soatto:
Compatibility-Aware Heterogeneous Visual Search. CVPR 2021: 10723-10732 - [c220]Sijie Yan, Yuanjun Xiong, Kaustav Kundu, Shuo Yang, Siqi Deng, Meng Wang, Wei Xia, Stefano Soatto:
Positive-Congruent Training: Towards Regression-Free Model Updates. CVPR 2021: 14299-14308 - [c219]Alessandro Achille, Aditya Golatkar, Avinash Ravichandran, Marzia Polito, Stefano Soatto:
LQF: Linear Quadratic Fine-Tuning. CVPR 2021: 15729-15739 - [c218]Yifan Xing, Tong He, Tianjun Xiao, Yongxin Wang, Yuanjun Xiong, Wei Xia, David Wipf, Zheng Zhang, Stefano Soatto:
Learning Hierarchical Graph Neural Networks for Image Clustering. ICCV 2021: 3447-3457 - [c217]Qi Dong, Zhuowen Tu, Haofu Liao, Yuting Zhang, Vijay Mahadevan, Stefano Soatto:
Visual Relationship Detection Using Part-and-Sum Transformers with Composite Queries. ICCV 2021: 3530-3539 - [c216]Tong He, Yuanlu Xu, Shunsuke Saito, Stefano Soatto, Tony Tung:
ARCH++: Animation-Ready Clothed Human Reconstruction Revisited. ICCV 2021: 11026-11036 - [c215]Alex Wong, Stefano Soatto:
Unsupervised Depth Completion with Calibrated Backprojection Layers. ICCV 2021: 12727-12736 - [c214]Hrayr Harutyunyan, Alessandro Achille, Giovanni Paolini, Orchid Majumder, Avinash Ravichandran, Rahul Bhotika, Stefano Soatto:
Estimating informativeness of samples with Smooth Unique Information. ICLR 2021 - [c213]Giovanni Paolini, Ben Athiwaratkun, Jason Krone, Jie Ma, Alessandro Achille, Rishita Anubhai, Cícero Nogueira dos Santos, Bing Xiang, Stefano Soatto:
Structured Prediction as Translation between Augmented Natural Languages. ICLR 2021 - [c212]Stephanie Tsuei, Stefano Soatto, Paulo Tabuada, Mark B. Milam:
Learned Uncertainty Calibration for Visual Inertial Localization. ICRA 2021: 5311-5317 - [c211]Mingze Xu, Yuanjun Xiong, Hao Chen, Xinyu Li, Wei Xia, Zhuowen Tu, Stefano Soatto:
Long Short-Term Transformer for Online Action Detection. NeurIPS 2021: 1086-1099 - [c210]Sébastien M. R. Arnold, Guneet S. Dhillon, Avinash Ravichandran, Stefano Soatto:
Uniform Sampling over Episode Difficulty. NeurIPS 2021: 1481-1493 - [i104]Giovanni Paolini, Ben Athiwaratkun, Jason Krone, Jie Ma, Alessandro Achille, Rishita Anubhai, Cícero Nogueira dos Santos, Bing Xiang, Stefano Soatto:
Structured Prediction as Translation between Augmented Natural Languages. CoRR abs/2101.05779 (2021) - [i103]Hrayr Harutyunyan, Alessandro Achille, Giovanni Paolini, Orchid Majumder, Avinash Ravichandran, Rahul Bhotika, Stefano Soatto:
Estimating informativeness of samples with Smooth Unique Information. CoRR abs/2101.06640 (2021) - [i102]Zhaowei Cai, Avinash Ravichandran, Subhransu Maji, Charless C. Fowlkes, Zhuowen Tu, Stefano Soatto:
Exponential Moving Average Normalization for Self-supervised and Semi-supervised Learning. CoRR abs/2101.08482 (2021) - [i101]Orchid Majumder, Avinash Ravichandran, Subhransu Maji, Marzia Polito, Rahul Bhotika, Stefano Soatto:
Revisiting Contrastive Learning for Few-Shot Classification. CoRR abs/2101.11058 (2021) - [i100]Aditya Deshpande, Alessandro Achille, Avinash Ravichandran, Hao Li, Luca Zancato, Charless C. Fowlkes, Rahul Bhotika, Stefano Soatto, Pietro Perona:
A linearized framework and a new benchmark for model selection for fine-tuning. CoRR abs/2102.00084 (2021) - [i99]Xinzhu Bei, Yanchao Yang, Stefano Soatto:
Learning Semantic-Aware Dynamics for Video Prediction. CoRR abs/2104.09762 (2021) - [i98]Qi Dong, Zhuowen Tu, Haofu Liao, Yuting Zhang, Vijay Mahadevan, Stefano Soatto:
Visual Composite Set Detection Using Part-and-Sum Transformers. CoRR abs/2105.02170 (2021) - [i97]Yuqing Xie, Yi-An Lai, Yuanjun Xiong, Yi Zhang, Stefano Soatto:
Regression Bugs Are In Your Model! Measuring, Reducing and Analyzing Regressions In NLP Model Updates. CoRR abs/2105.03048 (2021) - [i96]Rahul Duggal, Hao Zhou, Shuo Yang, Yuanjun Xiong, Wei Xia, Zhuowen Tu, Stefano Soatto:
Compatibility-aware Heterogeneous Visual Search. CoRR abs/2105.06047 (2021) - [i95]Alex Wong, Safa Cicek, Stefano Soatto:
Learning Topology from Synthetic Data for Unsupervised Depth Completion. CoRR abs/2106.02994 (2021) - [i94]Alex Wong, Xiaohan Fei, Byung-Woo Hong, Stefano Soatto:
An Adaptive Framework for Learning Unsupervised Depth Completion. CoRR abs/2106.03010 (2021) - [i93]Siqi Deng, Yuanjun Xiong, Meng Wang, Wei Xia, Stefano Soatto:
Harnessing Unrecognizable Faces for Face Recognition. CoRR abs/2106.04112 (2021) - [i92]Lanlan Liu, Yuting Zhang, Jia Deng, Stefano Soatto:
Dynamically Grown Generative Adversarial Networks. CoRR abs/2106.08505 (2021) - [i91]Stephanie Tsuei, Aditya Golatkar, Stefano Soatto:
Scene Uncertainty and the Wellington Posterior of Deterministic Image Classifiers. CoRR abs/2106.13870 (2021) - [i90]Yifan Xing, Tong He, Tianjun Xiao, Yongxin Wang, Yuanjun Xiong, Wei Xia, David Wipf, Zheng Zhang, Stefano Soatto:
Learning Hierarchical Graph Neural Networks for Image Clustering. CoRR abs/2107.01319 (2021) - [i89]Mingze Xu, Yuanjun Xiong, Hao Chen, Xinyu Li, Wei Xia, Zhuowen Tu, Stefano Soatto:
Long Short-Term Transformer for Online Action Detection. CoRR abs/2107.03377 (2021) - [i88]Zhizhong Li, Avinash Ravichandran, Charless C. Fowlkes, Marzia Polito, Rahul Bhotika, Stefano Soatto:
Representation Consolidation for Training Expert Students. CoRR abs/2107.08039 (2021) - [i87]Alexander Schperberg, Stephanie Tsuei, Stefano Soatto, Dennis W. Hong:
SABER: Data-Driven Motion Planner for Autonomously Navigating Heterogeneous Robots. CoRR abs/2108.01262 (2021) - [i86]Sébastien M. R. Arnold, Guneet S. Dhillon, Avinash Ravichandran, Stefano Soatto:
Uniform Sampling over Episode Difficulty. CoRR abs/2108.01662 (2021) - [i85]Tong He, Yuanlu Xu, Shunsuke Saito, Stefano Soatto, Tony Tung:
ARCH++: Animation-Ready Clothed Human Reconstruction Revisited. CoRR abs/2108.07845 (2021) - [i84]Alex Wong, Stefano Soatto:
Unsupervised Depth Completion with Calibrated Backprojection Layers. CoRR abs/2108.10531 (2021) - [i83]Alex Wong, Allison Chen, Yangchao Wu, Safa Cicek, Alexandre Tiard, Byung-Woo Hong, Stefano Soatto:
Small Lesion Segmentation in Brain MRIs with Subpixel Embedding. CoRR abs/2109.08791 (2021) - [i82]Stephanie Tsuei, Stefano Soatto, Paulo Tabuada, Mark B. Milam:
Learned Uncertainty Calibration for Visual Inertial Localization. CoRR abs/2110.02136 (2021) - [i81]Yonatan Dukler, Alessandro Achille, Giovanni Paolini, Avinash Ravichandran, Marzia Polito, Stefano Soatto:
DIVA: Dataset Derivative of a Learning Task. CoRR abs/2111.09785 (2021) - [i80]Zachary Berger, Parth Agrawal, Tian Yu Liu, Stefano Soatto, Alex Wong:
Stereoscopic Universal Perturbations across Different Architectures and Datasets. CoRR abs/2112.06116 (2021) - 2020
- [j60]Rita Fioresi, Pratik Chaudhari, Stefano Soatto:
A Geometric Interpretation of Stochastic Gradient Descent Using Diffusion Metrics. Entropy 22(1): 101 (2020) - [j59]Alex Wong, Xiaohan Fei, Stephanie Tsuei, Stefano Soatto:
Unsupervised Depth Completion From Visual Inertial Odometry. IEEE Robotics Autom. Lett. 5(2): 1899-1906 (2020) - [j58]Byung-Woo Hong, Ja-Keoung Koo, Martin Burger, Stefano Soatto:
Adaptive Regularization of Some Inverse Problems in Image Analysis. IEEE Trans. Image Process. 29: 2507-2521 (2020) - [c209]Shay Deutsch, Andrea L. Bertozzi, Stefano Soatto:
Zero Shot Learning with the Isoperimetric Loss. AAAI 2020: 10704-10712 - [c208]Tong He, John P. Collomosse, Hailin Jin, Stefano Soatto:
DeepVoxels++: Enhancing the Fidelity of Novel View Synthesis from 3D Voxel Embeddings. ACCV (1) 2020: 244-260 - [c207]Safa Cicek, Ning Xu, Zhaowen Wang, Hailin Jin, Stefano Soatto:
Spatial Class Distribution Shift in Unsupervised Domain Adaptation: Local Alignment Comes to Rescue. ACCV (3) 2020: 623-638 - [c206]Albert Zhao, Tong He, Yitao Liang, Haibin Huang, Guy Van den Broeck, Stefano Soatto:
SAM: Squeeze-and-Mimic Networks for Conditional Visual Driving Policy Learning. CoRL 2020: 156-175 - [c205]Yanchao Yang, Stefano Soatto:
FDA: Fourier Domain Adaptation for Semantic Segmentation. CVPR 2020: 4084-4094 - [c204]Yantao Shen, Yuanjun Xiong, Wei Xia, Stefano Soatto:
Towards Backward-Compatible Representation Learning. CVPR 2020: 6367-6376 - [c203]Yanchao Yang, Yutong Chen, Stefano Soatto:
Learning to Manipulate Individual Objects in an Image. CVPR 2020: 6557-6566 - [c202]Yanchao Yang, Dong Lao, Ganesh Sundaramoorthi, Stefano Soatto:
Phase Consistent Ecological Domain Adaptation. CVPR 2020: 9008-9017 - [c201]Aditya Golatkar, Alessandro Achille, Stefano Soatto:
Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks. CVPR 2020: 9301-9309 - [c200]Aditya Golatkar, Alessandro Achille, Stefano Soatto:
Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations. ECCV (29) 2020: 383-398 - [c199]Safa Cicek, Ning Xu, Zhaowen Wang, Hailin Jin, Stefano Soatto:
Disentangled Image Generation for Unsupervised Domain Adaptation. ECCV Workshops (1) 2020: 662-665 - [c198]Qing Liu, Orchid Majumder, Alessandro Achille, Avinash Ravichandran, Rahul Bhotika, Stefano Soatto:
Incremental Few-Shot Meta-learning via Indirect Discriminant Alignment. ECCV (7) 2020: 685-701 - [c197]Guneet Singh Dhillon, Pratik Chaudhari, Avinash Ravichandran, Stefano Soatto:
A Baseline for Few-Shot Image Classification. ICLR 2020 - [c196]Rasool Fakoor, Pratik Chaudhari, Stefano Soatto, Alexander J. Smola:
Meta-Q-Learning. ICLR 2020 - [c195]Hao Li, Pratik Chaudhari, Hao Yang, Michael Lam, Avinash Ravichandran, Rahul Bhotika, Stefano Soatto:
Rethinking the Hyperparameters for Fine-tuning. ICLR 2020 - [c194]Alexander Schperberg, Kenny Chen, Stephanie Tsuei, Michael Jewett, Joshua Hooks, Stefano Soatto, Ankur Mehta, Dennis W. Hong:
Risk-Averse MPC via Visual-Inertial Input and Recurrent Networks for Online Collision Avoidance. IROS 2020: 5730-5737 - [c193]Tong He, John P. Collomosse, Hailin Jin, Stefano Soatto:
Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstruction. NeurIPS 2020 - [c192]Alex Wong, Safa Cicek, Stefano Soatto:
Targeted Adversarial Perturbations for Monocular Depth Prediction. NeurIPS 2020 - [c191]Luca Zancato, Alessandro Achille, Avinash Ravichandran, Rahul Bhotika, Stefano Soatto:
Predicting Training Time Without Training. NeurIPS 2020 - [i79]Qing Liu, Orchid Majumder, Avinash Ravichandran, Rahul Bhotika, Stefano Soatto:
Incremental Learning for Metric-Based Meta-Learners. CoRR abs/2002.04162 (2020) - [i78]Xialei Liu, Hao Yang, Avinash Ravichandran, Rahul Bhotika, Stefano Soatto:
Continual Universal Object Detection. CoRR abs/2002.05347 (2020) - [i77]Hao Li, Pratik Chaudhari, Hao Yang, Michael Lam, Avinash Ravichandran, Rahul Bhotika, Stefano Soatto:
Rethinking the Hyperparameters for Fine-tuning. CoRR abs/2002.11770 (2020) - [i76]Aditya Golatkar, Alessandro Achille, Stefano Soatto:
Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations. CoRR abs/2003.02960 (2020) - [i75]Yantao Shen, Yuanjun Xiong, Wei Xia, Stefano Soatto:
Towards Backward-Compatible Representation Learning. CoRR abs/2003.11942 (2020) - [i74]Yanchao Yang, Dong Lao, Ganesh Sundaramoorthi, Stefano Soatto:
Phase Consistent Ecological Domain Adaptation. CoRR abs/2004.04923 (2020) - [i73]Yanchao Yang, Yutong Chen, Stefano Soatto:
Learning to Manipulate Individual Objects in an Image. CoRR abs/2004.05495 (2020) - [i72]Yanchao Yang, Stefano Soatto:
FDA: Fourier Domain Adaptation for Semantic Segmentation. CoRR abs/2004.05498 (2020) - [i71]Kensuke Nakamura, Stefano Soatto, Byung-Woo Hong:
Stochastic batch size for adaptive regularization in deep network optimization. CoRR abs/2004.06341 (2020) - [i70]Tong He, John P. Collomosse, Hailin Jin, Stefano Soatto:
Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstruction. CoRR abs/2006.08072 (2020) - [i69]Alex Wong, Safa Cicek, Stefano Soatto:
Targeted Adversarial Perturbations for Monocular Depth Prediction. CoRR abs/2006.08602 (2020) - [i68]Alexander Schperberg, Kenny Chen, Stephanie Tsuei, Michael Jewett, Joshua Hooks, Stefano Soatto, Ankur Mehta, Dennis W. Hong:
Risk-Averse MPC via Visual-Inertial Input and Recurrent Networks for Online Collision Avoidance. CoRR abs/2007.14035 (2020) - [i67]Yanchao Yang, Brian Lai, Stefano Soatto:
Time-Supervised Primary Object Segmentation. CoRR abs/2008.07012 (2020) - [i66]Luca Zancato, Alessandro Achille, Avinash Ravichandran, Rahul Bhotika, Stefano Soatto:
Predicting Training Time Without Training. CoRR abs/2008.12478 (2020) - [i65]Alex Wong, Mukund Mundhra, Stefano Soatto:
Stereopagnosia: Fooling Stereo Networks with Adversarial Perturbations. CoRR abs/2009.10142 (2020) - [i64]Shay Deutsch, Stefano Soatto:
Spectral Embedding of Graph Networks. CoRR abs/2009.14441 (2020) - [i63]Sijie Yan, Yuanjun Xiong, Kaustav Kundu, Shuo Yang, Siqi Deng, Meng Wang, Wei Xia, Stefano Soatto:
Positive-Congruent Training: Towards Regression-Free Model Updates. CoRR abs/2011.09161 (2020) - [i62]Alessandro Achille, Aditya Golatkar, Avinash Ravichandran, Marzia Polito, Stefano Soatto:
LQF: Linear Quadratic Fine-Tuning. CoRR abs/2012.11140 (2020) - [i61]Aditya Golatkar, Alessandro Achille, Avinash Ravichandran, Marzia Polito, Stefano Soatto:
Mixed-Privacy Forgetting in Deep Networks. CoRR abs/2012.13431 (2020)
2010 – 2019
- 2019
- [j57]Xiaohan Fei, Alex Wong, Stefano Soatto:
Geo-Supervised Visual Depth Prediction. IEEE Robotics Autom. Lett. 4(2): 1661-1668 (2019) - [c190]Tong He, Stefano Soatto:
Mono3D++: Monocular 3D Vehicle Detection with Two-Scale 3D Hypotheses and Task Priors. AAAI 2019: 8409-8416 - [c189]Safa Cicek, Alireza Nakhaei, Stefano Soatto, Kikuo Fujimura:
MARL-PPS: Multi-agent Reinforcement Learning with Periodic Parameter Sharing. AAMAS 2019: 1883-1885 - [c188]Yanchao Yang, Antonio Loquercio, Davide Scaramuzza, Stefano Soatto:
Unsupervised Moving Object Detection via Contextual Information Separation. CVPR 2019: 879-888 - [c187]Yanchao Yang, Alex Wong, Stefano Soatto:
Dense Depth Posterior (DDP) From Single Image and Sparse Range. CVPR 2019: 3353-3362 - [c186]Alex Wong, Stefano Soatto:
Bilateral Cyclic Constraint and Adaptive Regularization for Unsupervised Monocular Depth Prediction. CVPR 2019: 5644-5653 - [c185]Tong He, Haibin Huang, Li Yi, Yuqian Zhou, Chihao Wu, Jue Wang, Stefano Soatto:
GeoNet: Deep Geodesic Networks for Point Cloud Analysis. CVPR 2019: 6888-6897 - [c184]Kwonjoon Lee, Subhransu Maji, Avinash Ravichandran, Stefano Soatto:
Meta-Learning With Differentiable Convex Optimization. CVPR 2019: 10657-10665 - [c183]Avinash Ravichandran, Rahul Bhotika, Stefano Soatto:
Few-Shot Learning With Embedded Class Models and Shot-Free Meta Training. ICCV 2019: 331-339 - [c182]Safa Cicek, Stefano Soatto:
Unsupervised Domain Adaptation via Regularized Conditional Alignment. ICCV 2019: 1416-1425 - [c181]Alessandro Achille, Michael Lam, Rahul Tewari, Avinash Ravichandran, Subhransu Maji, Charless C. Fowlkes, Stefano Soatto, Pietro Perona:
Task2Vec: Task Embedding for Meta-Learning. ICCV 2019: 6429-6438 - [c180]Safa Cicek, Stefano Soatto:
Input and Weight Space Smoothing for Semi-Supervised Learning. ICCV Workshops 2019: 1344-1353 - [c179]Alessandro Achille, Matteo Rovere, Stefano Soatto:
Critical Learning Periods in Deep Networks. ICLR (Poster) 2019 - [c178]Aditya Golatkar, Alessandro Achille, Stefano Soatto:
Time Matters in Regularizing Deep Networks: Weight Decay and Data Augmentation Affect Early Learning Dynamics, Matter Little Near Convergence. NeurIPS 2019: 10677-10687 - [c177]Shay Deutsch, Iacopo Masi, Stefano Soatto:
Finding Structure in Point Cloud Data with the Robust Isoperimetric Loss. SSVM 2019: 25-37 - [i60]Tong He, Haibin Huang, Li Yi, Yuqian Zhou, Chihao Wu, Jue Wang, Stefano Soatto:
GeoNet: Deep Geodesic Networks for Point Cloud Analysis. CoRR abs/1901.00680 (2019) - [i59]Yanchao Yang, Antonio Loquercio, Davide Scaramuzza, Stefano Soatto:
Unsupervised Moving Object Detection via Contextual Information Separation. CoRR abs/1901.03360 (2019) - [i58]Tong He, Stefano Soatto:
Mono3D++: Monocular 3D Vehicle Detection with Two-Scale 3D Hypotheses and Task Priors. CoRR abs/1901.03446 (2019) - [i57]Yanchao Yang, Alex Wong, Stefano Soatto:
Dense Depth Posterior (DDP) from Single Image and Sparse Range. CoRR abs/1901.10034 (2019) - [i56]Alessandro Achille, Michael Lam, Rahul Tewari, Avinash Ravichandran, Subhransu Maji, Charless C. Fowlkes, Stefano Soatto, Pietro Perona:
Task2Vec: Task Embedding for Meta-Learning. CoRR abs/1902.03545 (2019) - [i55]Shay Deutsch, Andrea L. Bertozzi, Stefano Soatto:
Zero Shot Learning with the Isoperimetric Loss. CoRR abs/1903.06781 (2019) - [i54]Alex Wong, Byung-Woo Hong, Stefano Soatto:
Bilateral Cyclic Constraint and Adaptive Regularization for Unsupervised Monocular Depth Prediction. CoRR abs/1903.07309 (2019) - [i53]Alessandro Achille, Giovanni Paolini, Glen Mbeng, Stefano Soatto:
The Information Complexity of Learning Tasks, their Structure and their Distance. CoRR abs/1904.03292 (2019) - [i52]Kwonjoon Lee, Subhransu Maji, Avinash Ravichandran, Stefano Soatto:
Meta-Learning with Differentiable Convex Optimization. CoRR abs/1904.03758 (2019) - [i51]Avinash Ravichandran, Rahul Bhotika, Stefano Soatto:
Few-Shot Learning with Embedded Class Models and Shot-Free Meta Training. CoRR abs/1905.04398 (2019) - [i50]Alex Wong, Xiaohan Fei, Stefano Soatto:
VOICED: Depth Completion from Inertial Odometry and Vision. CoRR abs/1905.08616 (2019) - [i49]Safa Cicek, Stefano Soatto:
Unsupervised Domain Adaptation via Regularized Conditional Alignment. CoRR abs/1905.10885 (2019) - [i48]Alessandro Achille, Stefano Soatto:
Where is the Information in a Deep Neural Network? CoRR abs/1905.12213 (2019) - [i47]Aditya Golatkar, Alessandro Achille, Stefano Soatto:
Time Matters in Regularizing Deep Networks: Weight Decay and Data Augmentation Affect Early Learning Dynamics, Matter Little Near Convergence. CoRR abs/1905.13277 (2019) - [i46]Cuong V. Nguyen, Alessandro Achille, Michael Lam, Tal Hassner, Vijay Mahadevan, Stefano Soatto:
Toward Understanding Catastrophic Forgetting in Continual Learning. CoRR abs/1908.01091 (2019) - [i45]Guneet S. Dhillon, Pratik Chaudhari, Avinash Ravichandran, Stefano Soatto:
A Baseline for Few-Shot Image Classification. CoRR abs/1909.02729 (2019) - [i44]Rasool Fakoor, Pratik Chaudhari, Stefano Soatto, Alexander J. Smola:
Meta-Q-Learning. CoRR abs/1910.00125 (2019) - [i43]Rita Fioresi, Pratik Chaudhari, Stefano Soatto:
A geometric interpretation of stochastic gradient descent using diffusion metrics. CoRR abs/1910.12194 (2019) - [i42]Aditya Golatkar, Alessandro Achille, Stefano Soatto:
Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks. CoRR abs/1911.04933 (2019) - [i41]Albert Zhao, Tong He, Yitao Liang, Haibin Huang, Guy Van den Broeck, Stefano Soatto:
LaTeS: Latent Space Distillation for Teacher-Student Driving Policy Learning. CoRR abs/1912.02973 (2019) - 2018
- [j56]Alessandro Achille, Stefano Soatto:
A Separation Principle for Control in the Age of Deep Learning. Annu. Rev. Control. Robotics Auton. Syst. 1: 287-307 (2018) - [j55]Alessandro Achille, Stefano Soatto:
Emergence of Invariance and Disentanglement in Deep Representations. J. Mach. Learn. Res. 19: 50:1-50:34 (2018) - [j54]Alessandro Achille, Stefano Soatto:
Information Dropout: Learning Optimal Representations Through Noisy Computation. IEEE Trans. Pattern Anal. Mach. Intell. 40(12): 2897-2905 (2018) - [c176]Simon Korman, Mark Milam, Stefano Soatto:
OATM: Occlusion Aware Template Matching by Consensus Set Maximization. CVPR 2018: 2675-2683 - [c175]Alhussein Fawzi, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard, Stefano Soatto:
Empirical Study of the Topology and Geometry of Deep Networks. CVPR 2018: 3762-3770 - [c174]Safa Cicek, Alhussein Fawzi, Stefano Soatto:
SaaS: Speed as a Supervisor for Semi-supervised Learning. ECCV (2) 2018: 152-166 - [c173]Yanchao Yang, Stefano Soatto:
Conditional Prior Networks for Optical Flow. ECCV (15) 2018: 282-298 - [c172]Xiaohan Fei, Stefano Soatto:
Visual-Inertial Object Detection and Mapping. ECCV (11) 2018: 318-334 - [c171]Nikolaos Karianakis, Zicheng Liu, Yinpeng Chen, Stefano Soatto:
Reinforced Temporal Attention and Split-Rate Transfer for Depth-Based Person Re-identification. ECCV (5) 2018: 737-756 - [c170]Pratik Chaudhari, Stefano Soatto:
Stochastic gradient descent performs variational inference, converges to limit cycles for deep networks. ICLR (Poster) 2018 - [c169]Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, Omar Fawzi, Pascal Frossard, Stefano Soatto:
Robustness of Classifiers to Universal Perturbations: A Geometric Perspective. ICLR (Poster) 2018 - [c168]Alessandro Achille, Stefano Soatto:
Emergence of Invariance and Disentanglement in Deep Representations. ITA 2018: 1-9 - [c167]Pratik Chaudhari, Stefano Soatto:
Stochastic Gradient Descent Performs Variational Inference, Converges to Limit Cycles for Deep Networks. ITA 2018: 1-10 - [i40]Simon Korman, Mark Milam, Stefano Soatto:
OATM: Occlusion Aware Template Matching by Consensus Set Maximization. CoRR abs/1804.02638 (2018) - [i39]Safa Cicek, Alhussein Fawzi, Stefano Soatto:
SaaS: Speed as a Supervisor for Semi-supervised Learning. CoRR abs/1805.00980 (2018) - [i38]Safa Cicek, Stefano Soatto:
Input and Weight Space Smoothing for Semi-supervised Learning. CoRR abs/1805.09302 (2018) - [i37]Xiaohan Fei, Stefano Soatto:
Visual-Inertial Object Detection and Mapping. CoRR abs/1806.08498 (2018) - [i36]Yanchao Yang, Stefano Soatto:
Conditional Prior Networks for Optical Flow. CoRR abs/1807.10378 (2018) - [i35]Xiaohan Fei, Alex Wong, Stefano Soatto:
Geo-Supervised Visual Depth Prediction. CoRR abs/1807.11130 (2018) - [i34]Alessandro Achille, Glen Mbeng, Stefano Soatto:
The Dynamics of Differential Learning I: Information-Dynamics and Task Reachability. CoRR abs/1810.02440 (2018) - 2017
- [c166]Pratik Chaudhari, Adam M. Oberman, Stanley J. Osher, Stefano Soatto, Guillaume Carlier:
Partial differential equations for training deep neural networks. ACSSC 2017: 1627-1631 - [c165]Jingming Dong, Xiaohan Fei, Stefano Soatto:
Visual-Inertial-Semantic Scene Representation for 3D Object Detection. CVPR 2017: 3567-3577 - [c164]Yanchao Yang, Stefano Soatto:
S2F: Slow-to-Fast Interpolator Flow. CVPR 2017: 3767-3776 - [c163]Shay Deutsch, Soheil Kolouri, Kyungnam Kim, Yuri Owechko, Stefano Soatto:
Zero Shot Learning via Multi-scale Manifold Regularization. CVPR 2017: 5292-5299 - [c162]Pratik Chaudhari, Anna Choromanska, Stefano Soatto, Yann LeCun, Carlo Baldassi, Christian Borgs, Jennifer T. Chayes, Levent Sagun, Riccardo Zecchina:
Entropy-SGD: Biasing Gradient Descent Into Wide Valleys. ICLR (Poster) 2017 - [c161]Virginia Estellers, Stefano Soatto:
Adaptive Discretizations for Non-smooth Variational Vision. SSVM 2017: 629-642 - [i33]Byung-Woo Hong, Ja-Keoung Koo, Stefano Soatto:
Multi-Label Segmentation via Residual-Driven Adaptive Regularization. CoRR abs/1702.08336 (2017) - [i32]Pratik Chaudhari, Adam M. Oberman, Stanley J. Osher, Stefano Soatto, Guillaume Carlier:
Deep Relaxation: partial differential equations for optimizing deep neural networks. CoRR abs/1704.04932 (2017) - [i31]Byung-Woo Hong, Ja-Keoung Koo, Martin Burger, Stefano Soatto:
Adaptive Regularization of Some Inverse Problems in Image Analysis. CoRR abs/1705.03350 (2017) - [i30]Alhussein Fawzi, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard, Stefano Soatto:
Classification regions of deep neural networks. CoRR abs/1705.09552 (2017) - [i29]Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, Omar Fawzi, Pascal Frossard, Stefano Soatto:
Analysis of universal adversarial perturbations. CoRR abs/1705.09554 (2017) - [i28]Nikolaos Karianakis, Zicheng Liu, Yinpeng Chen, Stefano Soatto:
Person Depth ReID: Robust Person Re-identification with Commodity Depth Sensors. CoRR abs/1705.09882 (2017) - [i27]Alessandro Achille, Stefano Soatto:
On the Emergence of Invariance and Disentangling in Deep Representations. CoRR abs/1706.01350 (2017) - [i26]Pratik Chaudhari, Carlo Baldassi, Riccardo Zecchina, Stefano Soatto, Ameet Talwalkar:
Parle: parallelizing stochastic gradient descent. CoRR abs/1707.00424 (2017) - [i25]Pratik Chaudhari, Stefano Soatto:
Stochastic gradient descent performs variational inference, converges to limit cycles for deep networks. CoRR abs/1710.11029 (2017) - [i24]Alessandro Achille, Stefano Soatto:
A Separation Principle for Control in the Age of Deep Learning. CoRR abs/1711.03321 (2017) - [i23]Kensuke Nakamura, Stefano Soatto, Byung-Woo Hong:
Block-Cyclic Stochastic Coordinate Descent for Deep Neural Networks. CoRR abs/1711.07190 (2017) - [i22]Alessandro Achille, Matteo Rovere, Stefano Soatto:
Critical Learning Periods in Deep Neural Networks. CoRR abs/1711.08856 (2017) - [i21]Jameson Tyler Merkow, Robert B. Lufkin, Kim Nguyen, Stefano Soatto, Zhuowen Tu, Andrea Vedaldi:
DeepRadiologyNet: Radiologist Level Pathology Detection in CT Head Images. CoRR abs/1711.09313 (2017) - [i20]René Vidal, Joan Bruna, Raja Giryes, Stefano Soatto:
Mathematics of Deep Learning. CoRR abs/1712.04741 (2017) - 2016
- [j53]Virginia Estellers, Stefano Soatto:
Detecting Occlusions as an Inverse Problem. J. Math. Imaging Vis. 54(2): 181-198 (2016) - [j52]Virginia Estellers, M. A. Scott, Stefano Soatto:
Robust Surface Reconstruction. SIAM J. Imaging Sci. 9(4): 2073-2098 (2016) - [c160]Nikolaos Karianakis, Jingming Dong, Stefano Soatto:
An Empirical Evaluation of Current Convolutional Architectures' Ability to Manage Nuisance Location and Scale Variability. CVPR 2016: 4442-4451 - [c159]Thomas A. Goldstein, Paul Hand, Choongbum Lee, Vladislav Voroninski, Stefano Soatto:
ShapeFit and ShapeKick for Robust, Scalable Structure from Motion. ECCV (7) 2016: 289-304 - [c158]Xiaohan Fei, Konstantine Tsotsos, Stefano Soatto:
A Simple Hierarchical Pooling Data Structure for Loop Closure. ECCV (3) 2016: 321-337 - [c157]Vasiliy Karasev, Alper Ayvaci, Bernd Heisele, Stefano Soatto:
Intent-aware long-term prediction of pedestrian motion. ICRA 2016: 2543-2549 - [c156]Joshua Hernandez, Konstantine Tsotsos, Stefano Soatto:
Observability, Identifiability and Sensitivity of Vision-Aided Inertial Navigation. IJCAI 2016: 4170-4174 - [c155]Georgios Georgiadis, Stefano Soatto:
A mid-level representation of visual structures for video compression. WACV 2016: 1-8 - [c154]Stefano Soatto, Alessandro Chiuso:
Modeling Visual Representations: Defining Properties and Deep Approximations. ICLR (Poster) 2016 - [i19]Hossein Mobahi, Stefano Soatto:
A Theory of Local Matching: SIFT and Beyond. CoRR abs/1601.05116 (2016) - [i18]Stefano Soatto:
Visual-Inertial Scene Representations. CoRR abs/1606.03968 (2016) - [i17]Thomas A. Goldstein, Paul Hand, Choongbum Lee, Vladislav Voroninski, Stefano Soatto:
ShapeFit and ShapeKick for Robust, Scalable Structure from Motion. CoRR abs/1608.02165 (2016) - [i16]Alessandro Achille, Stefano Soatto:
Information Dropout: learning optimal representations through noise. CoRR abs/1611.01353 (2016) - [i15]Pratik Chaudhari, Anna Choromanska, Stefano Soatto, Yann LeCun, Carlo Baldassi, Christian Borgs, Jennifer T. Chayes, Levent Sagun, Riccardo Zecchina:
Entropy-SGD: Biasing Gradient Descent Into Wide Valleys. CoRR abs/1611.01838 (2016) - 2015
- [j51]Byung-Woo Hong, Stefano Soatto:
Shape Matching Using Multiscale Integral Invariants. IEEE Trans. Pattern Anal. Mach. Intell. 37(1): 151-160 (2015) - [j50]Virginia Estellers, Stefano Soatto, Xavier Bresson:
Adaptive Regularization With the Structure Tensor. IEEE Trans. Image Process. 24(6): 1777-1790 (2015) - [c153]Joachim Valente, Stefano Soatto:
Perspective distortion modeling, learning and compensation. CVPR Workshops 2015: 9-16 - [c152]Gottfried Graber, Jonathan Balzer, Stefano Soatto, Thomas Pock:
Efficient minimal-surface regularization of perspective depth maps in variational stereo. CVPR 2015: 511-520 - [c151]Georgios Georgiadis, Alessandro Chiuso, Stefano Soatto:
Texture representations for image and video synthesis. CVPR 2015: 2058-2066 - [c150]Jingming Dong, Nikolaos Karianakis, Damek Davis, Joshua Hernandez, Jonathan Balzer, Stefano Soatto:
Multi-view feature engineering and learning. CVPR 2015: 3251-3260 - [c149]Brian Taylor, Vasiliy Karasev, Stefano Soatto:
Causal video object segmentation from persistence of occlusions. CVPR 2015: 4268-4276 - [c148]Jingming Dong, Stefano Soatto:
Domain-size pooling in local descriptors: DSP-SIFT. CVPR 2015: 5097-5106 - [c147]Georgios Georgiadis, Stefano Soatto:
Exploiting Temporal Redundancy of Visual Structures for Video Compression. DCC 2015: 445 - [c146]Yanchao Yang, Ganesh Sundaramoorthi, Stefano Soatto:
Self-Occlusions and Disocclusions in Causal Video Object Segmentation. ICCV 2015: 4408-4416 - [c145]Joshua Hernandez, Konstantine Tsotsos, Stefano Soatto:
Observability, identifiability and sensitivity of vision-aided inertial navigation. ICRA 2015: 2319-2325 - [c144]Andrea Censi, Erich Mueller, Emilio Frazzoli, Stefano Soatto:
A Power-Performance Approach to Comparing Sensor Families, with application to comparing neuromorphic to traditional vision sensors. ICRA 2015: 3319-3326 - [c143]Konstantine Tsotsos, Alessandro Chiuso, Stefano Soatto:
Robust inference for visual-inertial sensor fusion. ICRA 2015: 5203-5210 - [c142]Virginia Estellers, Michael Scott, Kevin Tew, Stefano Soatto:
Robust Poisson Surface Reconstruction. SSVM 2015: 525-537 - [c141]Stefano Soatto, Alessandro Chiuso:
Visual Scene Representations: Sufficiency, Minimality, Invariance and Deep Approximations. ICLR (Workshop) 2015 - [c140]Stefano Soatto, Jingming Dong, Nikolaos Karianakis:
Visual Scene Representations: Scaling and Occlusion in Convolutional Architectures. ICLR (Workshop) 2015 - [i14]Nikolaos Karianakis, Thomas J. Fuchs, Stefano Soatto:
Boosting Convolutional Features for Robust Object Proposals. CoRR abs/1503.06350 (2015) - [i13]Nikolaos Karianakis, Jingming Dong, Stefano Soatto:
How Well Can a CNN Marginalize Simple Nuisances It is Designed for? CoRR abs/1505.06795 (2015) - [i12]Pratik Chaudhari, Stefano Soatto:
Trivializing The Energy Landscape Of Deep Networks. CoRR abs/1511.06485 (2015) - [i11]Xiaohan Fei, Konstantine Tsotsos, Stefano Soatto:
A Simple Hierarchical Pooling Data Structure for Loop Closure. CoRR abs/1511.06489 (2015) - 2014
- [j49]Mario Micheli, Yifei Lou, Stefano Soatto, Andrea L. Bertozzi:
A Linear Systems Approach to Imaging Through Turbulence. J. Math. Imaging Vis. 48(1): 185-201 (2014) - [j48]Luca Valente, Yen-Hsi Richard Tsai, Stefano Soatto:
Information-Seeking Control Under Visibility-Based Uncertainty. J. Math. Imaging Vis. 48(2): 339-358 (2014) - [c139]Jonathan Balzer, Daniel Acevedo Feliz, Stefano Soatto, Sebastian Höfer, Markus Hadwiger, Jürgen Beyerer:
Cavlectometry: Towards Holistic Reconstruction of Large Mirror Objects. 3DV 2014: 448-455 - [c138]Damek Davis, Jonathan Balzer, Stefano Soatto:
Asymmetric Sparse Kernel Approximations for Large-Scale Visual Search. CVPR 2014: 2115-2122 - [c137]Vasiliy Karasev, Avinash Ravichandran, Stefano Soatto:
Active Frame, Location, and Detector Selection for Automated and Manual Video Annotation. CVPR 2014: 2131-2138 - [c136]Jonathan Balzer, Stefano Soatto:
Second-Order Shape Optimization for Geometric Inverse Problems in Vision. CVPR 2014: 3850-3857 - [c135]Jonathan Balzer, Megan A. K. Peters, Stefano Soatto:
Volumetric reconstruction applied to perceptual studies of size and weight. WACV 2014: 45-52 - [p5]Stefano Soatto, Jingming Dong:
Visual Correspondence, the Lambert-Ambient Shape Space and the Systematic Design of Feature Descriptors. Registration and Recognition in Images and Videos 2014: 63-93 - [i10]Jonathan Balzer, Daniel Acevedo Feliz, Stefano Soatto, Sebastian Höfer, Markus Hadwiger, Jürgen Beyerer:
Cavlectometry: Towards Holistic Reconstruction of Large Mirror Objects. CoRR abs/1409.4095 (2014) - [i9]Konstantine Tsotsos, Alessandro Chiuso, Stefano Soatto:
Robust Inference for Visual-Inertial Sensor Fusion. CoRR abs/1412.4862 (2014) - [i8]Jingming Dong, Stefano Soatto:
Domain-Size Pooling in Local Descriptors: DSP-SIFT. CoRR abs/1412.8556 (2014) - 2013
- [c134]Jonathan Balzer, Stefano Soatto:
CLAM: Coupled Localization and Mapping with Efficient Outlier Handling. CVPR 2013: 1554-1561 - [c133]Yun Zeng, Chaohui Wang, Stefano Soatto, Shing-Tung Yau:
Nonlinearly Constrained MRFs: Exploring the Intrinsic Dimensions of Higher-Order Cliques. CVPR 2013: 1706-1713 - [c132]Georgios Georgiadis, Alessandro Chiuso, Stefano Soatto:
Texture Compression. DCC 2013: 221-230 - [c131]Brian Taylor, Alper Ayvaci, Avinash Ravichandran, Stefano Soatto:
Semantic Video Segmentation from Occlusion Relations within a Convex Optimization Framework. EMMCVPR 2013: 195-208 - [c130]Vasiliy Karasev, Alessandro Chiuso, Stefano Soatto:
Control recognition bounds for visual learning and exploration. ITA 2013: 1-8 - [p4]Stefano Soatto:
Actionable Information in Vision. Machine Learning for Computer Vision 2013: 17-48 - [i7]Jonathan Balzer, Stefano Soatto:
Second-order Shape Optimization for Geometric Inverse Problems in Vision. CoRR abs/1311.2626 (2013) - [i6]Jonathan Balzer, Megan A. K. Peters, Stefano Soatto:
Volumetric Reconstruction Applied to Perceptual Studies of Size and Weight. CoRR abs/1311.2642 (2013) - [i5]Jingming Dong, Jonathan Balzer, Damek Davis, Joshua Hernandez, Stefano Soatto:
On the Design and Analysis of Multiple View Descriptors. CoRR abs/1311.6048 (2013) - [i4]Stefano Soatto:
Observability, Identifiability, Sensitivity and Model Reduction For Vision-Assisted Inertial Navigation. CoRR abs/1311.7434 (2013) - 2012
- [j47]Alper Ayvaci, Michalis Raptis, Stefano Soatto:
Sparse Occlusion Detection with Optical Flow. Int. J. Comput. Vis. 97(3): 322-338 (2012) - [j46]Alper Ayvaci, Stefano Soatto:
Detachable Object Detection: Segmentation and Depth Ordering from Short-Baseline Video. IEEE Trans. Pattern Anal. Mach. Intell. 34(10): 1942-1951 (2012) - [c129]Luca Valente, Yen-Hsi Richard Tsai, Stefano Soatto:
Information gathering control via exploratory path planning. CISS 2012: 1-6 - [c128]Georgios Georgiadis, Alper Ayvaci, Stefano Soatto:
Actionable saliency detection: Independent motion detection without independent motion estimation. CVPR 2012: 646-653 - [c127]Michalis Raptis, Iasonas Kokkinos, Stefano Soatto:
Discovering discriminative action parts from mid-level video representations. CVPR 2012: 1242-1249 - [c126]Georgios Georgiadis, Stefano Soatto:
Scene-Aware Video Modeling and Compression. DCC 2012: 149-158 - [c125]Avinash Ravichandran, Chaohui Wang, Michalis Raptis, Stefano Soatto:
SuperFloxels: A Mid-level Representation for Video Sequences. ECCV Workshops (3) 2012: 131-140 - [c124]Avinash Ravichandran, Stefano Soatto:
Long-Range Spatio-Temporal Modeling of Video with Application to Fire Detection. ECCV (2) 2012: 329-342 - [c123]Konstantine Tsotsos, Alberto Pretto, Stefano Soatto:
Visual-inertial ego-motion estimation for humanoid platforms. Humanoids 2012: 704-711 - [c122]Alper Ayvaci, Hailin Jin, Zhe Lin, Scott Cohen, Stefano Soatto:
Video upscaling via spatio-temporal self-similarity. ICPR 2012: 2190-2193 - [c121]Zhao Yi, Stefano Soatto, Maneesh Dewan, Yiqiang Zhan:
Information Forests. ITA 2012: 143-146 - [c120]Vasiliy Karasev, Alessandro Chiuso, Stefano Soatto:
Controlled Recognition Bounds for Visual Learning and Exploration. NIPS 2012: 2924-2932 - [c119]Taehee Lee, Stefano Soatto:
Fast planar object detection and tracking via edgel templates. WACV 2012: 473-480 - [i3]Zhao Yi, Stefano Soatto, Maneesh Dewan, Yiqiang Zhan:
Information Forests. CoRR abs/1202.1523 (2012) - 2011
- [j45]Alper Ayvaci, Pingkun Yan, Sheng Xu, Stefano Soatto, Jochen Kruecker:
Biopsy needle detection in transrectal ultrasound. Comput. Medical Imaging Graph. 35(7-8): 653-659 (2011) - [j44]Eagle Jones, Stefano Soatto:
Visual-inertial navigation, mapping and localization: A scalable real-time causal approach. Int. J. Robotics Res. 30(4): 407-430 (2011) - [j43]Taehee Lee, Stefano Soatto:
Video-based descriptors for object recognition. Image Vis. Comput. 29(10): 639-652 (2011) - [j42]Yifei Lou, Andrea L. Bertozzi, Stefano Soatto:
Direct Sparse Deblurring. J. Math. Imaging Vis. 39(1): 1-12 (2011) - [j41]Ganesh Sundaramoorthi, Andrea Mennucci, Stefano Soatto, Anthony J. Yezzi:
A New Geometric Metric in the Space of Curves, and Applications to Tracking Deforming Objects by Prediction and Filtering. SIAM J. Imaging Sci. 4(1): 109-145 (2011) - [c118]Taehee Lee, Stefano Soatto:
Learning and matching multiscale template descriptors for real-time detection, localization and tracking. CVPR 2011: 1457-1464 - [c117]Stefano Soatto, Alessandro Chiuso:
Controlled Recognition Bounds for Scaling and Occlusion Channels. DCC 2011: 477 - [c116]Alper Ayvaci, Stefano Soatto:
Detachable Object Detection with Efficient Model Selection. EMMCVPR 2011: 191-204 - [c115]Zhao Yi, Stefano Soatto:
Multimodal Registration via Spatial-Context Mutual Information. IPMI 2011: 424-435 - [c114]Taehee Lee, Stefano Soatto:
Edgel templates for fast planar object detection and pose estimation. ISMAR 2011: 257-258 - [c113]Kamil Wnuk, Stefano Soatto:
Multiple Instance Filtering. NIPS 2011: 370-378 - [c112]Byung-Woo Hong, Kangyu Ni, Stefano Soatto:
Entropy-Scale Profiles for Texture Segmentation. SSVM 2011: 243-254 - [i2]Alper Ayvaci, Stefano Soatto:
Detachable Object Detection: Segmentation and Depth Ordering From Short-Baseline Video. CoRR abs/1109.4683 (2011) - [i1]Stefano Soatto:
Steps Towards a Theory of Visual Information: Active Perception, Signal-to-Symbol Conversion and the Interplay Between Sensing and Control. CoRR abs/1110.2053 (2011) - 2010
- [j40]Peter N. Belhumeur, Katsushi Ikeuchi, Emmanuel Prados, Stefano Soatto, Peter F. Sturm:
Editorial for the Special Issue on Photometric Analysis for Computer Vision. Int. J. Comput. Vis. 86(2-3): 125-126 (2010) - [j39]Teresa Ko, Josh Hyman, Eric A. Graham, Mark H. Hansen, Stefano Soatto, Deborah Estrin:
Embedded Imagers: Detecting, Localizing, and Recognizing Objects and Events in Natural Habitats. Proc. IEEE 98(11): 1934-1946 (2010) - [j38]Haibin Ling, Stefano Soatto, Narayanan Ramanathan, David W. Jacobs:
Face verification across age progression using discriminative methods. IEEE Trans. Inf. Forensics Secur. 5(1): 82-91 (2010) - [j37]Teresa Ko, Shaun Ahmadian, John Hicks, Mohammad H. Rahimi, Deborah Estrin, Stefano Soatto, Sharon Coe, Michael P. Hamilton:
Heartbeat of a nest: Using imagers as biological sensors. ACM Trans. Sens. Networks 6(3): 19:1-19:31 (2010) - [c111]Kamil Wnuk, Stefano Soatto:
Analyzing Diving: A Dataset for Judging Action Quality. ACCV Workshops (1) 2010: 266-276 - [c110]Teresa Ko, Stefano Soatto, Deborah Estrin:
Warping background subtraction. CVPR 2010: 1331-1338 - [c109]Michalis Raptis, Kamil Wnuk, Stefano Soatto:
Spike train driven dynamical models for human actions. CVPR 2010: 2077-2084 - [c108]Ganesh Sundaramoorthi, Stefano Soatto, Anthony J. Yezzi:
Curious snakes: A minimum latency solution to the cluttered background problem in active contours. CVPR 2010: 2855-2862 - [c107]Brian Fulkerson, Stefano Soatto:
Really Quick Shift: Image Segmentation on a GPU. ECCV Workshops (1) 2010: 350-358 - [c106]Michalis Raptis, Stefano Soatto:
Tracklet Descriptors for Action Modeling and Video Analysis. ECCV (1) 2010: 577-590 - [c105]Sylvain Boltz, Frank Nielsen, Stefano Soatto:
Texture Regimes for Entropy-Based Multiscale Image Analysis. ECCV (3) 2010: 692-705 - [c104]Sylvain Boltz, Frank Nielsen, Stefano Soatto:
Earth Mover Distance on superpixels. ICIP 2010: 4597-4600 - [c103]Taehee Lee, Stefano Soatto:
Feature tracking and object recognition on a hand-held. ISMAR 2010: 306 - [c102]Alper Ayvaci, Michalis Raptis, Stefano Soatto:
Occlusion Detection and Motion Estimation with Convex Optimization. NIPS 2010: 100-108 - [p3]Andrea Vedaldi, Haibin Ling, Stefano Soatto:
Knowing a Good Feature When You See It: Ground Truth and Methodology to Evaluate Local Features for Recognition. Computer Vision: Detection, Recognition and Reconstruction 2010: 27-49
2000 – 2009
- 2009
- [j36]Byung-Woo Hong, Stefano Soatto, Luminita A. Vese:
Enforcing local context into shape statistics. Adv. Comput. Math. 31(1-3): 185-213 (2009) - [j35]Kangyu Ni, Byung-Woo Hong, Stefano Soatto, Tony F. Chan:
Unsupervised multiphase segmentation: A recursive approach. Comput. Vis. Image Underst. 113(4): 502-510 (2009) - [j34]Alessandro Bissacco, Stefano Soatto:
Hybrid Dynamical Models of Human Motion for the Recognition of Human Gaits. Int. J. Comput. Vis. 85(1): 101-114 (2009) - [c101]Ganesh Sundaramoorthi, Andrea Mennucci, Stefano Soatto, Anthony J. Yezzi:
Tracking deforming objects by filtering and prediction in the space of curves. CDC 2009: 2395-2401 - [c100]Teresa Ko, Stefano Soatto, Deborah Estrin:
Categorization in natural time-varying image sequences. CVPR Workshops 2009: 53-60 - [c99]Ganesh Sundaramoorthi, Peter Petersen, V. S. Varadarajan, Stefano Soatto:
On the set of images modulo viewpoint and contrast changes. CVPR 2009: 832-839 - [c98]Zhao Yi, Stefano Soatto:
Nonrigid registration combining global and local statistics. CVPR 2009: 2200-2207 - [c97]Brian Fulkerson, Andrea Vedaldi, Stefano Soatto:
Class segmentation and object localization with superpixel neighborhoods. ICCV 2009: 670-677 - [c96]Stefano Soatto:
Actionable information in vision. ICCV 2009: 2138-2145 - [c95]Alper Ayvaci, Stefano Soatto:
Motion segmentation with occlusions on the superpixel graph. ICCV Workshops 2009: 727-734 - [c94]Yifei Lou, Paolo Favaro, Stefano Soatto, Andrea L. Bertozzi:
Nonlocal Similarity Image Filtering. ICIAP 2009: 62-71 - [c93]Mars Lan, Mahsan Rofouei, Stefano Soatto, Majid Sarrafzadeh:
SmartLDWS: A robust and scalable lane departure warning system for the smartphones. ITSC 2009: 1-6 - [c92]Emmanuel Prados, Nitin Jindal, Stefano Soatto:
A Non-local Approach to Shape from Ambient Shading. SSVM 2009: 696-708 - 2008
- [j33]Alessandro Chiuso, Giorgio Picci, Stefano Soatto:
Wide-Sense Estimation on the Special Orthogonal Group. Commun. Inf. Syst. 8(3): 185-200 (2008) - [j32]Cordelia Schmid, Stefano Soatto, Carlo Tomasi:
Editorial. Int. J. Comput. Vis. 76(2): 105 (2008) - [j31]Hailin Jin, Daniel Cremers, Dejun Wang, Emmanuel Prados, Anthony J. Yezzi, Stefano Soatto:
3-D Reconstruction of Shaded Objects from Multiple Images Under Unknown Illumination. Int. J. Comput. Vis. 76(3): 245-256 (2008) - [j30]Jeremy D. Jackson, Anthony J. Yezzi, Stefano Soatto:
Dynamic Shape and Appearance Modeling via Moving and Deforming Layers. Int. J. Comput. Vis. 79(1): 71-84 (2008) - [j29]Paolo Favaro, Stefano Soatto, Martin Burger, Stanley J. Osher:
Shape from Defocus via Diffusion. IEEE Trans. Pattern Anal. Mach. Intell. 30(3): 518-531 (2008) - [c91]Byung-Woo Hong, Stefano Soatto, Kangyu Ni, Tony F. Chan:
The scale of a texture and its application to segmentation. CVPR 2008 - [c90]Jason Meltzer, Stefano Soatto:
Edge descriptors for robust wide-baseline correspondence. CVPR 2008 - [c89]Andrea Vedaldi, Gregorio Guidi, Stefano Soatto:
Joint data alignment up to (lossy) transformations. CVPR 2008 - [c88]Andrea Vedaldi, Stefano Soatto:
Relaxed matching kernels for robust image comparison. CVPR 2008 - [c87]Kamil Wnuk, Stefano Soatto:
Filtering Internet image search results towards keyword based category recognition. CVPR 2008 - [c86]Brian Fulkerson, Andrea Vedaldi, Stefano Soatto:
Localizing Objects with Smart Dictionaries. ECCV (1) 2008: 179-192 - [c85]Teresa Ko, Stefano Soatto, Deborah Estrin:
Background Subtraction on Distributions. ECCV (3) 2008: 276-289 - [c84]Ryuzo Okada, Stefano Soatto:
Relevant Feature Selection for Human Pose Estimation and Localization in Cluttered Images. ECCV (2) 2008: 434-445 - [c83]Andrea Vedaldi, Stefano Soatto:
Quick Shift and Kernel Methods for Mode Seeking. ECCV (4) 2008: 705-718 - 2007
- [b1]Paolo Favaro, Stefano Soatto:
3-D Shape Estimation and Image Restoration - Exploiting Defocus and Motion Blur. Springer 2007, ISBN 978-1-84628-176-1, pp. I-XIV, 1-249 - [j28]Hailin Jin, Anthony J. Yezzi, Stefano Soatto:
Mumford-Shah on the Move: Region-Based Segmentation on Deforming Manifolds with Application to 3-D Reconstruction of Shape and Appearance from Multi-View Images. J. Math. Imaging Vis. 29(2-3): 219-234 (2007) - [j27]Gozde B. Unal, Anthony J. Yezzi, Stefano Soatto, Gregory G. Slabaugh:
A Variational Approach to Problems in Calibration of Multiple Cameras. IEEE Trans. Pattern Anal. Mach. Intell. 29(8): 1322-1338 (2007) - [j26]Alessandro Bissacco, Alessandro Chiuso, Stefano Soatto:
Classification and Recognition of Dynamical Models: The Role of Phase, Independent Components, Kernels and Optimal Transport. IEEE Trans. Pattern Anal. Mach. Intell. 29(11): 1958-1972 (2007) - [c82]Daniele Fontanelli, Luigi Ricciato, Stefano Soatto:
A Fast RANSAC-Based Registration Algorithm for Accurate Localization in Unknown Environments using LIDAR Measurements. CASE 2007: 597-602 - [c81]Alessandro Bissacco, Stefano Soatto:
On the Blind Classification of Time Series. CVPR 2007 - [c80]Alessandro Bissacco, Ming-Hsuan Yang, Stefano Soatto:
Fast Human Pose Estimation using Appearance and Motion via Multi-Dimensional Boosting Regression. CVPR 2007 - [c79]Jeremy D. Jackson, Anthony J. Yezzi, Stefano Soatto:
Joint Priors for Variational Shape and Appearance Modeling. CVPR 2007 - [c78]Yifei Lou, Paolo Favaro, Andrea L. Bertozzi, Stefano Soatto:
Autocalibration and Uncalibrated Reconstruction of Shape from Defocus. CVPR 2007 - [c77]Andrea Vedaldi, Gregorio Guidi, Stefano Soatto:
Moving Forward in Structure From Motion. CVPR 2007 - [c76]Haibin Ling, Stefano Soatto:
Proximity Distribution Kernels for Geometric Context in Category Recognition. ICCV 2007: 1-8 - [c75]Haibin Ling, Stefano Soatto, Narayanan Ramanathan, David W. Jacobs:
A Study of Face Recognition as People Age. ICCV 2007: 1-8 - [c74]Zhao Yi, Stefano Soatto:
Correspondence Transfer for the Registration of Multimodal Images. ICCV 2007: 1-8 - [c73]Teresa Ko, Zainul Charbiwala, Shaun Ahmadian, Mohammad H. Rahimi, Mani B. Srivastava, Stefano Soatto, Deborah Estrin:
Exploring Tradeoffs in Accuracy, Energy and Latency of Scale Invariant Feature Transform in Wireless Camera Networks. ICDSC 2007: 313-320 - 2006
- [j25]René Vidal, Yi Ma, Stefano Soatto, Shankar Sastry:
Two-View Multibody Structure from Motion. Int. J. Comput. Vis. 68(1): 7-25 (2006) - [j24]Daniel Cremers, Stanley J. Osher, Stefano Soatto:
Kernel Density Estimation and Intrinsic Alignment for Shape Priors in Level Set Segmentation. Int. J. Comput. Vis. 69(3): 335-351 (2006) - [j23]Alessandro Duci, Anthony J. Yezzi, Sanjoy K. Mitter, Stefano Soatto:
Region matching with missing parts. Image Vis. Comput. 24(3): 271-277 (2006) - [j22]Richard Mason, Jim Radford, Deepak Kumar, Robert Walters, Brian Fulkerson, Eagle Jones, David Caldwell, Jason Meltzer, Yaniv Alon, Amnon Shashua, Hiroshi Hattori, Emilio Frazzoli, Stefano Soatto:
The Golem Group/University of California at Los Angeles autonomous ground vehicle in the DARPA grand challenge. J. Field Robotics 23(8): 527-553 (2006) - [j21]Alessandro Duci, Anthony J. Yezzi, Stefano Soatto, Kelvin R. Rocha:
Harmonic Embeddings for Linear Shape Analysis. J. Math. Imaging Vis. 25(3): 341-352 (2006) - [j20]Siddharth Manay, Daniel Cremers, Byung-Woo Hong, Anthony J. Yezzi, Stefano Soatto:
Integral Invariants for Shape Matching. IEEE Trans. Pattern Anal. Mach. Intell. 28(10): 1602-1618 (2006) - [j19]Gianfranco Doretto, Stefano Soatto:
Dynamic Shape and Appearance Models. IEEE Trans. Pattern Anal. Mach. Intell. 28(12): 2006-2019 (2006) - [c72]Dejun Wang, Stefano Soatto, Emmanuel Prados:
Towards Robust and Physically Plausible Shaded Stereoscopic Segmentation. CVPR Workshops 2006: 171 - [c71]Byung-Woo Hong, Emmanuel Prados, Stefano Soatto, Luminita A. Vese:
Shape Representation based on Integral Kernels: Application to Image Matching and Segmentation. CVPR (1) 2006: 833-840 - [c70]Emmanuel Prados, Stefano Soatto, Christophe Lenglet, Jean-Philippe Pons, Nicolas Wotawa, Rachid Deriche, Olivier D. Faugeras:
Control Theory and Fast Marching Techniques for Brain Connectivity Mapping. CVPR (1) 2006: 1076-1083 - [c69]Alessandro Bissacco, Stefano Soatto:
Classifying Human Dynamics Without Contact Forces. CVPR (2) 2006: 1678-1685 - [c68]Andrea Vedaldi, Stefano Soatto:
Local Features, All Grown Up. CVPR (2) 2006: 1753-1760 - [c67]Andrea Vedaldi, Stefano Soatto:
Viewpoint Induced Deformation Statistics and the Design of Viewpoint Invariant Features: Singularities and Occlusions. ECCV (2) 2006: 360-373 - [c66]Jia Ming Mar, Alessandro Bissacco, Stefano Soatto, Soheil Ghiasi:
High Performance Feature Detection on a Reconfigurable Co-Processor. FCCM 2006: 341-342 - [c65]Alessandro Bissacco, Ming-Hsuan Yang, Stefano Soatto:
Detecting Humans via Their Pose. NIPS 2006: 169-176 - [c64]Andrea Vedaldi, Stefano Soatto:
A Complexity-Distortion Approach to Joint Pattern Alignment. NIPS 2006: 1425-1432 - [p2]Gianfranco Doretto, Stefano Soatto:
Modeling Dynamic Scenes: An Overview of Dynamic Textures. Handbook of Mathematical Models in Computer Vision 2006: 341-355 - [p1]Siddharth Manay, Daniel Cremers, Byung-Woo Hong, Anthony J. Yezzi, Stefano Soatto:
Integral Invariants and Shape Matching. Statistics and Analysis of Shapes 2006: 137-166 - 2005
- [j18]Hailin Jin, Stefano Soatto, Anthony J. Yezzi:
Multi-View Stereo Reconstruction of Dense Shape and Complex Appearance. Int. J. Comput. Vis. 63(3): 175-189 (2005) - [j17]Paolo Favaro, Stefano Soatto:
A Geometric Approach to Shape from Defocus. IEEE Trans. Pattern Anal. Mach. Intell. 27(3): 406-417 (2005) - [c63]Siddharth Manay, Daniel Cremers, Anthony J. Yezzi, Stefano Soatto:
One-Shot Integral Invariant Shape Priors for Variational Segmentation. EMMCVPR 2005: 414-426 - [c62]Jeremy D. Jackson, Anthony J. Yezzi, Stefano Soatto:
Dynamic Shape and Appearance Modeling Via Moving and Deforming Layers. EMMCVPR 2005: 427-438 - [c61]Andrea Vedaldi, Hailin Jin, Paolo Favaro, Stefano Soatto:
KALMANSAC: Robust Filtering by Consensus. ICCV 2005: 633-640 - [c60]Eagle Jones, Stefano Soatto:
Layered Active Appearance Models. ICCV 2005: 1097-1102 - [c59]Andrea Vedaldi, Stefano Soatto:
Features for Recognition: Viewpoint Invariance for Non-Planar Scenes. ICCV 2005: 1474-1481 - [c58]Emmanuel Prados, Stefano Soatto:
Fast Marching Method for Generic Shape from Shading. VLSM 2005: 320-331 - 2004
- [j16]Daniel Cremers, Stefano Soatto:
Motion Competition: A Variational Approach to Piecewise Parametric Motion Segmentation. Int. J. Comput. Vis. 62(3): 249-265 (2004) - [c57]Jeremy D. Jackson, Anthony J. Yezzi, Stefano Soatto:
Tracking deformable moving objects under severe occlusions. CDC 2004: 2990-2995 - [c56]Hailin Jin, Daniel Cremers, Anthony J. Yezzi, Stefano Soatto:
Shedding Light on Stereoscopic Segmentation. CVPR (1) 2004: 36-42 - [c55]Paolo Favaro, Stefano Soatto:
A Variational Approach to Scene Reconstruction and Image Segmentation from Motion-Blur Cues. CVPR (1) 2004: 631-637 - [c54]Daniel Cremers, Stanley J. Osher, Stefano Soatto:
Kernel Density Estimation and Intrinsic Alignment for Knowledge-Driven Segmentation: Teaching Level Sets to Walk. DAGM-Symposium 2004: 36-44 - [c53]Siddharth Manay, Byung-Woo Hong, Anthony J. Yezzi, Stefano Soatto:
Integral Invariant Signatures. ECCV (4) 2004: 87-99 - [c52]Hailin Jin, Anthony J. Yezzi, Stefano Soatto:
Region-Based Segmentation on Evolving Surfaces with Application to 3D Reconstruction of Shape and Piecewise Constant Radiance. ECCV (2) 2004: 114-125 - [c51]Jason Meltzer, Ming-Hsuan Yang, Rakesh Gupta, Stefano Soatto:
Multiple View Feature Descriptors from Image Sequences via Kernel Principal Component Analysis. ECCV (1) 2004: 215-227 - [c50]Paolo Favaro, Martin Burger, Stefano Soatto:
Scene and Motion Reconstruction from Defocused and Motion-Blurred Images via Anisotropic Diffusion. ECCV (1) 2004: 257-269 - [c49]Payam Saisan, Alessandro Bissacco, Alessandro Chiuso, Stefano Soatto:
Modeling and Synthesis of Facial Motion Driven by Speech. ECCV (3) 2004: 456-467 - [c48]Gianfranco Doretto, Eagle Jones, Stefano Soatto:
Spatially Homogeneous Dynamic Textures. ECCV (2) 2004: 591-602 - [c47]Jason Meltzer, Rakesh Gupta, Ming-Hsuan Yang, Stefano Soatto:
Simultaneous localization and mapping using multiple view feature descriptors. IROS 2004: 1550-1555 - [c46]Jana Kosecká, Yi Ma, Stefano Soatto, René Vidal:
Multiple-view geometry for image-based modeling. SIGGRAPH Course Notes 2004: 9 - 2003
- [j15]Gianfranco Doretto, Alessandro Chiuso, Ying Nian Wu, Stefano Soatto:
Dynamic Textures. Int. J. Comput. Vis. 51(2): 91-109 (2003) - [j14]Paolo Favaro, Andrea Mennucci, Stefano Soatto:
Observing Shape from Defocused Images. Int. J. Comput. Vis. 52(1): 25-43 (2003) - [j13]Anthony J. Yezzi, Stefano Soatto:
Stereoscopic Segmentation. Int. J. Comput. Vis. 53(1): 31-43 (2003) - [j12]Anthony J. Yezzi, Stefano Soatto:
Deformotion: Deforming Motion, Shape Average and the Joint Registration and Approximation of Structures in Images. Int. J. Comput. Vis. 53(2): 153-167 (2003) - [j11]Hailin Jin, Anthony J. Yezzi, Yen-Hsi Tsai, Li-Tien Cheng, Stefano Soatto:
Estimation of 3D Surface Shape and Smooth Radiance from 2D Images: A Level Set Approach. J. Sci. Comput. 19(1-3): 267-292 (2003) - [j10]Hailin Jin, Paolo Favaro, Stefano Soatto:
A semi-direct approach to structure from motion. Vis. Comput. 19(6): 377-394 (2003) - [c45]René Vidal, Stefano Soatto, Yi Ma, Shankar Sastry:
An algebraic geometric approach to the identification of a class of linear hybrid systems. CDC 2003: 167-172 - [c44]Gianfranco Doretto, Stefano Soatto:
Editable Dynamic Textures. CVPR (2) 2003: 137-142 - [c43]Hailin Jin, Stefano Soatto, Anthony J. Yezzi:
Multi-view Stereo Beyond Lambert. CVPR (1) 2003: 171-178 - [c42]Paolo Favaro, Stanley J. Osher, Stefano Soatto, Luminita A. Vese:
3D Shape from Anisotropic Diffusion. CVPR (1) 2003: 179-186 - [c41]Anthony J. Yezzi, Stefano Soatto:
Structure From Motion for Scenes Without Features. CVPR (1) 2003: 525-532 - [c40]Paolo Favaro, Stefano Soatto:
Seeing Beyond Occlusions (and other marvels of a finite lens aperture). CVPR (2) 2003: 579-586 - [c39]René Vidal, Alessandro Chiuso, Stefano Soatto, Shankar Sastry:
Observability of Linear Hybrid Systems. HSCC 2003: 526-539 - [c38]Paolo Favaro, Alessandro Duci, Yi Ma, Stefano Soatto:
On Exploiting Occlusions in Multiple-view Geometry. ICCV 2003: 479-486 - [c37]Alessandro Duci, Anthony J. Yezzi, Sanjoy K. Mitter, Stefano Soatto:
Shape Representation via Harmonic Embedding. ICCV 2003: 656-662 - [c36]Daniel Cremers, Stefano Soatto:
Variational Space-Time Motion Segmentation. ICCV 2003: 886-893 - [c35]Stefano Soatto, Anthony J. Yezzi, Hailin Jin:
Tales of Shape and Radiance in Multi-view Stereo. ICCV 2003: 974-981 - [c34]Gianfranco Doretto, Daniel Cremers, Paolo Favaro, Stefano Soatto:
Dynamic Texture Segmentation. ICCV 2003: 1236-1242 - 2002
- [j9]Alessandro Chiuso, Paolo Favaro, Hailin Jin, Stefano Soatto:
Structure from Motion Causally Integrated Over Time. IEEE Trans. Pattern Anal. Mach. Intell. 24(4): 523-535 (2002) - [c33]Sung Ha Kang, Tony F. Chan, Stefano Soatto:
Inpainting from Multiple Views. 3DPVT 2002: 622-625 - [c32]Hailin Jin, Anthony J. Yezzi, Stefano Soatto:
Variational Multiframe Stereo in the Presence of Specular Reflections. 3DPVT 2002: 626-631 - [c31]Cecilia Mazzaro, Mario Sznaier, Octavia I. Camps, Stefano Soatto, Alessandro Bissacco:
A Model (In)Validation Approach to Gait Recognition. 3DPVT 2002: 700-703 - [c30]René Vidal, Alessandro Chiuso, Stefano Soatto:
Observability and identifiability of jump linear systems. CDC 2002: 3614-3619 - [c29]Stefano Soatto, Anthony J. Yezzi:
DEFORMOTION: Deforming Motion, Shape Average and the Joint Registration and Segmentation of Images. ECCV (3) 2002: 32-57 - [c28]Alessandro Duci, Anthony J. Yezzi, Sanjoy K. Mitter, Stefano Soatto:
Region Matching with Missing Parts. ECCV (3) 2002: 48-64 - [c27]Paolo Favaro, Stefano Soatto:
Learning Shape from Defocus. ECCV (2) 2002: 735-745 - [c26]Gianfranco Doretto, Stefano Soatto:
Editable dynamic textures. SIGGRAPH Abstracts and Applications 2002: 177 - 2001
- [c25]Alessandro Bissacco, Alessandro Chiuso, Yi Ma, Stefano Soatto:
Recognition of Human Gaits. CVPR (2) 2001: 52-57 - [c24]Payam Saisan, Gianfranco Doretto, Ying Nian Wu, Stefano Soatto:
Dynamic Texture Recognition. CVPR (2) 2001: 58-63 - [c23]Anthony J. Yezzi, Stefano Soatto:
Stereoscopic Segmentation. ICCV 2001: 59-66 - [c22]Stefano Soatto, Gianfranco Doretto, Ying Nian Wu:
Dynamic Textures. ICCV 2001: 439-446 - [c21]Hailin Jin, Paolo Favaro, Stefano Soatto:
Real-Time Feature Tracking and Outlier Rejection with Changes in Illumination. ICCV 2001: 684-689 - [c20]Paolo Favaro, Hailin Jin, Stefano Soatto:
Real-time Virtual Object Insertion. ICCV 2001: 749 - [c19]Paolo Favaro, Hailin Jin, Stefano Soatto:
A Semi-direct Approach to Structure from Motion. ICIAP 2001: 250-255 - 2000
- [j8]Yi Ma, Stefano Soatto, Jana Kosecka, Shankar Sastry:
Euclidean Reconstruction and Reprojection Up to Subgroups. Int. J. Comput. Vis. 38(3): 219-229 (2000) - [j7]Alessandro Chiuso, Roger W. Brockett, Stefano Soatto:
Optimal Structure from Motion: Local Ambiguities and Global Estimates. Int. J. Comput. Vis. 39(3): 195-228 (2000) - [c18]Alessandro Chiuso, Stefano Soatto:
Monte Carlo filtering on Lie groups. CDC 2000: 304-309 - [c17]Hailin Jin, Stefano Soatto, Anthony J. Yezzi:
Stereoscopic Shading: Integrating Mult1Frame Shape Cues in a Variational Framework. CVPR 2000: 1169-1176 - [c16]Stefano Soatto, Paolo Favaro:
A Geometric Approach to Blind Deconvolution with Application to Shape from Defocu. CVPR 2000: 2010-2017 - [c15]Hailin Jin, Paolo Favaro, Stefano Soatto:
Real-Time 3-D Motion and Structure of Point-Features: A Front-End for Vision-Based Control and Interaction. CVPR 2000: 2778-2779 - [c14]Alessandro Chiuso, Paolo Favaro, Hailin Jin, Stefano Soatto:
3-D Motion and Structure from 2-D Motion Causally Integrated over Time: Implementation. ECCV (2) 2000: 734-750 - [c13]Paolo Favaro, Stefano Soatto:
Shape and Radiance Estimation from the Information-Divergence of Blurred Images. ECCV (1) 2000: 755-768
1990 – 1999
- 1999
- [c12]Yi Ma, Stefano Soatto, Jana Kosecka, Shankar Sastry:
Euclidean Reconstruction and Reprojection up to Subgroups. ICCV 1999: 773-780 - [c11]Andrea Mennucci, Stefano Soatto:
On Observing Shape from Defocused Images. ICIAP 1999: 550-555 - 1998
- [j6]Stefano Soatto, Pietro Perona:
Reducing "Structure From Motion": A General Framework for Dynamic Vision Part 1: Modeling. IEEE Trans. Pattern Anal. Mach. Intell. 20(9): 933-942 (1998) - [j5]Stefano Soatto, Pietro Perona:
Reducing "Structure From Motion": A General Framework for Dynamic Vision Part 2: Implementation and Experimental Assessment. IEEE Trans. Pattern Anal. Mach. Intell. 20(9): 943-960 (1998) - [j4]Stefano Soatto, Pietro Perona:
Correction to: "Reducing 'Structure From Motion': A General Framework for Dynamic Vision Part 2: Implementation and Experimental Assessment". IEEE Trans. Pattern Anal. Mach. Intell. 20(10): 1117 (1998) - [c10]Stefano Soatto, Roger W. Brockett:
Optimal Structure from Motion: Local Ambiguities and Global Estimates. CVPR 1998: 282-288 - 1997
- [j3]Stefano Soatto:
3-D Structure from Visual Motion: Modeling, Representation and Observability. Autom. 33(7): 1287-1312 (1997) - [j2]Stefano Soatto, Pietro Perona:
Motion from Fixation. Real Time Imaging 3(2): 129-153 (1997) - [c9]Ruggero Frezza, Giorgio Picci, Stefano Soatto:
A lagrangian formulation of nonholonomic path following. Block Island Workshop on Vision and Control 1997: 118-133 - 1996
- [j1]Stefano Soatto, Ruggero Frezza, Pietro Perona:
Motion estimation via dynamic vision. IEEE Trans. Autom. Control. 41(3): 393-413 (1996) - [c8]Stefano Soatto, Pietro Perona:
Motion from fixation. CVPR 1996: 817-824 - [c7]Stefano Soatto, Pietro Perona:
Reducing "structure from motion". CVPR 1996: 825-832 - 1995
- [c6]Stefano Soatto, Pietro Perona:
Dynamic Rigid Motion Estimation from Weak Perspective. ICCV 1995: 321- - [c5]Stefano Soatto, Pietro Perona:
Visual motion estimation from point features: unified view. ICIP (3) 1995: 21-24 - 1994
- [c4]Stefano Soatto, Ruggero Frezza, Pietro Perona:
Motion Estimation on the Essential Manifold. ECCV (2) 1994: 61-72 - [c3]Stefano Soatto, Pietro Perona:
Recursive Estimation of Camera Motion from Uncalibrated Image Sequences. ICIP (3) 1994: 58-62 - [c2]Stefano Soatto, Pietro Perona:
Dynamic Visual Motion Estimation from Subspace Constraints. ICIP (1) 1994: 333-337 - 1993
- [c1]Stefano Soatto, Pietro Perona, Ruggero Frezza, Giorgio Picci:
Recursive motion and structure estimation with complete error characterization. CVPR 1993: 428-433
Coauthor Index
[c271] [c270] [c267] [c264] [c260] [c258] [i172] [i167] [i166] [i159] [i154] [i153] [i152] [c254] [c251] [c250] [c249] [c248] [c247] [c244] [c243] [c242] [i147] [i146] [i145] [i144] [i142] [i139] [i138] [i137] [i134] [i133] [i130] [i129] [i126] [c240] [c238] [c232] [c230] [i124] [i123] [i120] [i119] [i113] [i111] [i110] [i107] [i105] [j65] [c224] [c219] [c214] [c213] [i104] [i103] [i100] [i81] [c201] [c200] [c198] [c191] [i76] [i66] [i62] [i61] [c181] [c179] [c178] [i56] [i53] [i48] [i47] [i46] [i42] [j56] [j55] [j54] [c168] [i34] [i27] [i24] [i22] [i16]
[c254] [c245] [c244] [i145] [i144] [c240] [c236] [c234] [c232] [c231] [i119] [i117] [i116] [i109] [i108] [c225] [c224] [c219] [c214] [c210] [i103] [i102] [i101] [i100] [i88] [i86] [i81] [c198] [c197] [c195] [c191] [i79] [i78] [i77] [i66] [i62] [i61] [c184] [c183] [c181] [i56] [i52] [i51] [i45] [c137] [c131] [c125] [c124]
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-12-23 19:28 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
