paper-with-me

홈 › Papers

Self-Supervised Video Representation Learning in a Heuristic Decoupled Perspective

2024-07-19 · Zeen Song, Jingyao Wang, Jianqi Zhang, Changwen Zheng, Wenwen Qiang

Video contrastive learning (v-CL) has gained prominence as a leading framework for unsupervised video representation learning, showcasing impressive performance across various tasks such as action classification and detection. In the field of video representation learning, a feature extractor should ideally capture both static and dynamic semantics. However, our series of experiments reveals that existing v-CL methods predominantly capture static semantics, with limited capturing of dynamic semantics. Through causal analysis, we identify the root cause: the v-CL objective lacks explicit modeling of dynamic features and the measurement of dynamic similarity is confounded by static semantics, while the measurement of static similarity is confounded by dynamic semantics. In response, we propose "Bi-level Optimization of Learning Dynamic with Decoupling and Intervention" (BOLD-DI) to capture both static and dynamic semantics in a decoupled manner. Our method can be seamlessly integrated into the existing v-CL methods and experimental results highlight the significant improvements.

📄 PDF Abstract BibTeX arXiv:2407.14069

Code (0)

등록된 구현이 없습니다.

Tasks

Action ClassificationContrastive LearningRepresentation Learning

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Hierarchically Decoupled Spatial-Temporal Contrast for Self-supervised Video Representation Learning

2020-11-23 · Zehua Zhang, David Crandall

We present a novel technique for self-supervised video representation learning by: (a) decoupling the learning objective into two contrastive subtasks respectively emphasizing spatial and temporal features, and (b) perfo…

Action RecognitionContrastive LearningRepresentation Learning

Self-Supervised Learning of Motion Concepts by Optimizing Counterfactuals

2025-03-25 · Stefan Stojanov, David Wendt, Seungwoo Kim, Rahul Venkatesh 외

Estimating motion in videos is an essential computer vision problem with many downstream applications, including controllable video generation and robotics. Current solutions are primarily trained using synthetic data or…

counterfactualMotion EstimationOcclusion EstimationSelf-Supervised Learning+1

MCDS-VSS: Moving Camera Dynamic Scene Video Semantic Segmentation by Filtering with Self-Supervised Geometry and Motion

2024-05-30 · Angel Villar-Corrales, Moritz Austermann, Sven Behnke

Autonomous systems, such as self-driving cars, rely on reliable semantic environment perception for decision making. Despite great advances in video semantic segmentation, existing approaches ignore important inductive b…

Decision MakingScene SegmentationSegmentationSelf-Driving Cars+2

D$^2$NeRF: Self-Supervised Decoupling of Dynamic and Static Objects from a Monocular Video

2022-05-31 · Tianhao Wu, Fangcheng Zhong, Andrea Tagliasacchi, Forrester Cole 외

Given a monocular video, segmenting and decoupling dynamic objects while recovering the static environment is a widely studied problem in machine intelligence. Existing solutions usually approach this problem in the imag…

Image SegmentationNeRFSemantic SegmentationShadow Removal

Decoupling anomaly discrimination and representation learning: self-supervised learning for anomaly detection on attributed graph

2023-04-11 · YanMing Hu, Chuan Chen, Bowen Deng, YuJing Lai 외

Anomaly detection on attributed graphs is a crucial topic for its practical application. Existing methods suffer from semantic mixture and imbalance issue because they mainly focus on anomaly discrimination, ignoring rep…

Anomaly DetectionRepresentation LearningSelf-Supervised Learning