{"total":32,"rows":[{"id":"2503.09146","title":"Generative Frame Sampler for Long Video Understanding","created":"2025-03-12","cited_by_count":37,"area":null},{"id":"2412.18619","title":"Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey","created":"2024-12-16","cited_by_count":27,"area":null},{"id":"2509.24008","title":"FrameMind: Frame-Interleaved Video Reasoning via Reinforcement Learning","created":"2025-09-28","cited_by_count":21,"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":"2602.15329","title":"EventMemAgent: Hierarchical Event-Centric Memory for Online Video Understanding with Adaptive Tool Use","created":"2026-02-17","cited_by_count":12,"area":null},{"id":"2412.08879","title":"Video Repurposing from User Generated Content: A Large-scale Dataset and Benchmark","created":"2024-12-12","cited_by_count":9,"area":null},{"id":"2506.09445","title":"TOGA: Temporally Grounded Open-Ended Video QA with Weak Supervision","created":"2025-06-11","cited_by_count":8,"area":null},{"id":"2512.03575","title":"UniComp: Rethinking Video Compression Through Informational Uniqueness","created":"2025-12-03","cited_by_count":7,"area":null},{"id":"2509.23724","title":"Video Panels for Long Video Understanding","created":"2025-09-28","cited_by_count":6,"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":"2501.03301","title":"Rethinking Byzantine Robustness in Federated Recommendation from Sparse Aggregation Perspective","created":"2025-01-06","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":"2603.23186","title":"ViKey: Enhancing Temporal Understanding in Videos via Visual Prompting","created":"2026-03-24","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":"2510.10671","title":"Image-to-Video Transfer Learning based on Image-Language Foundation Models: A Comprehensive Survey","created":"2025-10-12","cited_by_count":2,"area":null},{"id":"2607.11862","title":"Evidence-Backed Video Question Answering","created":"2026-07-13","cited_by_count":2,"area":null},{"id":"2508.07388","title":"Invert4TVG: A Temporal Video Grounding Framework with Inversion Tasks Preserving Action Understanding Ability","created":"2025-08-10","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":"2603.05969","title":"Imagine How To Change: Explicit Procedure Modeling for Change Captioning","created":"2026-03-06","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":"2604.03819","title":"ActivityForensics: A Comprehensive Benchmark for Localizing Manipulated Activity in Videos","created":"2026-04-04","cited_by_count":1,"area":null},{"id":"2604.10527","title":"STORM: End-to-End Referring Multi-Object Tracking in Videos","created":"2026-04-12","cited_by_count":1,"area":null},{"id":"2604.13715","title":"Towards Fine-grained Temporal Perception: Post-Training Large Audio-Language Models with Audio-Side Time Prompt","created":"2026-04-15","cited_by_count":1,"area":null},{"id":"2510.17519","title":"MUG-V 10B: High-efficiency Training Pipeline for Large Video Generation Models","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2603.13710","title":"InterventionLens: A Multi-Agent Framework for Detecting ASD Intervention Strategies in Parent-Child Shared Reading","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2605.00684","title":"Static and Dynamic Graph Alignment Network for Temporal Video Grounding","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2605.14705","title":"Towards Continuous Sign Language Conversation from Isolated Signs","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2607.23951","title":"TimePLE: Rethinking Temporal Representation for Video Temporal Grounding","created":"2026-07-27","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":"2608.30584","title":"Learning Compositional Spatio-Temporal Video Grounding with Synthetic Curriculum","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.15224","title":"Long-to-Short Video Evidence Reasoning for Grounded Question Answering","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.39883","title":"Grounding with Confidence: Controllable Generative Video Temporal Grounding","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}