{"total":94,"rows":[{"id":"2501.12380","title":"MMVU: Measuring Expert-Level Multi-Discipline Video Understanding","created":"2025-01-21","cited_by_count":137,"area":null},{"id":"2402.13217","title":"VideoPrism: A Foundational Visual Encoder for Video Understanding","created":"2024-02-20","cited_by_count":105,"area":null},{"id":"2501.00599","title":"VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM","created":"2024-12-31","cited_by_count":72,"area":null},{"id":"2410.06234","title":"TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data","created":"2024-10-08","cited_by_count":70,"area":null},{"id":"2404.12353","title":"V2Xum-LLM: Cross-Modal Video Summarization with Temporal Prompt Instruction Tuning","created":"2024-04-18","cited_by_count":46,"area":null},{"id":"2404.14368","title":"Graphic Design with Large Multimodal Model","created":"2024-04-22","cited_by_count":40,"area":null},{"id":"2404.19664","title":"Towards Generalist Robot Learning from Internet Video: A Survey","created":"2024-04-30","cited_by_count":40,"area":null},{"id":"2406.05615","title":"Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives","created":"2024-06-09","cited_by_count":37,"area":null},{"id":"2503.13139","title":"Logic-in-Frames: Dynamic Keyframe Search via Visual Semantic-Logical Verification for Long Video Understanding","created":"2025-03-17","cited_by_count":34,"area":null},{"id":"2408.04223","title":"VideoQA in the Era of LLMs: An Empirical Study","created":"2024-08-08","cited_by_count":29,"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":"2509.24008","title":"FrameMind: Frame-Interleaved Video Reasoning via Reinforcement Learning","created":"2025-09-28","cited_by_count":21,"area":null},{"id":"2412.17799","title":"Automating the Search for Artificial Life with Foundation Models","created":"2024-12-23","cited_by_count":20,"area":null},{"id":"2506.10890","title":"CreatiPoster: Towards Editable and Controllable Multi-Layer Graphic Design Generation","created":"2025-06-12","cited_by_count":19,"area":null},{"id":"2410.10441","title":"Free Video-LLM: Prompt-guided Visual Perception for Efficient Training-free Video LLMs","created":"2024-10-14","cited_by_count":17,"area":null},{"id":"2411.13610","title":"Video2BEV: Transforming Drone Videos to BEVs for Video-based Geo-localization","created":"2024-11-20","cited_by_count":17,"area":null},{"id":"2501.06250","title":"Generative AI for Cel-Animation: A Survey","created":"2025-01-08","cited_by_count":17,"area":null},{"id":"2401.09386","title":"Tri$^{2}$-plane: Thinking Head Avatar via Feature Pyramid","created":"2024-01-17","cited_by_count":16,"area":null},{"id":"2402.17128","title":"OSCaR: Object State Captioning and State Change Representation","created":"2024-02-27","cited_by_count":16,"area":null},{"id":"2409.17523","title":"EAGLE: Egocentric AGgregated Language-video Engine","created":"2024-09-26","cited_by_count":16,"area":null},{"id":"2410.04960","title":"On Efficient Variants of Segment Anything Model: A Survey","created":"2024-10-07","cited_by_count":16,"area":null},{"id":"2503.14378","title":"Impossible Videos","created":"2025-03-18","cited_by_count":16,"area":null},{"id":"2412.13845","title":"Do Language Models Understand Time?","created":"2024-12-18","cited_by_count":14,"area":null},{"id":"2505.18078","title":"DanceTogether! Identity-Preserving Multi-Person Interactive Video Generation","created":"2025-05-23","cited_by_count":13,"area":null},{"id":"2407.03179","title":"Motion meets Attention: Video Motion Prompts","created":"2024-07-03","cited_by_count":12,"area":null},{"id":"2512.04451","title":"StreamEQA: Towards Streaming Video Understanding for Embodied Scenarios","created":"2025-12-04","cited_by_count":12,"area":null},{"id":"2602.00288","title":"TimeBlind: A Spatio-Temporal Compositionality Benchmark for Video LLMs","created":"2026-01-30","cited_by_count":11,"area":null},{"id":"2410.05714","title":"Enhancing Temporal Modeling of Video LLMs via Time Gating","created":"2024-10-08","cited_by_count":10,"area":null},{"id":"2411.09105","title":"VideoCogQA: A Controllable Benchmark for Evaluating Cognitive Abilities in Video-Language Models","created":"2024-11-14","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":"2512.12675","title":"Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling","created":"2025-12-14","cited_by_count":10,"area":null},{"id":"2505.20124","title":"TUNA: Comprehensive Fine-grained Temporal Understanding Evaluation on Dense Dynamic Videos","created":"2025-05-26","cited_by_count":9,"area":null},{"id":"2504.09282","title":"VideoAds for Fast-Paced Video Understanding","created":"2025-04-12","cited_by_count":8,"area":null},{"id":"2505.16630","title":"SoccerChat: Integrating Multimodal Data for Enhanced Soccer Game Understanding","created":"2025-05-22","cited_by_count":8,"area":null},{"id":"2605.07897","title":"Semantic-Aware Adaptive Visual Memory for Streaming Video Understanding","created":"2026-05-08","cited_by_count":8,"area":null},{"id":"2511.17490","title":"Video-R4: Reinforcing Text-Rich Video Reasoning with Visual Rumination","created":"2025-11-21","cited_by_count":6,"area":null},{"id":"2402.13546","title":"LLMs Meet Long Video: Advancing Long Video Question Answering with An Interactive Visual Adapter in LLMs","created":"2024-02-21","cited_by_count":5,"area":null},{"id":"2408.07249","title":"Bridging Information Asymmetry in Text-video Retrieval: A Data-centric Approach","created":"2024-08-14","cited_by_count":5,"area":null},{"id":"2502.02487","title":"Hier-EgoPack: Hierarchical Egocentric Video Understanding with Diverse Task Perspectives","created":"2025-02-04","cited_by_count":5,"area":null},{"id":"2512.16891","title":"LinkedOut: Linking World Knowledge Representation Out of Video LLM for Next-Generation Video Recommendation","created":"2025-12-18","cited_by_count":5,"area":null},{"id":"2605.17423","title":"Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration","created":"2026-05-17","cited_by_count":5,"area":null},{"id":"2504.07867","title":"SAMJAM: Zero-Shot Video Scene Graph Generation for Egocentric Kitchen Videos","created":"2025-04-10","cited_by_count":4,"area":null},{"id":"2509.20851","title":"Poisoning Prompt-Guided Sampling in Video Large Language Models","created":"2025-09-25","cited_by_count":4,"area":null},{"id":"2604.05079","title":"SVAgent: Storyline-Guided Long Video Understanding via Cross-Modal Multi-Agent Collaboration","created":"2026-04-06","cited_by_count":4,"area":null},{"id":"2410.01180","title":"UAL-Bench: The First Comprehensive Unusual Activity Localization Benchmark","created":"2024-10-02","cited_by_count":3,"area":null},{"id":"2505.04488","title":"\"I Can See Forever!\": Evaluating Real-time VideoLLMs for Assisting Individuals with Visual Impairments","created":"2025-05-07","cited_by_count":3,"area":null},{"id":"2511.18831","title":"VideoCompressa: Data-Efficient Video Understanding via Joint Temporal Compression and Spatial Reconstruction","created":"2025-11-24","cited_by_count":3,"area":null},{"id":"2604.26707","title":"CurEvo: Curriculum-Guided Self-Evolution for Video Understanding","created":"2026-04-29","cited_by_count":3,"area":null},{"id":"2609.00291","title":"StreamScout: Learning When to Look Deeper for Streaming Video Understanding","created":"2026-08-31","cited_by_count":3,"area":null},{"id":"2412.09907","title":"IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs","created":"2024-12-13","cited_by_count":2,"area":null},{"id":"2503.09205","title":"Quality Over Quantity? LLM-Based Curation for a Data-Efficient Audio-Video Foundation Model","created":"2025-03-12","cited_by_count":2,"area":null},{"id":"2504.02009","title":"Urban Computing in the Era of Large Language Models","created":"2025-04-02","cited_by_count":2,"area":null},{"id":"2603.29494","title":"VecAttention: Vector-wise Sparse Attention for Accelerating Long Context Inference","created":"2026-03-31","cited_by_count":2,"area":null},{"id":"2605.18018","title":"See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object Understanding","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2506.02012","title":"Leveraging Large Language Models in Visual Speech Recognition: Model Scaling, Context-Aware Decoding, and Iterative Polishing","created":"2025-05-27","cited_by_count":1,"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":"2511.20965","title":"TrafficLens: Multi-Camera Traffic Video Analysis Using LLMs","created":"2025-11-26","cited_by_count":1,"area":null},{"id":"2602.07689","title":"Process-of-Thought Reasoning for Videos","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2602.11244","title":"Stress Tests REVEAL Fragile Temporal and Visual Grounding in Video-Language Models","created":"2026-02-11","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":"2606.03471","title":"A formal definition and meta-model for a machine theory of mind","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2409.10641","title":"HAVANA: Hierarchical stochastic neighbor embedding for Accelerated Video ANnotAtions","created":"2024-09-16","cited_by_count":0,"area":null},{"id":"2410.14993","title":"Making Every Frame Matter: Continuous Activity Recognition in Streaming Video via Adaptive Video Context Modeling","created":"2024-10-19","cited_by_count":0,"area":null},{"id":"2502.09573","title":"Optimizing GPT for Video Understanding: Zero-Shot Performance and Prompt Engineering","created":"2025-02-13","cited_by_count":0,"area":null},{"id":"2504.09893","title":"LangPert: Detecting and Handling Task-level Perturbations for Robust Object Rearrangement","created":"2025-04-14","cited_by_count":0,"area":null},{"id":"2505.19554","title":"Aggregated Structural Representation with Large Language Models for Human-Centric Layout Generation","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2505.19568","title":"MSD-LLM: Predicting Ship Detention in Port State Control Inspections with Large Language Model","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2509.06335","title":"Harnessing Object Grounding for Time-Sensitive Video Understanding","created":"2025-09-08","cited_by_count":0,"area":null},{"id":"2509.09151","title":"Video Understanding by Design: How Datasets Shape Video Models","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2509.16810","title":"Automated Procedural Analysis via Video-Language Models for AI-assisted Nursing Skills Assessment","created":"2025-09-20","cited_by_count":0,"area":null},{"id":"2509.22544","title":"HyCoVAD: A Hybrid SSL-LLM Model for Complex Video Anomaly Detection","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2510.08138","title":"Understanding Temporal Logic Consistency in Video-Language Models through Cross-Modal Attention Discriminability","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2510.18362","title":"FeatureFool: Zero-Query Fooling of Video Models via Feature Map","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2510.19292","title":"Vision-Based Mistake Analysis in Procedural Activities: A Review of Advances and Challenges","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2601.14773","title":"Semantic-Guided Unsupervised Video Summarization","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2603.00126","title":"QuickGrasp: Responsive Video-Language Querying Service via Accelerated Tokenization and Edge-Augmented Inference","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2603.12887","title":"Forecasting Epileptic Seizures from Contactless Camera via Cross-Species Transfer Learning","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2603.20187","title":"NOUS: Video-Driven 3D Human Reaction Generation via Observation-Reaction Mutual Steering","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2603.26772","title":"From Content to Audience: A Multimodal Annotation Framework for Broadcast Television Analytics","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2603.27662","title":"A Benchmarking Methodology to Assess Open-Source Video Large Language Models in Automatic Captioning of News Videos","created":"2026-03-29","cited_by_count":0,"area":null},{"id":"2605.00826","title":"Understanding the Performance Plateau in Text-to-Video Retrieval: A Comprehensive Empirical and Linguistic Analysis","created":"2026-03-07","cited_by_count":0,"area":null},{"id":"2605.28604","title":"Mining Multi-Modality Spatio-Temporal Cues for Video Important Person Identification","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.06338","title":"StoryVideoQA: Scaling Deep Video Understanding with a Large-Scale, Multi-Genre and Auto-Generated Dataset","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2607.10598","title":"Anomalous Frame Detection by Grouping Frame Similarities between Two Videos Computed by Vision-Language Model to Extract Expert Workers' Unique Actions","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2607.11957","title":"Anomalous Frame Detection Using VLM-Based Description Comparison for Extracting Expert-Specific Actions and Contextual Decision-Making Scenes with Intra-Video Self-Similarity","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2607.20057","title":"Antigen-specific Antibody Multi-modal Foundation Model for Functional Antibody Design","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2607.22632","title":"VlogReward: Learning Multi-Dimensional Evaluation for Vlog Editing","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2608.28675","title":"Multi-Agent Self-Improving Reinforcement Learning for Video Reasoning","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2608.30068","title":"TAKE 85: Testing Audiovisual filmmaKer's intEnt across 85 Hours of Film","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.02528","title":"Doppio: A Dataset for Contactless Weight Estimation of Falling Particles","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.10355","title":"Why Is Video Still So Expensive? A Survey of Inference-Efficiency Mechanisms in Video and Audiovisual LLMs","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.17112","title":"Not Another Text Benchmark: Putting the \"Visual\" Back in Visual Question Answering for Large Video Models","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.24031","title":"Video-STLayout Pre-training","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.31665","title":"Language-Augmented Video Action Anticipation: Design Fundamentals, Benchmarks, and Open Challenges","created":"2026-09-15","cited_by_count":0,"area":null}],"next_cursor":null}