{"total":13,"rows":[{"id":"2311.07042","title":"Open-Vocabulary Video Anomaly Detection","created":"2023-11-13","cited_by_count":57,"area":null},{"id":"2309.00096","title":"AttrSeg: Open-Vocabulary Semantic Segmentation via Attribute Decomposition-Aggregation","created":"2023-08-31","cited_by_count":29,"area":null},{"id":"2403.11074","title":"Audio-Visual Segmentation via Unlabeled Frame Exploitation","created":"2024-03-17","cited_by_count":28,"area":null},{"id":"2407.11717","title":"Turbo: Informativity-Driven Acceleration Plug-In for Vision-Language Large Models","created":"2024-07-16","cited_by_count":13,"area":null},{"id":"2410.14238","title":"Storyboard guided Alignment for Fine-grained Video Action Recognition","created":"2024-10-18","cited_by_count":4,"area":null},{"id":"2502.12917","title":"Contrast-Unity for Partially-Supervised Temporal Sentence Grounding","created":"2025-02-18","cited_by_count":4,"area":null},{"id":"2511.01588","title":"Explore More, Learn Better: Parallel MLLM Embeddings under Mutual Information Minimization","created":"2025-11-03","cited_by_count":3,"area":null},{"id":"2503.14559","title":"Squeeze Out Tokens from Sample for Finer-Grained Data Governance","created":"2025-03-18","cited_by_count":2,"area":null},{"id":"2506.03662","title":"Zero-Shot Temporal Interaction Localization for Egocentric Videos","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2408.13777","title":"Towards Completeness: A Generalizable Action Proposal Generator for Zero-Shot Temporal Action Localization","created":"2024-08-25","cited_by_count":1,"area":null},{"id":"2508.12349","title":"EgoLoc: A Generalizable Solution for Temporal Interaction Localization in Egocentric Videos","created":"2025-08-17","cited_by_count":1,"area":null},{"id":"2511.01593","title":"Wave-Particle (Continuous-Discrete) Dualistic Visual Tokenization for Unified Understanding and Generation","created":"2025-11-03","cited_by_count":1,"area":null},{"id":"2603.24030","title":"Decompose and Transfer: CoT-Prompting Enhanced Alignment for Open-Vocabulary Temporal Action Detection","created":"2026-03-25","cited_by_count":0,"area":null}],"next_cursor":null}