{"total":133,"rows":[{"id":"2410.02713","title":"LLaVA-Video: Video Instruction Tuning With Synthetic Data","created":"2024-10-03","cited_by_count":583,"area":"mllm"},{"id":"2307.06942","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","created":"2023-07-13","cited_by_count":497,"area":null},{"id":"2403.06977","title":"VideoMamba: State Space Model for Efficient Video Understanding","created":"2024-03-11","cited_by_count":328,"area":"ssm"},{"id":"2404.05726","title":"MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding","created":"2024-04-08","cited_by_count":229,"area":"mllm"},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"area":null},{"id":"2305.06988","title":"Self-Chained Image-Language Model for Video Localization and Question Answering","created":"2023-05-11","cited_by_count":203,"area":null},{"id":"2303.16058","title":"Unmasked Teacher: Towards Training-Efficient Video Foundation Models","created":"2023-03-28","cited_by_count":199,"area":null},{"id":"2305.18500","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","created":"2023-05-29","cited_by_count":169,"area":null},{"id":"2302.00402","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","created":"2023-02-01","cited_by_count":154,"area":null},{"id":"2407.00634","title":"Tarsier: Recipes for Training and Evaluating Large Video Description Models","created":"2024-06-30","cited_by_count":141,"area":null},{"id":"2304.08345","title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","created":"2023-04-17","cited_by_count":140,"area":null},{"id":"2309.01327","title":"Can I Trust Your Answer? Visually Grounded Video Question Answering","created":"2023-09-04","cited_by_count":135,"area":null},{"id":"2210.09263","title":"Vision-Language Pre-training: Basics, Recent Advances, and Future Trends","created":"2022-10-17","cited_by_count":117,"area":"mllm"},{"id":"2402.13217","title":"VideoPrism: A Foundational Visual Encoder for Video Understanding","created":"2024-02-20","cited_by_count":105,"area":null},{"id":"2410.10818","title":"TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models","created":"2024-10-14","cited_by_count":97,"area":null},{"id":"2406.16338","title":"VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Models","created":"2024-06-24","cited_by_count":90,"area":"mllm"},{"id":"2212.05051","title":"VindLU: A Recipe for Effective Video-and-Language Pretraining","created":"2022-12-09","cited_by_count":87,"area":null},{"id":"2312.06720","title":"Audio-Visual LLM for Video Understanding","created":"2023-12-11","cited_by_count":77,"area":"mllm"},{"id":"2304.06708","title":"Verbs in Action: Improving verb understanding in video-language models","created":"2023-04-13","cited_by_count":76,"area":null},{"id":"2404.06511","title":"MoReVQA: Exploring Modular Reasoning Models for Video Question Answering","created":"2024-04-09","cited_by_count":74,"area":"lr"},{"id":"2206.07160","title":"LAVENDER: Unifying Video-Language Understanding as Masked Language Modeling","created":"2022-06-14","cited_by_count":73,"area":null},{"id":"2410.23266","title":"TOMATO: Assessing Visual Temporal Reasoning Capabilities in Multimodal Foundation Models","created":"2024-10-30","cited_by_count":73,"area":"lr"},{"id":"2212.14546","title":"HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training","created":"2022-12-30","cited_by_count":72,"area":null},{"id":"2212.04979","title":"VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners","created":"2022-12-09","cited_by_count":70,"area":null},{"id":"2301.02311","title":"HierVL: Learning Hierarchical Video-Language Embeddings","created":"2023-01-05","cited_by_count":66,"area":null},{"id":"2311.17404","title":"VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models","created":"2023-11-29","cited_by_count":55,"area":null},{"id":"2301.02074","title":"Test of Time: Instilling Video-Language Models with a Sense of Time","created":"2023-01-05","cited_by_count":51,"area":null},{"id":"2309.10091","title":"Unified Coarse-to-Fine Alignment for Video-Text Retrieval","created":"2023-09-18","cited_by_count":49,"area":null},{"id":"2305.10683","title":"Paxion: Patching Action Knowledge in Video-Language Foundation Models","created":"2023-05-18","cited_by_count":42,"area":null},{"id":"2309.15785","title":"BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning","created":"2023-09-27","cited_by_count":41,"area":null},{"id":"2403.13347","title":"vid-TLDR: Training Free Token merging for Light-weight Video Transformer","created":"2024-03-20","cited_by_count":41,"area":null},{"id":"2311.14906","title":"AutoEval-Video: An Automatic Benchmark for Assessing Large Vision Language Models in Open-Ended Video Question Answering","created":"2023-11-25","cited_by_count":40,"area":"mllm"},{"id":"2410.02763","title":"Vinoground: Scrutinizing LMMs over Dense Temporal Reasoning with Short Videos","created":"2024-10-03","cited_by_count":38,"area":"lr"},{"id":"2312.07395","title":"A Simple Recipe for Contrastively Pre-training Video-First Encoders Beyond 16 Frames","created":"2023-12-12","cited_by_count":34,"area":null},{"id":"2512.01989","title":"PAI-Bench: A Comprehensive Benchmark For Physical AI","created":"2025-12-01","cited_by_count":34,"area":"mllm"},{"id":"2507.06485","title":"Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoning","created":"2025-07-09","cited_by_count":33,"area":"lr"},{"id":"2311.10111","title":"VideoCon: Robust Video-Language Alignment via Contrast Captions","created":"2023-11-15","cited_by_count":30,"area":null},{"id":"2506.03340","title":"Seeing the Arrow of Time in Large Multimodal Models","created":"2025-06-03","cited_by_count":30,"area":"mllm"},{"id":"2506.09987","title":"A Shortcut-aware Video-QA Benchmark for Physical Understanding via Minimal Video Pairs","created":"2025-06-11","cited_by_count":30,"area":"lr"},{"id":"2408.04223","title":"VideoQA in the Era of LLMs: An Empirical Study","created":"2024-08-08","cited_by_count":29,"area":null},{"id":"2210.11522","title":"Composing Ensembles of Pre-trained Models via Iterative Consensus","created":"2022-10-20","cited_by_count":28,"area":null},{"id":"2311.07022","title":"ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models","created":"2023-11-13","cited_by_count":26,"area":null},{"id":"2207.11100","title":"Zero-Shot Video Captioning with Evolving Pseudo-Tokens","created":"2022-07-22","cited_by_count":25,"area":null},{"id":"2410.10816","title":"LVD-2M: A Long-take Video Dataset with Temporally Dense Captions","created":"2024-10-14","cited_by_count":25,"area":null},{"id":"2503.14935","title":"FAVOR-Bench: A Comprehensive Benchmark for Fine-Grained Video Motion Understanding","created":"2025-03-19","cited_by_count":24,"area":"mllm"},{"id":"2307.03948","title":"Reading Between the Lanes: Text VideoQA on the Road","created":"2023-07-08","cited_by_count":23,"area":null},{"id":"2310.05010","title":"Building an Open-Vocabulary Video CLIP Model with Better Architectures, Optimization and Data","created":"2023-10-08","cited_by_count":22,"area":null},{"id":"2211.05588","title":"Watching the News: Towards VideoQA Models that can Read","created":"2022-11-10","cited_by_count":20,"area":"lr"},{"id":"2311.12919","title":"SPOT! Revisiting Video-Language Models for Event Understanding","created":"2023-11-21","cited_by_count":20,"area":null},{"id":"2409.01071","title":"VideoLLaMB: Long Streaming Video Understanding with Recurrent Memory Bridges","created":"2024-09-02","cited_by_count":20,"area":null},{"id":"2411.09921","title":"Motion-Grounded Video Reasoning: Understanding and Perceiving Motion at Pixel Level","created":"2024-11-15","cited_by_count":19,"area":"lr"},{"id":"2411.16771","title":"VidHal: Benchmarking Temporal Hallucinations in Vision LLMs","created":"2024-11-25","cited_by_count":19,"area":null},{"id":"2406.18113","title":"Chrono: A Simple Blueprint for Representing Time in MLLMs","created":"2024-06-26","cited_by_count":18,"area":"mllm"},{"id":"2305.13167","title":"VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending","created":"2023-05-22","cited_by_count":17,"area":null},{"id":"2503.08585","title":"HierarQ: Task-Aware Hierarchical Q-Former for Enhanced Video Understanding","created":"2025-03-11","cited_by_count":17,"area":"mllm"},{"id":"2407.01872","title":"Referring Atomic Video Action Recognition","created":"2024-07-02","cited_by_count":16,"area":null},{"id":"2211.11446","title":"SMAUG: Sparse Masked Autoencoder for Efficient Video-Language Pre-training","created":"2022-11-21","cited_by_count":15,"area":null},{"id":"2308.11551","title":"Multi-event Video-Text Retrieval","created":"2023-08-22","cited_by_count":15,"area":null},{"id":"2311.05698","title":"Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities","created":"2023-11-09","cited_by_count":15,"area":null},{"id":"2307.03166","title":"VideoGLUE: Video General Understanding Evaluation of Foundation Models","created":"2023-07-06","cited_by_count":14,"area":null},{"id":"2301.11507","title":"Semi-Parametric Video-Grounded Text Generation","created":"2023-01-27","cited_by_count":13,"area":null},{"id":"2412.19178","title":"Reversed in Time: A Novel Temporal-Emphasized Benchmark for Cross-Modal Video-Text Retrieval","created":"2024-12-26","cited_by_count":13,"area":null},{"id":"2406.10221","title":"Long Story Short: Story-level Video Understanding from 20K Short Films","created":"2024-06-14","cited_by_count":12,"area":"mllm"},{"id":"2304.08809","title":"SViTT: Temporal Learning of Sparse Video-Text Transformers","created":"2023-04-18","cited_by_count":11,"area":null},{"id":"2306.09085","title":"COSA: Concatenated Sample Pretrained Vision-Language Foundation Model","created":"2023-06-15","cited_by_count":11,"area":"mllm"},{"id":"2405.17719","title":"Do Egocentric Video-Language Models Truly Understand Hand-Object Interactions?","created":"2024-05-28","cited_by_count":11,"area":null},{"id":"2412.02071","title":"Progress-Aware Video Frame Captioning","created":"2024-12-03","cited_by_count":11,"area":null},{"id":"2509.08502","title":"Chirality in Action: Time-Aware Video Representation Learning by Latent Straightening","created":"2025-09-10","cited_by_count":11,"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":"2310.16754","title":"CAD -- Contextual Multi-modal Alignment for Dynamic AVQA","created":"2023-10-25","cited_by_count":10,"area":null},{"id":"2407.14872","title":"Adapt2Reward: Adapting Video-Language Models to Generalizable Robotic Rewards via Failure Prompts","created":"2024-07-20","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":"2306.08889","title":"Dissecting Multimodality in VideoQA Transformer Models by Impairing Modality Fusion","created":"2023-06-15","cited_by_count":8,"area":null},{"id":"2407.03788","title":"MAMA: Meta-optimized Angular Margin Contrastive Framework for Video-Language Representation Learning","created":"2024-07-04","cited_by_count":8,"area":null},{"id":"2407.07478","title":"EA-VTR: Event-Aware Video-Text Retrieval","created":"2024-07-10","cited_by_count":8,"area":null},{"id":"2301.01953","title":"Learning Trajectory-Word Alignments for Video-Language Tasks","created":"2023-01-05","cited_by_count":7,"area":null},{"id":"2401.01823","title":"Detours for Navigating Instructional Videos","created":"2024-01-03","cited_by_count":7,"area":null},{"id":"2505.23617","title":"One Trajectory, One Token: Grounded Video Tokenization via Panoptic Sub-object Trajectory","created":"2025-05-29","cited_by_count":7,"area":null},{"id":"2209.15280","title":"Learning Transferable Spatiotemporal Representations from Natural Script Knowledge","created":"2022-09-30","cited_by_count":6,"area":null},{"id":"2309.08022","title":"Empowering Visually Impaired Individuals: A Novel Use of Apple Live Photos and Android Motion Photos","created":"2023-09-14","cited_by_count":6,"area":null},{"id":"2503.14237","title":"Make Your Training Flexible: Towards Deployment-Efficient Video Models","created":"2025-03-18","cited_by_count":6,"area":null},{"id":"2609.15478","title":"BVB: Benchmarking Agentic Video Understanding via Programmatic Reconstruction in Blender","created":"2026-09-14","cited_by_count":6,"area":"diffusion"},{"id":"2312.00414","title":"Vision-Language Models Learn Super Images for Efficient Partially Relevant Video Retrieval","created":"2023-12-01","cited_by_count":5,"area":"mllm"},{"id":"2401.17797","title":"M2-RAAP: A Multi-Modal Recipe for Advancing Adaptation-based Pre-training towards Effective and Efficient Zero-shot Video-text Retrieval","created":"2024-01-31","cited_by_count":5,"area":null},{"id":"2403.14870","title":"VidLA: Video-Language Alignment at Scale","created":"2024-03-21","cited_by_count":5,"area":null},{"id":"2412.12833","title":"FocusChat: Text-guided Long Video Understanding via Spatiotemporal Information Filtering","created":"2024-12-17","cited_by_count":5,"area":"mllm"},{"id":"2508.00367","title":"Representation Shift: Unifying Token Compression with FlashAttention","created":"2025-08-01","cited_by_count":5,"area":"inference"},{"id":"2305.10512","title":"IMAD: IMage-Augmented multi-modal Dialogue","created":"2023-05-17","cited_by_count":4,"area":null},{"id":"2401.07669","title":"SRL-CLIP: Efficient CLIP Video Adaptation via Structured Semantic Role Labels","created":"2024-01-15","cited_by_count":4,"area":null},{"id":"2410.12018","title":"LocoMotion: Learning Motion-Focused Video-Language Representations","created":"2024-10-15","cited_by_count":4,"area":null},{"id":"2506.18071","title":"MUPA: Towards Multi-Path Agentic Reasoning for Grounded Video Question Answering","created":"2025-06-22","cited_by_count":4,"area":"agents"},{"id":"2509.19245","title":"ConViS-Bench: Estimating Video Similarity Through Semantic Concepts","created":"2025-09-23","cited_by_count":4,"area":null},{"id":"2512.02846","title":"Action Anticipation at a Glimpse: To What Extent Can Multimodal Cues Replace Video?","created":"2025-12-02","cited_by_count":4,"area":null},{"id":"2208.11553","title":"MuMUR : Multilingual Multimodal Universal Retrieval","created":"2022-08-24","cited_by_count":3,"area":"mllm"},{"id":"2304.02080","title":"Scalable and Accurate Self-supervised Multimodal Representation Learning without Aligned Video and Text Data","created":"2023-04-04","cited_by_count":3,"area":null},{"id":"2309.02290","title":"ATM: Action Temporality Modeling for Video Question Answering","created":"2023-09-05","cited_by_count":3,"area":"lr"},{"id":"2603.05663","title":"Keeping the Evidence Chain: Semantic Evidence Allocation for Training-Free Token Pruning in Video Temporal Grounding","created":"2026-03-05","cited_by_count":3,"area":"inference"},{"id":"2603.08436","title":"Can Vision-Language Models Solve the Shell Game?","created":"2026-03-09","cited_by_count":3,"area":"mllm"},{"id":"2210.03941","title":"Learning Fine-Grained Visual Understanding for Video Question Answering via Decoupling Spatial-Temporal Modeling","created":"2022-10-08","cited_by_count":2,"area":null},{"id":"2309.01380","title":"Understanding Video Scenes through Text: Insights from Text-based Video Question Answering","created":"2023-09-04","cited_by_count":2,"area":null}],"next_cursor":"100"}