{"total":20,"rows":[{"id":"2401.01578","title":"Context-Guided Spatio-Temporal Video Grounding","created":"2024-01-03","cited_by_count":46,"area":null},{"id":"2309.13925","title":"Towards Surveillance Video-and-Language Understanding: New Dataset, Baselines, and Challenges","created":"2023-09-25","cited_by_count":42,"area":null},{"id":"2502.11168","title":"Knowing Your Target: Target-Aware Transformer Makes Better Spatio-Temporal Video Grounding","created":"2025-02-16","cited_by_count":18,"area":null},{"id":"2503.13016","title":"Efficient Motion-Aware Video MLLM","created":"2025-03-17","cited_by_count":14,"area":null},{"id":"2403.05021","title":"Beyond MOT: Semantic Multi-Object Tracking","created":"2024-03-08","cited_by_count":12,"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":"2606.02569","title":"AdaCodec: A Predictive Visual Code for Video MLLMs","created":"2026-06-01","cited_by_count":7,"area":null},{"id":"2410.08860","title":"Audio Description Generation in the Era of LLMs and VLMs: A Review of Transferable Generative AI Technologies","created":"2024-10-11","cited_by_count":5,"area":null},{"id":"2412.20964","title":"Hierarchical Banzhaf Interaction for General Video-Language Representation Learning","created":"2024-12-30","cited_by_count":4,"area":null},{"id":"2503.17417","title":"Generative Modeling of Class Probability for Multi-Modal Representation Learning","created":"2025-03-21","cited_by_count":3,"area":null},{"id":"2501.18269","title":"MAMS: Model-Agnostic Module Selection Framework for Video Captioning","created":"2025-01-30","cited_by_count":2,"area":null},{"id":"2312.13330","title":"Towards Subject-Oriented Video Captioning via User-Specified Targets","created":"2023-12-20","cited_by_count":1,"area":null},{"id":"2508.17932","title":"See What You Need: Query-Aware Visual Intelligence through Reasoning-Perception Loops","created":"2025-08-25","cited_by_count":1,"area":null},{"id":"2311.14977","title":"Incorporating granularity bias as the margin into contrastive loss for video captioning","created":"2023-11-25","cited_by_count":0,"area":null},{"id":"2412.10720","title":"Bridging Vision and Language: Modeling Causality and Temporality in Video Narratives","created":"2024-12-14","cited_by_count":0,"area":null},{"id":"2503.23679","title":"The Devil is in the Distributions: Explicit Modeling of Scene Content is Key in Zero-Shot Video Captioning","created":"2025-03-31","cited_by_count":0,"area":null},{"id":"2508.01270","title":"SGCap: Decoding Semantic Group for Zero-shot Video Captioning","created":"2025-08-02","cited_by_count":0,"area":null},{"id":"2607.13421","title":"ScanFocus: A Coarse-to-Fine Framework for Spatio-Temporal Video Grounding","created":"2026-07-15","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":"2609.31700","title":"Modernising the Compressed-Domain Video Captioner: A Controlled Study of SigLIP2 and GPT-2 Substitutions","created":"2026-09-19","cited_by_count":0,"area":null}],"next_cursor":null}