{"total":23,"rows":[{"id":"2304.11234","title":"Advances in Deep Concealed Scene Understanding","created":"2023-04-21","cited_by_count":47,"area":null},{"id":"2408.14562","title":"A Survey of Camouflaged Object Detection and Beyond","created":"2024-08-26","cited_by_count":37,"area":null},{"id":"2211.12883","title":"Mitigating and Evaluating Static Bias of Action Representations in the Background and the Foreground","created":"2022-11-23","cited_by_count":27,"area":null},{"id":"2308.11488","title":"Opening the Vocabulary of Egocentric Actions","created":"2023-08-22","cited_by_count":23,"area":null},{"id":"2207.06261","title":"Is Appearance Free Action Recognition Possible?","created":"2022-07-13","cited_by_count":16,"area":null},{"id":"2303.17285","title":"Decomposed Cross-modal Distillation for RGB-based Temporal Action Detection","created":"2023-03-30","cited_by_count":12,"area":null},{"id":"2311.18825","title":"CAST: Cross-Attention in Space and Time for Video Action Recognition","created":"2023-11-30","cited_by_count":12,"area":null},{"id":"2306.08889","title":"Dissecting Multimodality in VideoQA Transformer Models by Impairing Modality Fusion","created":"2023-06-15","cited_by_count":8,"area":null},{"id":"2403.12710","title":"Selective, Interpretable, and Motion Consistent Privacy Attribute Obfuscation for Action Recognition","created":"2024-03-19","cited_by_count":8,"area":null},{"id":"2407.10860","title":"Human-Centric Transformer for Domain Adaptive Action Recognition","created":"2024-07-15","cited_by_count":8,"area":null},{"id":"2211.01783","title":"Quantifying and Learning Static vs. Dynamic Information in Deep Spatiotemporal Networks","created":"2022-11-03","cited_by_count":7,"area":null},{"id":"2211.05120","title":"Deep Learning based Computer Vision Methods for Complex Traffic Environments Perception: A Review","created":"2022-11-09","cited_by_count":7,"area":null},{"id":"2503.19730","title":"CamSAM2: Segment Anything Accurately in Camouflaged Videos","created":"2025-03-25","cited_by_count":7,"area":null},{"id":"2307.07812","title":"Multiscale Memory Comparator Transformer for Few-Shot Video Segmentation","created":"2023-07-15","cited_by_count":2,"area":null},{"id":"2606.07770","title":"Contrast encodes inductive bias: separating slow noise from dynamics in predictive representation learning","created":"2026-06-05","cited_by_count":2,"area":null},{"id":"2304.05930","title":"MED-VT++: Unifying Multimodal Learning with a Multiscale Encoder-Decoder Video Transformer","created":"2023-04-12","cited_by_count":1,"area":null},{"id":"2506.17685","title":"Domain Generalization using Action Sequences for Egocentric Action Recognition","created":"2025-06-21","cited_by_count":1,"area":null},{"id":"2508.10896","title":"ESSENTIAL: Episodic and Semantic Memory Integration for Video Class-Incremental Learning","created":"2025-08-14","cited_by_count":1,"area":null},{"id":"2606.03490","title":"TrAction: Action Recognition with Sparse Trajectories","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2610.00064","title":"Reachability Is Not Generalization: Understanding Verb--Noun Decomposition in Assembly Action Recognition","created":"2026-09-04","cited_by_count":1,"area":null},{"id":"2503.23447","title":"CA^2ST: Cross-Attention in Audio, Space, and Time for Holistic Video Recognition","created":"2025-03-30","cited_by_count":0,"area":null},{"id":"2609.33419","title":"TT-VidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.16471","title":"Auditing Observation-Quality Shortcuts in the Evaluation of Person-Centered Motion for Video Anomaly Detection","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}