{"total":23,"rows":[{"id":"2112.01514","title":"Self-supervised Video Transformer","created":"2021-12-02","cited_by_count":64,"area":null},{"id":"2404.04346","title":"Koala: Key frame-conditioned long video-LLM","created":"2024-04-05","cited_by_count":57,"area":null},{"id":"2403.14622","title":"Language Repository for Long Video Understanding","created":"2024-03-21","cited_by_count":55,"area":null},{"id":"2112.03902","title":"MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection","created":"2021-12-07","cited_by_count":42,"area":null},{"id":"2305.15701","title":"Action Sensitivity Learning for Temporal Action Localization","created":"2023-05-25","cited_by_count":28,"area":null},{"id":"2108.04536","title":"Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition","created":"2021-08-10","cited_by_count":25,"area":null},{"id":"2211.09119","title":"Token Turing Machines","created":"2022-11-16","cited_by_count":25,"area":null},{"id":"2210.11035","title":"PointTAD: Multi-Label Temporal Action Detection with Learnable Query Points","created":"2022-10-20","cited_by_count":22,"area":null},{"id":"2404.00653","title":"Dual DETRs for Multi-Label Temporal Action Detection","created":"2024-03-31","cited_by_count":20,"area":null},{"id":"2104.02357","title":"Adaptive Mutual Supervision for Weakly-Supervised Temporal Action Localization","created":"2021-04-06","cited_by_count":18,"area":null},{"id":"2112.06447","title":"SVIP: Sequence VerIfication for Procedures in Videos","created":"2021-12-13","cited_by_count":16,"area":null},{"id":"2404.04933","title":"UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection","created":"2024-04-07","cited_by_count":16,"area":null},{"id":"2303.12149","title":"SPARTAN: Self-supervised Spatiotemporal Transformers Approach to Group Activity Recognition","created":"2023-03-06","cited_by_count":14,"area":null},{"id":"2305.06310","title":"SoGAR: Self-supervised Spatiotemporal Attention-based Social Group Activity Recognition","created":"2023-04-27","cited_by_count":8,"area":null},{"id":"2308.05051","title":"PAT: Position-Aware Transformer for Dense Multi-Label Action Detection","created":"2023-08-09","cited_by_count":6,"area":null},{"id":"2111.13675","title":"Weakly-guided Self-supervised Pretraining for Temporal Activity Detection","created":"2021-11-26","cited_by_count":5,"area":null},{"id":"2303.08463","title":"Co-Occurrence Matters: Learning Action Relation for Temporal Action Localization","created":"2023-03-15","cited_by_count":1,"area":null},{"id":"2309.00696","title":"AAN: Attributes-Aware Network for Temporal Action Detection","created":"2023-09-01","cited_by_count":1,"area":null},{"id":"2311.02432","title":"P-Age: Pexels Dataset for Robust Spatio-Temporal Apparent Age Classification","created":"2023-11-04","cited_by_count":1,"area":null},{"id":"2206.12420","title":"SCAI: A Spectral data Classification framework with Adaptive Inference for the IoT platform","created":"2022-06-24","cited_by_count":0,"area":null},{"id":"2406.06187","title":"An Effective-Efficient Approach for Dense Multi-Label Action Detection","created":"2024-06-10","cited_by_count":0,"area":null},{"id":"2409.20270","title":"Loose Social-Interaction Recognition in Real-world Therapy Scenarios","created":"2024-09-30","cited_by_count":0,"area":null},{"id":"2501.18509","title":"Reframing Dense Action Detection (RefDense): A Paradigm Shift in Problem Solving & a Novel Optimization Strategy","created":"2025-01-30","cited_by_count":0,"area":null}],"next_cursor":null}