{"total":105,"rows":[{"id":"2506.09985","title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","created":"2025-06-11","cited_by_count":809,"area":"wm"},{"id":"2504.13181","title":"Perception Encoder: The best visual embeddings are not at the output of the network","created":"2025-04-17","cited_by_count":326,"area":null},{"id":"2405.17247","title":"An Introduction to Vision-Language Modeling","created":"2024-05-27","cited_by_count":178,"area":"mllm"},{"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":"2603.14482","title":"V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning","created":"2026-03-15","cited_by_count":117,"area":null},{"id":"2410.05643","title":"TRACE: Temporal Grounding Video LLM via Causal Event Modeling","created":"2024-10-08","cited_by_count":89,"area":null},{"id":"2412.10471","title":"VCA: Video Curious Agent for Long Video Understanding","created":"2024-12-12","cited_by_count":56,"area":"agents"},{"id":"2412.11959","title":"Gramian Multimodal Representation Learning and Alignment","created":"2024-12-16","cited_by_count":54,"area":null},{"id":"2405.03770","title":"Foundation Models for Video Understanding: A Survey","created":"2024-05-06","cited_by_count":46,"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":"2503.10677","title":"A Survey on Knowledge-Oriented Retrieval-Augmented Generation","created":"2025-03-11","cited_by_count":36,"area":"rag"},{"id":"2412.15212","title":"Scaling 4D Representations","created":"2024-12-19","cited_by_count":30,"area":null},{"id":"2509.14476","title":"AToken: A Unified Tokenizer for Vision","created":"2025-09-17","cited_by_count":30,"area":null},{"id":"2412.19326","title":"Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment","created":"2024-12-26","cited_by_count":29,"area":"mllm"},{"id":"2407.16658","title":"EgoCVR: An Egocentric Benchmark for Fine-Grained Composed Video Retrieval","created":"2024-07-23","cited_by_count":21,"area":null},{"id":"2507.17343","title":"Principled Multimodal Representation Learning","created":"2025-07-23","cited_by_count":19,"area":null},{"id":"2509.24734","title":"A TRIANGLE Enables Multimodal Alignment Beyond Cosine Similarity","created":"2025-09-29","cited_by_count":18,"area":null},{"id":"2404.09275","title":"TrafficVLM: A Controllable Visual Language Model for Traffic Video Captioning","created":"2024-04-14","cited_by_count":17,"area":"mllm"},{"id":"2502.07001","title":"From Image to Video: An Empirical Study of Diffusion Representations","created":"2025-02-10","cited_by_count":15,"area":"diffusion"},{"id":"2512.19687","title":"Pushing the Frontier of Audiovisual Perception with Large-Scale Multimodal Correspondence Learning","created":"2025-12-22","cited_by_count":13,"area":null},{"id":"2407.06491","title":"VideoEval: Comprehensive Benchmark Suite for Low-Cost Evaluation of Video Foundation Model","created":"2024-07-09","cited_by_count":12,"area":null},{"id":"2509.24317","title":"Rethinking JEPA: Compute-Efficient Video SSL with Frozen Teachers","created":"2025-09-29","cited_by_count":12,"area":null},{"id":"2504.03970","title":"VideoComp: Advancing Fine-Grained Compositional and Temporal Alignment in Video-Text Models","created":"2025-04-04","cited_by_count":11,"area":"mllm"},{"id":"2510.06040","title":"VideoMiner: Iteratively Grounding Key Frames of Hour-Long Videos via Tree-based Group Relative Policy Optimization","created":"2025-10-07","cited_by_count":11,"area":"lr"},{"id":"2405.13911","title":"TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment","created":"2024-05-22","cited_by_count":10,"area":null},{"id":"2501.01426","title":"Unifying Specialized Visual Encoders for Video Language Models","created":"2025-01-02","cited_by_count":10,"area":"lr"},{"id":"2504.20041","title":"Learning Streaming Video Representation via Multitask Training","created":"2025-04-28","cited_by_count":10,"area":null},{"id":"2508.11576","title":"Causality Matters: How Temporal Information Emerges in Video Language Models","created":"2025-08-15","cited_by_count":10,"area":null},{"id":"2504.00527","title":"SMILE: Infusing Spatial and Motion Semantics in Masked Video Learning","created":"2025-04-01","cited_by_count":9,"area":null},{"id":"2504.07519","title":"VideoExpert: Augmented LLM for Temporal-Sensitive Video Understanding","created":"2025-04-10","cited_by_count":9,"area":null},{"id":"2506.07603","title":"SurgBench: A Unified Large-Scale Benchmark for Surgical Video Analysis","created":"2025-06-09","cited_by_count":9,"area":null},{"id":"2511.18833","title":"PrismAudio: Decomposed Chain-of-Thoughts and Multi-dimensional Rewards for Video-to-Audio Generation","created":"2025-11-24","cited_by_count":9,"area":"lr"},{"id":"2502.16427","title":"Fine-Grained Captioning of Long Videos through Scene Graph Consolidation","created":"2025-02-23","cited_by_count":8,"area":"mllm"},{"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":"2510.03584","title":"FrameOracle: Learning What to See and How Much to See in Videos","created":"2025-10-04","cited_by_count":7,"area":"mllm"},{"id":"2512.01342","title":"InternVideo-Next: Towards General Video Foundation Models without Video-Text Supervision","created":"2025-12-01","cited_by_count":7,"area":"wm"},{"id":"2406.10079","title":"Localizing Events in Videos with Multimodal Queries","created":"2024-06-14","cited_by_count":6,"area":null},{"id":"2409.16145","title":"Learning to Localize Actions in Instructional Videos with LLM-Based Multi-Pathway Text-Video Alignment","created":"2024-09-22","cited_by_count":6,"area":null},{"id":"2507.03578","title":"SciVid: Cross-Domain Evaluation of Video Models in Scientific Applications","created":"2025-07-04","cited_by_count":6,"area":null},{"id":"2410.17136","title":"AlphaChimp: Tracking and Behavior Recognition of Chimpanzees","created":"2024-10-22","cited_by_count":5,"area":null},{"id":"2412.14294","title":"TRecViT: A Recurrent Video Transformer","created":"2024-12-18","cited_by_count":5,"area":null},{"id":"2507.09513","title":"Animal behavioral analysis and neural encoding with transformer-based self-supervised pretraining","created":"2025-07-13","cited_by_count":5,"area":null},{"id":"2511.02767","title":"Dynamic Reflections: Probing Video Representations with Text Alignment","created":"2025-11-04","cited_by_count":5,"area":null},{"id":"2410.12018","title":"LocoMotion: Learning Motion-Focused Video-Language Representations","created":"2024-10-15","cited_by_count":4,"area":null},{"id":"2504.05706","title":"SEVERE++: Evaluating Benchmark Sensitivity in Generalization of Video Representation Learning","created":"2025-04-08","cited_by_count":4,"area":null},{"id":"2507.13942","title":"Frozen Forecasting: A Unified Evaluation","created":"2025-07-18","cited_by_count":4,"area":null},{"id":"2507.23284","title":"Bidirectional Likelihood Estimation with Multi-Modal Large Language Models for Text-Video Retrieval","created":"2025-07-31","cited_by_count":4,"area":"mllm"},{"id":"2601.16210","title":"PyraTok: Language-Aligned Pyramidal Tokenizer for Video Understanding and Generation","created":"2026-01-22","cited_by_count":4,"area":null},{"id":"2602.08099","title":"VidVec: Unlocking Video MLLM Embeddings for Video-Text Retrieval","created":"2026-02-08","cited_by_count":4,"area":"mllm"},{"id":"2602.09507","title":"Towards Uniformity and Alignment for Multimodal Representation Learning","created":"2026-02-10","cited_by_count":4,"area":null},{"id":"2410.12158","title":"SAM-Guided Masked Token Prediction for 3D Scene Understanding","created":"2024-10-16","cited_by_count":3,"area":"distill"},{"id":"2411.13683","title":"Extending Video Masked Autoencoders to 128 frames","created":"2024-11-20","cited_by_count":3,"area":null},{"id":"2504.01792","title":"UniViTAR: Unified Vision Transformer with Native Resolution","created":"2025-04-02","cited_by_count":3,"area":null},{"id":"2508.07312","title":"MobileViCLIP: An Efficient Video-Text Model for Mobile Devices","created":"2025-08-10","cited_by_count":3,"area":null},{"id":"2511.12034","title":"Calibrated Multimodal Representation Learning with Missing Modalities","created":"2025-11-15","cited_by_count":3,"area":null},{"id":"2601.07833","title":"Tuning-free Visual Effect Transfer across Videos","created":"2026-01-12","cited_by_count":3,"area":null},{"id":"2602.04202","title":"VTok: A Unified Video Tokenizer with Decoupled Spatial-Temporal Latents","created":"2026-02-04","cited_by_count":3,"area":null},{"id":"2602.09146","title":"SemanticMoments: Training-Free Motion Similarity via Third Moment Features","created":"2026-02-09","cited_by_count":3,"area":null},{"id":"2603.24539","title":"CliPPER: Contextual Video-Language Pretraining on Long-form Intraoperative Surgical Procedures for Event Recognition","created":"2026-03-25","cited_by_count":3,"area":null},{"id":"2503.18637","title":"Unbiasing through Textual Descriptions: Mitigating Representation Bias in Video Benchmarks","created":"2025-03-24","cited_by_count":2,"area":null},{"id":"2506.01119","title":"MOOSE: Pay Attention to Temporal Dynamics for Video Understanding via Optical Flows","created":"2025-06-01","cited_by_count":2,"area":null},{"id":"2507.02909","title":"Fine-grained Token Allocation Via Operation Pruning for Efficient MLLMs","created":"2025-06-24","cited_by_count":2,"area":"mllm"},{"id":"2507.09068","title":"Infinite Video Understanding","created":"2025-07-11","cited_by_count":2,"area":null},{"id":"2511.09675","title":"PriVi: Towards A General-Purpose Video Model For Primate Behavior In The Wild","created":"2025-11-12","cited_by_count":2,"area":null},{"id":"2603.08648","title":"CAST: Modeling Visual State Transitions for Consistent Video Retrieval","created":"2026-03-09","cited_by_count":2,"area":null},{"id":"2408.11318","title":"TWLV-I: Analysis and Insights from Holistic Evaluation on Video Foundation Models","created":"2024-08-21","cited_by_count":1,"area":null},{"id":"2412.07704","title":"GEXIA: Granularity Expansion and Iterative Approximation for Scalable Multi-grained Video-language Learning","created":"2024-12-10","cited_by_count":1,"area":null},{"id":"2505.16025","title":"Context and Pixel Aware Large Language Model for Video Quality Assessment","created":"2025-05-21","cited_by_count":1,"area":"mllm"},{"id":"2510.06509","title":"From Captions to Keyframes: KeyScore for Multimodal Frame Scoring and Video-Language Understanding","created":"2025-10-07","cited_by_count":1,"area":null},{"id":"2510.21798","title":"An Evaluation of Hybrid Annotation Workflows on High-Ambiguity Spatiotemporal Video Footage","created":"2025-10-20","cited_by_count":1,"area":null},{"id":"2512.14102","title":"Neurosymbolic Inference On Foundation Models For Remote Sensing Text-to-image Retrieval With Complex Queries","created":"2025-12-16","cited_by_count":1,"area":"mllm"},{"id":"2512.21004","title":"Learning from Next-Frame Prediction: Autoregressive Video Modeling Encodes Effective Representations","created":"2025-12-24","cited_by_count":1,"area":"diffusion"},{"id":"2602.15287","title":"Consistency-Preserving Diverse Video Generation","created":"2026-02-17","cited_by_count":1,"area":"diffusion"},{"id":"2602.19874","title":"BigMaQ: A Big Macaque Motion and Animation Dataset Bridging Image and 3D Pose Representations","created":"2026-02-23","cited_by_count":1,"area":null},{"id":"2603.26929","title":"Live Interactive Training for Video Segmentation","created":"2026-03-27","cited_by_count":1,"area":null},{"id":"2606.03490","title":"TrAction: Action Recognition with Sparse Trajectories","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.09641","title":"MAVIS: Multi-Agent Video Retrieval via Structured Video Understanding","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2607.06856","title":"Gen4U: Unifying Video Generation and Understanding via Diffusion","created":"2026-07-07","cited_by_count":1,"area":"diffusion"},{"id":"2607.09876","title":"Prompting-MammAlps: Fine-Grained Text-to-Video Retrieval for Camera-Trap Data","created":"2026-07-10","cited_by_count":1,"area":null},{"id":"2609.33800","title":"Binding Multiple Modalities via Multimodal Wasserstein Barycenter","created":"2026-09-27","cited_by_count":1,"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":"2511.20162","title":"Action Without Interaction: Probing the Physical Foundations of Video LMMs via Contact-Release Detection","created":"2025-11-25","cited_by_count":0,"area":"mllm"},{"id":"2602.13507","title":"Benchmarking Video Foundation Models for Remote Parkinson's Disease Screening","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2602.16545","title":"Let's Split Up: Zero-Shot Classifier Edits for Fine-Grained Video Understanding","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2604.03302","title":"Beyond Static Vision: Scene Dynamic Field Unlocks Intuitive Physics Understanding in Multi-modal Large Language Models","created":"2026-03-30","cited_by_count":0,"area":"mllm"},{"id":"2604.08337","title":"InstAP: Instance-Aware Vision-Language Pre-Train for Spatial-Temporal Understanding","created":"2026-04-09","cited_by_count":0,"area":"mllm"},{"id":"2604.08762","title":"InstrAct: Towards Action-Centric Understanding in Instructional Videos","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2605.27304","title":"PlayClass: Automated Play Behaviour Classification in Poultry","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2606.03635","title":"VidMsg: A Benchmark for Implicit Message Inference in Short Videos","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.04280","title":"The Loss Is Not Enough: Sampling Conditions and Inductive Bias in Contrastive Representation Learning","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.04433","title":"Stateful Visual Encoders for Vision-Language Models","created":"2026-06-03","cited_by_count":0,"area":"mllm"},{"id":"2607.04518","title":"A non-invasive video-based method for individual identification of wildlife using gait dynamics","created":"2026-07-05","cited_by_count":0,"area":null},{"id":"2607.07438","title":"Two-Stage Multi-Modal Fusion with Adaptive Alignment for Action Quality Assessment","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2607.17625","title":"Brain-Aligned Multi-Stream Video Transformers with Sparse Self-Selection","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2608.13283","title":"Towards Context-Aware Clinical Motion Understanding in Daily Living at Home: Freezing of Gait Detection with Egocentric Vision","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.21281","title":"WildFin: An In-the-Wild Dataset for Fish Behavioral Recognition","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.00505","title":"ViTAL-X: Video-Text Alignment with Cross-Modal Temporal Edits","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.13024","title":"Label-Guided Knowledge Distillation for 3D-CNNs in Action Recognition","created":"2026-09-11","cited_by_count":0,"area":"distill"},{"id":"2609.15320","title":"Hypergraph-Regularized Gramian Volumes for Multimodal Retrieval","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.15335","title":"Query-Conditioned Spherical Centroid Aggregation for Multimodal Retrieval","created":"2026-09-14","cited_by_count":0,"area":null}],"next_cursor":"100"}