Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- ArticleJanuary 2025
EIA: Edge-Aware Imperceptible Adversarial Attacks on 3D Point Clouds
AbstractAdversarial attacks on point clouds are crucial for assessing and improving the adversarial robustness of 3D deep learning models. Existing methods typically apply perturbations to all points on the point cloud using the same strategy. However, ...
- ArticleDecember 2024
Learning Neural Radiance Field from Quasi-uniformly Sampled Spherical Image for Immersive Virtual Reality
AbstractThe neural radiance field (NeRF) is a prominent method of novel view synthesis that is widely applied to many tasks. Recently, the NeRF method, which was originally developed for perspective images, has been extended to 360-degree omnidirectional ...
- research-articleNovember 2024
End-to-end pedestrian trajectory prediction via Efficient Multi-modal Predictors
Computer Vision and Image Understanding (CVIU), Volume 248, Issue Chttps://doi.org/10.1016/j.cviu.2024.104107AbstractPedestrian trajectory prediction plays a key role in understanding human behavior and guiding autonomous driving. It is a difficult task due to the multi-modal nature of human motion. Recent advances have mainly focused on modeling this multi-...
Highlights- We proposed EMP, an end-to-end multi-modal framework achieving accurate prediction with parallel predictors.
- EMP’s posterior policy eliminates the need for implicit distributions and anchors.
- EMP achieved state-of-the-art ...
- research-articleNovember 2024
Robust and smooth Couinaud segmentation via anatomical structure-guided point-voxel network
- Xukun Zhang,
- Sharib Ali,
- Tao Liu,
- Xiao Zhao,
- Zhiming Cui,
- Minghao Han,
- Shuwei Ma,
- Jingyi Zhu,
- Yanlan Kang,
- Le Wang,
- Xiaoying Wang,
- Lihua Zhang
Computers in Biology and Medicine (CBIM), Volume 182, Issue Chttps://doi.org/10.1016/j.compbiomed.2024.109202AbstractPrecise Couinaud segmentation from preoperative liver computed tomography (CT) is crucial for surgical planning and lesion examination. However, this task is challenging as it is defined based on vessel structures, and there is no intensity ...
Highlights- Introduced a novel automatic Couinaud liver segmentation framework, leveraging a dual-branch point-voxel fusion for enhanced spatial and semantic modeling.
- Developed a local attention module and a novel feature-level distance loss, ...
- research-articleOctober 2024
SymAttack: Symmetry-aware Imperceptible Adversarial Attacks on 3D Point Clouds
MM '24: Proceedings of the 32nd ACM International Conference on MultimediaPages 3131–3140https://doi.org/10.1145/3664647.3681181Adversarial attacks on point clouds are crucial for assessing and improving the adversarial robustness of 3D deep learning models. Despite leveraging various geometric constraints, current adversarial attack strategies often suffer from inadequate ...
-
- research-articleOctober 2024
Multimodal LLM Enhanced Cross-lingual Cross-modal Retrieval
MM '24: Proceedings of the 32nd ACM International Conference on MultimediaPages 8296–8305https://doi.org/10.1145/3664647.3680886Cross-lingual cross-modal retrieval (CCR) aims to retrieve visually relevant content based on non-English queries, without relying on human-labeled cross-modal data pairs during training. One popular approach involves utilizing machine translation (MT) ...
- research-articleOctober 2024
Exposing Stealthy Wash Trading on Automated Market Maker Exchanges
ACM Transactions on Internet Technology (TOIT), Volume 24, Issue 4Article No.: 17, Pages 1–30https://doi.org/10.1145/3689631Decentralized Finance (DeFi), a pivotal component of the emerging Web3 landscape, is gaining popularity but remains vulnerable to market manipulations, such as wash trading. Wash trading is an illegal practice, where traders buy and sell assets to ...
- research-articleOctober 2024
Neuroadaptive event-triggered tracking control for nonlinear systems with dynamic fault feedback and prescribed time convergence
AbstractThis paper investigates the problem of event-triggered adaptive prescribed time tracking control for nonlinear systems with combining multiplicative and additive dynamic sensor fault. A simple state observer is designed by fusing fault output and ...
- ArticleNovember 2024
PMT: Progressive Mean Teacher via Exploring Temporal Consistency for Semi-Supervised Medical Image Segmentation
AbstractSemi-supervised learning has emerged as a widely adopted technique in the field of medical image segmentation. The existing works either focuses on the construction of consistency constraints or the generation of pseudo labels to provide high-...
- ArticleOctober 2024
Analysis-by-Synthesis Transformer for Single-View 3D Reconstruction
AbstractDeep learning approaches have made significant success in single-view 3D reconstruction, but they often rely on expensive 3D annotations for training. Recent efforts tackle this challenge by adopting an analysis-by-synthesis paradigm to learn 3D ...
- ArticleOctober 2024
R3D-AD: Reconstruction via Diffusion for 3D Anomaly Detection
Abstract3D anomaly detection plays a crucial role in monitoring parts for localized inherent defects in precision manufacturing. Embedding-based and reconstruction-based approaches are among the most popular and successful methods. However, there are two ...
- ArticleOctober 2024
Learning Anomalies with Normality Prior for Unsupervised Video Anomaly Detection
AbstractUnsupervised video anomaly detection (UVAD) aims to detect abnormal events in videos without any annotations. It remains challenging because anomalies are rare, diverse, and usually not well-defined. Existing UVAD methods are purely data-driven ...
- ArticleSeptember 2024
Stepwise Multi-grained Boundary Detector for Point-Supervised Temporal Action Localization
AbstractPoint-supervised temporal action localization pursues high-accuracy action detection under low-cost data annotation. Despite recent advances, a significant challenge remains: sparse labeling of individual frames leads to semantic ambiguity in ...
- research-articleAugust 2024
Adversarial Attack and Defense in Deep Ranking
IEEE Transactions on Pattern Analysis and Machine Intelligence (ITPM), Volume 46, Issue 8Pages 5306–5324https://doi.org/10.1109/TPAMI.2024.3365699Deep Neural Network classifiers are vulnerable to adversarial attacks, where an imperceptible perturbation could result in misclassification. However, the vulnerability of DNN-based image ranking systems remains under-explored. In this paper, we propose ...
- research-articleAugust 2024
Influentials, early adopters, or random targets? Optimal seeding strategies under vertical differentiations
AbstractProduct seeding, defined as the act by which firms send products to selected customers and encourage them to spread word of mouth, is a critical decision support strategy for the success of new products. Using multiple agent-based simulation ...
Highlights- We investigated the relative importance seeding strategies in a competitive market.
- We focus on products vertically differentiated in terms of quality and brand strength.
- An optimal seeding strategy depends on consumers' propensity ...
- ArticleOctober 2024
Reinforced Negative Sampling for Knowledge Graph Embedding
AbstractAs a key part of knowledge graph embedding (KGE), negative sampling can mine hard negative examples required for model training to improve the accuracy and effectiveness of the KGE models. However, static negative sampling can’t adapt to the ...
- research-articleJuly 2024
MIM: A multiple integration model for intrusion detection on imbalanced samples
AbstractThe quantity of normal samples is commonly significantly greater than that of malicious samples, resulting in an imbalance in network security data. When dealing with imbalanced samples, the classification model requires careful sampling and ...
- research-articleJune 2024
Worst Perception Scenario Search via Recurrent Neural Controller and K-Reciprocal Re-Ranking
IEEE Transactions on Intelligent Transportation Systems (ITS-TRANSACTIONS), Volume 25, Issue 6Pages 5612–5626https://doi.org/10.1109/TITS.2023.3340257Achieving excellent generalization on perceiving real traffic scenarios with diversity is the long-term goal for building robust autonomous driving systems. A recent theoretical study shows that the generalization on the worst-group of test samples is far ...
- research-articleJune 2024
Bidirectional feature learning network for RGB-D salient object detection
AbstractRGB-D salient object detection aims to perform the pixel-wise localization of salient objects from both RGB and depth images, whose challenge mainly comes from how to learn complementary features from each modality. Existing works often use ...
Highlights- We design a bidirectional feature fusion model to learn discriminative features.
- We propose a dual consistency loss to learn complementary information.
- We achieve the state-of-the-art performance on several datasets.
- research-articleMay 2024
Residual feature learning with hierarchical calibration for gaze estimation
Machine Vision and Applications (MVAA), Volume 35, Issue 4https://doi.org/10.1007/s00138-024-01545-zAbstractGaze estimation aims to predict accurate gaze direction from natural eye images, which is an extreme challenging task due to both random variations in head pose and person-specific biases. Existing works often independently learn features from ...