{"total":33,"rows":[{"id":"2306.02018","title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","created":"2023-06-03","cited_by_count":464,"area":null},{"id":"2108.09322","title":"MM-ViT: Multi-Modal Video Transformer for Compressed Video Action Recognition","created":"2021-08-20","cited_by_count":46,"area":null},{"id":"2303.07863","title":"You Can Ground Earlier than See: An Effective and Efficient Pipeline for Temporal Sentence Grounding in Compressed Videos","created":"2023-03-14","cited_by_count":41,"area":null},{"id":"2104.00862","title":"Self-supervised Video Representation Learning by Context and Motion Decoupling","created":"2021-04-02","cited_by_count":34,"area":null},{"id":"2207.12622","title":"Multi-Attention Network for Compressed Video Referring Object Segmentation","created":"2022-07-26","cited_by_count":28,"area":null},{"id":"2202.02813","title":"A Coding Framework and Benchmark towards Low-Bitrate Video Understanding","created":"2022-02-06","cited_by_count":17,"area":null},{"id":"2203.15336","title":"End-to-End Compressed Video Representation Learning for Generic Event Boundary Detection","created":"2022-03-29","cited_by_count":16,"area":null},{"id":"2203.08897","title":"Gate-Shift-Fuse for Video Action Recognition","created":"2022-03-16","cited_by_count":15,"area":null},{"id":"2211.06742","title":"Deep Unsupervised Key Frame Extraction for Efficient Video Classification","created":"2022-11-12","cited_by_count":14,"area":null},{"id":"2309.01265","title":"SOAR: Scene-debiasing Open-set Action Recognition","created":"2023-09-03","cited_by_count":12,"area":null},{"id":"2406.04765","title":"SMC++: Masked Learning of Unsupervised Video Semantic Compression","created":"2024-06-07","cited_by_count":12,"area":null},{"id":"2602.13191","title":"CoPE-VideoLM: Leveraging Codec Primitives For Efficient Video Language Modeling","created":"2026-02-13","cited_by_count":11,"area":null},{"id":"2101.00317","title":"Identity-aware Facial Expression Recognition in Compressed Video","created":"2021-01-01","cited_by_count":9,"area":null},{"id":"2210.02995","title":"Compressed Vision for Efficient Video Understanding","created":"2022-10-06","cited_by_count":8,"area":null},{"id":"2211.01781","title":"Video Event Extraction via Tracking Visual States of Arguments","created":"2022-11-03","cited_by_count":8,"area":null},{"id":"2303.07224","title":"Efficient Semantic Segmentation by Altering Resolutions for Compressed Videos","created":"2023-03-13","cited_by_count":8,"area":null},{"id":"2201.10162","title":"Semantically Video Coding: Instill Static-Dynamic Clues into Structured Bitstream for AI Tasks","created":"2022-01-25","cited_by_count":7,"area":null},{"id":"2606.02569","title":"AdaCodec: A Predictive Visual Code for Video MLLMs","created":"2026-06-01","cited_by_count":7,"area":null},{"id":"2404.04848","title":"Task-Aware Encoder Control for Deep Video Compression","created":"2024-04-07","cited_by_count":6,"area":null},{"id":"2110.08814","title":"TEAM-Net: Multi-modal Learning for Video Action Recognition with Partial Decoding","created":"2021-10-17","cited_by_count":5,"area":null},{"id":"2309.15431","title":"Local Compressed Video Stream Learning for Generic Event Boundary Detection","created":"2023-09-27","cited_by_count":3,"area":null},{"id":"2103.03465","title":"Unsupervised Motion Representation Enhanced Network for Action Recognition","created":"2021-03-05","cited_by_count":2,"area":null},{"id":"2503.13724","title":"Towards Scalable Modeling of Compressed Videos for Efficient Action Recognition","created":"2025-03-17","cited_by_count":2,"area":null},{"id":"2101.00359","title":"Video Captioning in Compressed Video","created":"2021-01-02","cited_by_count":1,"area":null},{"id":"2110.01015","title":"Spatio-Temporal Video Representation Learning for AI Based Video Playback Style Prediction","created":"2021-10-03","cited_by_count":1,"area":null},{"id":"2205.03569","title":"Representation Learning for Compressed Video Action Recognition via Attentive Cross-modal Interaction with Motion Enhancement","created":"2022-05-07","cited_by_count":1,"area":null},{"id":"2604.03640","title":"ComPrivDet: Efficient Privacy Object Detection in Compressed Domains Through Inference Reuse","created":"2026-04-04","cited_by_count":1,"area":null},{"id":"2606.31004","title":"Auditing Generalization in AI-Generated Video Detection: A Six-Control Protocol and the VidAudit Toolkit","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2209.14757","title":"Speeding Up Action Recognition Using Dynamic Accumulation of Residuals in Compressed Domain","created":"2022-09-29","cited_by_count":0,"area":null},{"id":"2212.10174","title":"CGCV:Context Guided Correlation Volume for Optical Flow Neural Networks","created":"2022-12-20","cited_by_count":0,"area":null},{"id":"2307.04132","title":"Reasoning over the Behaviour of Objects in Video-Clips for Adverb-Type Recognition","created":"2023-07-09","cited_by_count":0,"area":null},{"id":"2401.07584","title":"Collaboratively Self-supervised Video Representation Learning for Action Recognition","created":"2024-01-15","cited_by_count":0,"area":null},{"id":"2608.21837","title":"Towards Bitstream-corrupted Harsh Visual Understanding: Through Bitstream Language Modeling as Robust Semantic Priors","created":"2026-08-22","cited_by_count":0,"area":null}],"next_cursor":null}