{"total":48,"rows":[{"id":"2411.10332","title":"Number it: Temporal Grounding Videos like Flipping Manga","created":"2024-11-15","cited_by_count":65,"area":null},{"id":"2506.05302","title":"Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos","created":"2025-06-05","cited_by_count":51,"area":null},{"id":"2504.14693","title":"Video-MMLU: A Massive Multi-Discipline Lecture Understanding Benchmark","created":"2025-04-20","cited_by_count":37,"area":null},{"id":"2502.12782","title":"VidCapBench: A Comprehensive Benchmark of Video Captioning for Controllable Text-to-Video Generation","created":"2025-02-18","cited_by_count":23,"area":null},{"id":"2510.22693","title":"VADTree: Explainable Training-Free Video Anomaly Detection via Hierarchical Granularity-Aware Tree","created":"2025-10-26","cited_by_count":18,"area":null},{"id":"2412.09601","title":"TimeRefine: Temporal Grounding with Time Refining Video LLM","created":"2024-12-12","cited_by_count":15,"area":null},{"id":"2412.13845","title":"Do Language Models Understand Time?","created":"2024-12-18","cited_by_count":14,"area":null},{"id":"2504.01020","title":"Shot-by-Shot: Film-Grammar-Aware Training-Free Audio Description Generation","created":"2025-04-01","cited_by_count":13,"area":null},{"id":"2502.11594","title":"iMOVE: Instance-Motion-Aware Video Understanding","created":"2025-02-17","cited_by_count":10,"area":null},{"id":"2504.05541","title":"Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting","created":"2025-04-07","cited_by_count":10,"area":null},{"id":"2512.03666","title":"ToG-Bench: Task-Oriented Spatio-Temporal Grounding in Egocentric Videos","created":"2025-12-03","cited_by_count":8,"area":null},{"id":"2512.09841","title":"ChronusOmni: Improving Time Awareness of Omni Large Language Models","created":"2025-12-10","cited_by_count":6,"area":null},{"id":"2509.26360","title":"TimeScope: Towards Task-Oriented Temporal Grounding In Long Videos","created":"2025-09-30","cited_by_count":5,"area":null},{"id":"2511.16937","title":"OmniGround: A Comprehensive Spatio-Temporal Grounding Benchmark for Real-World Complex Scenarios","created":"2025-11-21","cited_by_count":5,"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":"2504.05925","title":"SVLTA: Benchmarking Vision-Language Temporal Alignment via Synthetic Video Situation","created":"2025-04-08","cited_by_count":4,"area":null},{"id":"2507.14784","title":"LeAdQA: LLM-Driven Context-Aware Temporal Grounding for Video Question Answering","created":"2025-07-20","cited_by_count":4,"area":null},{"id":"2512.24097","title":"Factorized Learning for Temporally Grounded Video-Language Models","created":"2025-12-30","cited_by_count":4,"area":null},{"id":"2601.04778","title":"CounterVid: Counterfactual Video Generation for Mitigating Action and Temporal Hallucinations in Video-Language Models","created":"2026-01-08","cited_by_count":4,"area":null},{"id":"2601.06559","title":"ArrowGEV: Grounding Events in Video via Learning the Arrow of Time","created":"2026-01-10","cited_by_count":4,"area":null},{"id":"2604.25276","title":"OmniVTG: A Large-Scale Dataset and Training Paradigm for Open-World Video Temporal Grounding","created":"2026-04-28","cited_by_count":4,"area":null},{"id":"2605.13803","title":"EvoGround: Self-Evolving Video Agents for Video Temporal Grounding","created":"2026-05-13","cited_by_count":4,"area":null},{"id":"2606.06294","title":"Towards One-to-Many Temporal Grounding","created":"2026-06-04","cited_by_count":4,"area":null},{"id":"2511.23151","title":"Learning to Refuse: Refusal-Aware Reinforcement Fine-Tuning for Hard-Irrelevant Queries in Video Temporal Grounding","created":"2025-11-28","cited_by_count":3,"area":null},{"id":"2503.09027","title":"Measure Twice, Cut Once: A Semantic-Oriented Approach to Video Temporal Localization with Video LLMs","created":"2025-03-12","cited_by_count":2,"area":null},{"id":"2601.17868","title":"VidLaDA: Bidirectional Diffusion Large Language Models for Efficient Video Understanding","created":"2026-01-25","cited_by_count":2,"area":null},{"id":"2508.06317","title":"Uncertainty-quantified Rollout Policy Adaptation for Unlabelled Cross-domain Temporal Grounding","created":"2025-08-08","cited_by_count":1,"area":null},{"id":"2510.12126","title":"MetaCaptioner: Towards Generalist Visual Captioning with Open-source Suites","created":"2025-10-14","cited_by_count":1,"area":null},{"id":"2601.07366","title":"HiVid-Narrator: Hierarchical Video Narrative Generation with Scene-Primed ASR-anchored Compression","created":"2026-01-12","cited_by_count":1,"area":null},{"id":"2602.05215","title":"E.M.Ground: A Temporal Grounding Vid-LLM with Holistic Event Perception and Matching","created":"2026-02-05","cited_by_count":1,"area":null},{"id":"2603.06973","title":"T2SGrid: Temporal-to-Spatial Gridification for Video Temporal Grounding","created":"2026-03-07","cited_by_count":1,"area":null},{"id":"2605.26104","title":"EVIDENT: Routing MLLM Adaptation through Entity-Grounded Visual Evidence for Cross-Domain Video Temporal Grounding","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2609.35718","title":"Hard Vision, Easy Vision: What GPT-6 Astra Reveals Across Computer Vision","created":"2026-09-28","cited_by_count":1,"area":null},{"id":"2601.11178","title":"TANDEM: Temporal-Aware Neural Detection for Multimodal Hate Speech","created":"2026-01-16","cited_by_count":0,"area":null},{"id":"2602.19146","title":"VIGiA: Instructional Video Guidance via Dialogue Reasoning and Retrieval","created":"2026-02-22","cited_by_count":0,"area":null},{"id":"2604.02860","title":"A Paradigm Shift: Fully End-to-End Training for Temporal Sentence Grounding in Videos","created":"2026-04-03","cited_by_count":0,"area":null},{"id":"2605.01512","title":"Two-Pass Zero-Shot Temporal-Spatial Grounding of Rare Traffic Events in Surveillance Video","created":"2026-05-02","cited_by_count":0,"area":null},{"id":"2605.02623","title":"Retrieving Any Relevant Moments: Benchmark and Models for Generalized Moment Retrieval","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2605.03398","title":"MASRA: MLLM-Assisted Semantic-Relational Consistent Alignment for Video Temporal Grounding","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2605.10833","title":"MMVIAD: Multi-view Multi-task Video Understanding for Industrial Anomaly Detection","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2606.02402","title":"Explainable Forensics of Manipulated Segments in Untrimmed Long Videos","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.06926","title":"SVHighlights: Towards Extremely Long Sport Video Highlight Detection","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2607.05095","title":"FAST: A Holistic Framework for Optimizing Memory-I/O, Computation, and Sampling in Temporal GNN Training","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.04480","title":"REZE: Recognition-Based Zero-Shot Extraction for Video Temporal Grounding","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.28192","title":"Locate Anything in Videos: Rethinking Efficient Generative Spatio-Temporal Video Grounding","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.04183","title":"Seeing Before Synthesizing: VLM-Guided Transition Event Discovery for Weakly-Supervised Dense Video Captioning","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.09736","title":"IAE-VTG: Interaction-Aligned Action-Entity Video Temporal Grounding","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.17923","title":"Audio for Sports Highlight Detection: A Comparative Empirical Study","created":"2026-09-15","cited_by_count":0,"area":null}],"next_cursor":null}