Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleJune 2024
Temporal adaptive feature pyramid network for action detection
Computer Vision and Image Understanding (CVIU), Volume 240, Issue CMar 2024https://doi.org/10.1016/j.cviu.2024.103945AbstractDetecting actions in videos has become a prominent research task due to its wide application. In addition to recognizing action category, this task also needs to localize the start time and end time of each action instance, which requires the ...
Highlights- We introduce a temporal adaptive module to enhance temporal modeling.
- We introduce a channel adaptive module to adjust channel weights.
- We propose a TAFPN to generate multi-level features at different temporal scales.
- We also ...
- research-articleMay 2024
AutoML for Large Capacity Modeling of Meta's Ranking Systems
- Hang Yin,
- Kuang-Hung Liu,
- Mengying Sun,
- Yuxin Chen,
- Buyun Zhang,
- Jiang Liu,
- Vivek Sehgal,
- Rudresh Rajnikant Panchal,
- Eugen Hotaj,
- Xi Liu,
- Daifeng Guo,
- Jamey Zhang,
- Zhou Wang,
- Shali Jiang,
- Huayu Li,
- Zhengxing Chen,
- Wen-Yen Chen,
- Jiyan Yang,
- Wei Wen
WWW '24: Companion Proceedings of the ACM on Web Conference 2024May 2024, Pages 374–382https://doi.org/10.1145/3589335.3648336Web-scale ranking systems at Meta serving billions of users is complex. Improving ranking models is essential but engineering heavy. Automated Machine Learning (AutoML) can potentially release engineers from labor intensive work of tuning ranking models; ...
- research-articleMay 2024
Rankitect: Ranking Architecture Search Battling World-class Engineers at Meta Scale
- Wei Wen,
- Kuang-Hung Liu,
- Igor Fedorov,
- Xin Zhang,
- Hang Yin,
- Weiwei Chu,
- Kaveh Hassani,
- Mengying Sun,
- Jiang Liu,
- Xu Wang,
- Lin Jiang,
- Yuxin Chen,
- Buyun Zhang,
- Xi Liu,
- Dehua Cheng,
- Zhengxing Chen,
- Guang Zhao,
- Fangqiu Han,
- Jiyan Yang,
- Yuchen Hao,
- Liang Xiong,
- Wen-Yen Chen
WWW '24: Companion Proceedings of the ACM on Web Conference 2024May 2024, Pages 73–82https://doi.org/10.1145/3589335.3648304Neural Architecture Search (NAS) has demonstrated its efficacy in computer vision and potential for ranking systems. However, prior work focused on academic problems, which are evaluated at small scale under well-controlled fixed baselines. In industry ...
- research-articleMay 2024
MODE: a multimodal open-domain dialogue dataset with explanation
Applied Intelligence (KLU-APIN), Volume 54, Issue 7Apr 2024, Pages 5891–5906https://doi.org/10.1007/s10489-024-05479-xAbstractThe need for high-quality data has been a key issue hindering the research of dialogue tasks. Recent studies try to build datasets through manual, web crawling and so on. However, man-made data is expensive and data collected from the internet ...
- research-articleJanuary 2024
Research on micro parallax adversarial sample generation method based on texture sensitive region
Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology (JIFS), Volume 46, Issue 12024, Pages 2573–2584https://doi.org/10.3233/JIFS-231653Deep neural networks have been extensively applied in fields such as image classification, object detection, and face recognition. However, research has shown that adversarial samples with subtle perturbations can effectively deceive these networks. ...
-
- ArticleSeptember 2023
Learning Geometric Representations of Objects via Interaction
Machine Learning and Knowledge Discovery in Databases: Research TrackSep 2023, Pages 629–644https://doi.org/10.1007/978-3-031-43421-1_37AbstractWe address the problem of learning representations from observations of a scene involving an agent and an external object the agent interacts with. To this end, we propose a representation learning framework extracting the location in physical ...
- research-articleJuly 2023
Fluid Cohomology
ACM Transactions on Graphics (TOG), Volume 42, Issue 4Article No.: 126, Pages 1–25https://doi.org/10.1145/3592402The vorticity-streamfunction formulation for incompressible inviscid fluids is the basis for many fluid simulation methods in computer graphics, including vortex methods, streamfunction solvers, spectral methods, and Monte Carlo methods. We point out ...
- research-articleMay 2023
Multimodal dance style transfer
Machine Vision and Applications (MVAA), Volume 34, Issue 4Jul 2023https://doi.org/10.1007/s00138-023-01399-xAbstractThis paper first presents CycleDance, a novel dance style transfer system that transforms an existing motion clip in one dance style into a motion clip in another dance style while attempting to preserve the motion context of the dance. CycleDance ...
- research-articleOctober 2022
Integrating data augmentation and hybrid feature selection for small sample credit risk assessment with high dimensionality
Computers and Operations Research (CORS), Volume 146, Issue COct 2022https://doi.org/10.1016/j.cor.2022.105937Highlights- An integrated data augmentation and hybrid feature selection method is proposed.
Data scarcity is a serious issue in credit risk assessment for some emerging financial institutions. As a typical category of data scarcity, small sample with high dimensionality often leads to the failure to build an effective credit ...
- research-articleSeptember 2022
An extreme learning machine based virtual sample generation method with feature engineering for credit risk assessment with data scarcity
Expert Systems with Applications: An International Journal (EXWA), Volume 202, Issue CSep 2022https://doi.org/10.1016/j.eswa.2022.117363Highlights- An ELM based virtual sample generation method with feature engineering is proposed.
As a typical category of data scarcity, small sample often makes it difficult to build a reliable machine learning model in credit risk assessment, and thus many virtual sample generation (VSG) methods have been proposed for sample ...
- research-articleAugust 2022
Engineering Vehicles Detection for Warehouse Surveillance System Based on Modified YOLOv4-Tiny
Neural Processing Letters (NPLE), Volume 55, Issue 3Jun 2023, Pages 2743–2759https://doi.org/10.1007/s11063-022-10982-8AbstractThe engineering vehicle detection is a key issue for the raw material warehouse scenes. Through the engineering vehicle detection, the working conditions of engineering vehicles in the raw material warehouse can be intelligently managed to prevent ...
- research-articleJune 2022
Construction of Risk Control Decision-Making Model Platform for Transportation Hub Projects under the Background of Message Technique
With the acceleration of urbanization, the construction and operation of comprehensive transportation hub have promoted the development of regional economy. However, due to its huge scale, high building density, and crowded public space, the safety status ...
- research-articleMay 2022
How to Sense the World: Leveraging Hierarchy in Multimodal Perception for Robust Reinforcement Learning Agents
AAMAS '22: Proceedings of the 21st International Conference on Autonomous Agents and Multiagent SystemsMay 2022, Pages 1301–1309This work addresses the problem of sensing the world: how to learn a multimodal representation of a reinforcement learning agent's environment that allows the execution of tasks under incomplete perceptual conditions. To address such problem, we argue ...
- research-articleApril 2022
Towards Understanding Diminished Reality
CHI '22: Proceedings of the 2022 CHI Conference on Human Factors in Computing SystemsApril 2022, Article No.: 549, Pages 1–16https://doi.org/10.1145/3491102.3517452Diminished reality (DR) refers to the concept of removing content from a user’s visual environment. While its implementation is becoming feasible, it is still unclear how users perceive and interact in DR-enabled environments and what applications it ...
- research-articleFebruary 2022
Leveraging hierarchy in multimodal generative models for effective cross-modality inference
Neural Networks (NENE), Volume 146, Issue CFeb 2022, Pages 238–255https://doi.org/10.1016/j.neunet.2021.11.019AbstractThis work addresses the problem of cross-modality inference (CMI), i.e., inferring missing data of unavailable perceptual modalities (e.g., sound) using data from available perceptual modalities (e.g., image). We overview single-...
- research-articleJanuary 2022
Analysis and Design of the Project Risk Management System Based on the Fuzzy Clustering Algorithm
Journal of Control Science and Engineering (JCSAE), Volume 20222022https://doi.org/10.1155/2022/9328038In order to effectively control the cost risk of power grid construction projects, the author proposes a cost risk management system for power grid construction projects based on the fuzzy clustering algorithm. The system introduces the fuzzy clustering ...
- research-articleDecember 2021
A stability result for network reduced power systems including virtual friction control
2021 60th IEEE Conference on Decision and Control (CDC)Dec 2021, Pages 4228–4235https://doi.org/10.1109/CDC45484.2021.9683094We prove that virtual friction control can stabilize a power grid containing several virtual synchronous machines (VSMs), connecting line impedances and loads. Virtual friction is a torque added to the swing equation of each VSM, proportional to the ...
- research-articleNovember 2021
Automatic ventricular nuclear magnetic resonance image processing with deep learning
Multimedia Tools and Applications (MTAA), Volume 80, Issue 26-27Nov 2021, Pages 34103–34119https://doi.org/10.1007/s11042-020-08911-9AbstractCardiovascular diseases (CVD) seriously threaten the health of human beings, and they have caused widespread concern in recent years. At present, the diagnosis of CVD is mainly conducted by computed tomography (CT), echocardiography and nuclear ...
- research-articleSeptember 2021
Graph-based Task-specific Prediction Models for Interactions between Deformable and Rigid Objects
2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)Sep 2021, Pages 5741–5748https://doi.org/10.1109/IROS51168.2021.9636660Capturing scene dynamics and predicting the future scene state is challenging but essential for robotic manipulation tasks, especially when the scene contains both rigid and deformable objects. In this work, we contribute a simulation environment and ...
- research-articleAugust 2021
Energy-Efficient Models for High-Dimensional Spike Train Classification using Sparse Spiking Neural Networks
KDD '21: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data MiningAugust 2021, Pages 2017–2025https://doi.org/10.1145/3447548.3467252Spike train classification is an important problem in many areas such as healthcare and mobile sensing, where each spike train is a high-dimensional time series of binary values. Conventional research on spike train classification mainly focus on ...