{"total":17,"rows":[{"id":"2406.09399","title":"OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation","created":"2024-06-13","cited_by_count":118,"area":null},{"id":"2603.02096","title":"FluxMem: Adaptive Hierarchical Memory for Streaming Video Understanding","created":"2026-03-02","cited_by_count":28,"area":null},{"id":"2412.13845","title":"Do Language Models Understand Time?","created":"2024-12-18","cited_by_count":14,"area":null},{"id":"2412.10443","title":"SweetTok: Semantic-Aware Spatial-Temporal Tokenizer for Compact Video Discretization","created":"2024-12-11","cited_by_count":12,"area":null},{"id":"2506.03605","title":"Generating 6DoF Object Manipulation Trajectories from Action Description in Egocentric Vision","created":"2025-06-04","cited_by_count":11,"area":null},{"id":"2507.20163","title":"Player-Centric Multimodal Prompt Generation for Large Language Model Based Identity-Aware Basketball Video Captioning","created":"2025-07-27","cited_by_count":7,"area":null},{"id":"2601.07290","title":"VideoLoom: A Video Large Language Model for Joint Spatial-Temporal Understanding","created":"2026-01-12","cited_by_count":5,"area":null},{"id":"2603.22953","title":"Cluster-Wise Spatio-Temporal Masking for Efficient Video-Language Pretraining","created":"2026-03-24","cited_by_count":2,"area":null},{"id":"2507.14743","title":"InterAct-Video: Reasoning-Rich Video QA for Urban Traffic","created":"2025-07-19","cited_by_count":1,"area":null},{"id":"2509.21783","title":"Prompt-guided Disentangled Representation for Action Recognition","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2511.19475","title":"Tracking and Segmenting Anything in Any Modality","created":"2025-11-22","cited_by_count":1,"area":null},{"id":"2509.03426","title":"Time-Scaling State-Space Models for Dense Video Captioning","created":"2025-09-03","cited_by_count":0,"area":null},{"id":"2512.01128","title":"OmniFD: A Unified Model for Versatile Face Forgery Detection","created":"2025-11-30","cited_by_count":0,"area":null},{"id":"2607.26097","title":"Knowledge-guided Disentanglement with Atomic Actions for Action Recognition","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.04939","title":"Reading Between the Frames of Multimodal Drivelology","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.20690","title":"Identity-Aware Human-Object Interaction Motion Captioning","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.24031","title":"Video-STLayout Pre-training","created":"2026-09-21","cited_by_count":0,"area":null}],"next_cursor":null}