{"total":184,"rows":[{"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":"2511.00062","title":"World Simulation with Video Foundation Models for Physical AI","created":"2025-10-28","cited_by_count":200,"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":"2503.08153","title":"WISA: World Simulator Assistant for Physics-Aware Text-to-Video Generation","created":"2025-03-11","cited_by_count":90,"area":null},{"id":"2504.15376","title":"Towards Understanding Camera Motions in Any Video","created":"2025-04-21","cited_by_count":64,"area":null},{"id":"2503.04812","title":"LLaVE: Large Language and Vision Embedding Models with Hardness-Weighted Contrastive Learning","created":"2025-03-04","cited_by_count":55,"area":null},{"id":"2405.03770","title":"Foundation Models for Video Understanding: A Survey","created":"2024-05-06","cited_by_count":46,"area":null},{"id":"2505.19650","title":"Modality Curation: Building Universal Embeddings for Advanced Multimodal Information Retrieval","created":"2025-05-26","cited_by_count":26,"area":null},{"id":"2412.11694","title":"From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities","created":"2024-12-16","cited_by_count":22,"area":null},{"id":"2503.19009","title":"Video-ColBERT: Contextualized Late Interaction for Text-to-Video Retrieval","created":"2025-03-24","cited_by_count":20,"area":null},{"id":"2501.00513","title":"CaReBench: A Fine-Grained Benchmark for Video Captioning and Retrieval","created":"2024-12-31","cited_by_count":19,"area":null},{"id":"2502.12558","title":"MomentSeeker: A Task-Oriented Benchmark For Long-Video Moment Retrieval","created":"2025-02-18","cited_by_count":14,"area":null},{"id":"2503.17069","title":"PVChat: Personalized Video Chat with One-Shot Learning","created":"2025-03-21","cited_by_count":13,"area":null},{"id":"2503.20776","title":"Feature4X: Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fields","created":"2025-03-26","cited_by_count":13,"area":null},{"id":"2507.19599","title":"Object-centric Video Question Answering with Visual Grounding and Referring","created":"2025-07-25","cited_by_count":13,"area":null},{"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":"2405.13824","title":"GMMFormer v2: An Uncertainty-aware Framework for Partially Relevant Video Retrieval","created":"2024-05-22","cited_by_count":12,"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":"2602.08683","title":"OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence","created":"2026-02-09","cited_by_count":12,"area":null},{"id":"2605.18678","title":"Lance: Unified Multimodal Modeling by Multi-Task Synergy","created":"2026-05-18","cited_by_count":12,"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":"2407.11784","title":"Data-Juicer Sandbox: A Feedback-Driven Suite for Multimodal Data-Model Co-development","created":"2024-07-16","cited_by_count":10,"area":null},{"id":"2504.20041","title":"Learning Streaming Video Representation via Multitask Training","created":"2025-04-28","cited_by_count":10,"area":null},{"id":"2507.14902","title":"U-MARVEL: Unveiling Key Factors for Universal Multimodal Retrieval via Embedding Learning with MLLMs","created":"2025-07-20","cited_by_count":10,"area":null},{"id":"2604.14816","title":"NTIRE 2026 Challenge on Video Saliency Prediction: Methods and Results","created":"2026-04-16","cited_by_count":10,"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":"2506.07886","title":"EgoM2P: Egocentric Multimodal Multitask Pretraining","created":"2025-06-09","cited_by_count":9,"area":null},{"id":"2510.02778","title":"AdaRD-key: Adaptive Relevance-Diversity Keyframe Sampling for Long-form Video understanding","created":"2025-10-03","cited_by_count":9,"area":null},{"id":"2510.27571","title":"Towards Universal Video Retrieval: Generalizing Video Embedding via Synthesized Multimodal Pyramid Curriculum","created":"2025-10-31","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":"2506.21742","title":"VRR-QA: Visual Relational Reasoning in Videos Beyond Explicit Cues","created":"2025-06-26","cited_by_count":8,"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":"2505.24329","title":"DisTime: Distribution-based Time Representation for Video Large Language Models","created":"2025-05-30","cited_by_count":7,"area":null},{"id":"2506.03990","title":"DynTok: Dynamic Compression of Visual Tokens for Efficient and Effective Video Understanding","created":"2025-06-04","cited_by_count":7,"area":null},{"id":"2507.18531","title":"IntentVCNet: Bridging Spatio-Temporal Gaps for Intention-Oriented Controllable Video Captioning","created":"2025-07-24","cited_by_count":7,"area":null},{"id":"2406.10079","title":"Localizing Events in Videos with Multimodal Queries","created":"2024-06-14","cited_by_count":6,"area":null},{"id":"2503.09321","title":"DAVE: Diagnostic benchmark for Audio Visual Evaluation","created":"2025-03-12","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":"2511.16077","title":"VideoSeg-R1:Reasoning Video Object Segmentation via Reinforcement Learning","created":"2025-11-20","cited_by_count":6,"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":"2512.04483","title":"DeRA: Decoupled Representation Alignment for Video Tokenization","created":"2025-12-04","cited_by_count":6,"area":null},{"id":"2512.14017","title":"KFS-Bench: Comprehensive Evaluation of Key Frame Sampling in Long Video Understanding","created":"2025-12-16","cited_by_count":6,"area":null},{"id":"2507.02316","title":"Are Synthetic Videos Useful? A Benchmark for Retrieval-Centric Evaluation of Synthetic Videos","created":"2025-07-03","cited_by_count":5,"area":null},{"id":"2512.04532","title":"PhyVLLM: Physics-Guided Video Language Model with Motion-Appearance Disentanglement","created":"2025-12-04","cited_by_count":5,"area":null},{"id":"2601.00943","title":"PhyEduVideo: A Benchmark for Evaluating Text-to-Video Models for Physics Education","created":"2026-01-02","cited_by_count":5,"area":null},{"id":"2603.09827","title":"MA-EgoQA: Question Answering over Egocentric Videos from Multiple Embodied Agents","created":"2026-03-10","cited_by_count":5,"area":null},{"id":"2505.23155","title":"PreFM: Online Audio-Visual Event Parsing via Predictive Future Modeling","created":"2025-05-29","cited_by_count":4,"area":null},{"id":"2507.22522","title":"Recognizing Actions from Robotic View for Natural Human-Robot Interaction","created":"2025-07-30","cited_by_count":4,"area":null},{"id":"2510.20244","title":"Empower Words: DualGround for Structured Phrase and Sentence-Level Temporal Grounding","created":"2025-10-23","cited_by_count":4,"area":null},{"id":"2511.21681","title":"Seeing without Pixels: Perception from Camera Trajectories","created":"2025-11-26","cited_by_count":4,"area":null},{"id":"2601.00260","title":"TotalFM: An Organ-Separated 3D-CT Foundation Model Leveraging Large-Scale Routine Clinical Radiology Data","created":"2026-01-01","cited_by_count":4,"area":null},{"id":"2602.09507","title":"Towards Uniformity and Alignment for Multimodal Representation Learning","created":"2026-02-10","cited_by_count":4,"area":null},{"id":"2607.13298","title":"FOLIO: Focused Semantic Memory for Streaming Video Understanding","created":"2026-07-14","cited_by_count":4,"area":null},{"id":"2410.23946","title":"MV-CC: Mask Enhanced Video Model for Remote Sensing Change Caption","created":"2024-10-31","cited_by_count":3,"area":null},{"id":"2412.09202","title":"Temporal Action Localization with Cross Layer Task Decoupling and Refinement","created":"2024-12-12","cited_by_count":3,"area":null},{"id":"2501.07305","title":"The Devil is in the Spurious Correlations: Boosting Moment Retrieval with Dynamic Learning","created":"2025-01-13","cited_by_count":3,"area":null},{"id":"2503.24298","title":"Order Matters: On Parameter-Efficient Image-to-Video Probing for Recognizing Nearly Symmetric Actions","created":"2025-03-31","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":"2506.14356","title":"EVA02-AT: Egocentric Video-Language Understanding with Spatial-Temporal Rotary Positional Embeddings and Symmetric Optimization","created":"2025-06-17","cited_by_count":3,"area":null},{"id":"2506.22056","title":"Universal Retrieval for Multimodal Trajectory Modeling","created":"2025-06-27","cited_by_count":3,"area":null},{"id":"2507.07262","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","created":"2025-07-09","cited_by_count":3,"area":null},{"id":"2507.09338","title":"Simplifying Traffic Anomaly Detection with Video Foundation Models","created":"2025-07-12","cited_by_count":3,"area":null},{"id":"2510.13016","title":"SVAG-Bench: A Large-Scale Benchmark for Multi-Instance Spatio-temporal Video Action Grounding","created":"2025-10-14","cited_by_count":3,"area":null},{"id":"2510.18346","title":"AV-Master: Dual-Path Comprehensive Perception Makes Better Audio-Visual Question Answering","created":"2025-10-21","cited_by_count":3,"area":null},{"id":"2510.21406","title":"MUVR: A Multi-Modal Untrimmed Video Retrieval Benchmark with Multi-Level Visual Correspondence","created":"2025-10-24","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":"2601.21193","title":"Generative Recall, Dense Reranking: Learning Multi-View Semantic IDs for Efficient Text-to-Video Retrieval","created":"2026-01-29","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":"2603.23186","title":"ViKey: Enhancing Temporal Understanding in Videos via Visual Prompting","created":"2026-03-24","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":"2605.17179","title":"iMiGUE-3K: A Large-Scale Benchmark for Micro-Gesture Analysis with Self-Supervised Learning","created":"2026-05-16","cited_by_count":3,"area":null},{"id":"2407.13750","title":"PO-GUISE+: Pose and object guided transformer token selection for efficient driver action recognition","created":"2024-07-18","cited_by_count":2,"area":null},{"id":"2408.06622","title":"ActPrompt: In-Domain Feature Adaptation via Action Cues for Video Temporal Grounding","created":"2024-08-13","cited_by_count":2,"area":null},{"id":"2409.09678","title":"A Comprehensive Methodological Survey of Human Activity Recognition Across Divers Data Modalities","created":"2024-09-15","cited_by_count":2,"area":null},{"id":"2507.07744","title":"Sparse-Dense Side-Tuner for efficient Video Temporal Grounding","created":"2025-07-10","cited_by_count":2,"area":null},{"id":"2508.04273","title":"Audio Does Matter: Importance-Aware Multi-Granularity Fusion for Video Moment Retrieval","created":"2025-08-06","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":"2512.00885","title":"HanDyVQA: A Video QA Benchmark for Fine-Grained Hand-Object Interaction Dynamics","created":"2025-11-30","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":"2601.22508","title":"CoVA: Text-Guided Composed Video Retrieval for Audio-Visual Content","created":"2026-01-30","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":"2603.22953","title":"Cluster-Wise Spatio-Temporal Masking for Efficient Video-Language Pretraining","created":"2026-03-24","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":"2604.08613","title":"ViSAGE @ NTIRE 2026 Challenge on Video Saliency Prediction","created":"2026-04-09","cited_by_count":2,"area":null},{"id":"2605.22823","title":"Which Way Did It Move? Diagnosing and Overcoming Directional Motion Blindness in Video-LLMs","created":"2026-05-21","cited_by_count":2,"area":null},{"id":"2412.18386","title":"Switch-a-View: View Selection Learned from Unlabeled In-the-wild Videos","created":"2024-12-24","cited_by_count":1,"area":null},{"id":"2503.13821","title":"Stitch-a-Demo: Video Demonstrations from Multistep Descriptions","created":"2025-03-18","cited_by_count":1,"area":null},{"id":"2504.01591","title":"Leveraging Modality Tags for Enhanced Cross-Modal Video Retrieval","created":"2025-04-02","cited_by_count":1,"area":null},{"id":"2504.10443","title":"Multimodal Long Video Modeling Based on Temporal Dynamic Context","created":"2025-04-14","cited_by_count":1,"area":null},{"id":"2504.19637","title":"Enhanced Partially Relevant Video Retrieval through Inter- and Intra-Sample Analysis with Coherence Prediction","created":"2025-04-28","cited_by_count":1,"area":null},{"id":"2505.16784","title":"Four Eyes Are Better Than Two: Harnessing the Collaborative Potential of Large Models via Differentiated Thinking and Complementary Ensembles","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2505.23952","title":"Leveraging Auxiliary Information in Text-to-Video Retrieval: A Review","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2506.15937","title":"Beyond Audio and Pose: A General-Purpose Framework for Video Synchronization","created":"2025-06-19","cited_by_count":1,"area":null},{"id":"2506.23196","title":"DEL: Dense Event Localization for Multi-modal Audio-Visual Understanding","created":"2025-06-29","cited_by_count":1,"area":null},{"id":"2508.11183","title":"Versatile Video Representation via Feed-Forward 2D Gaussian Splatting Tokenization","created":"2025-08-15","cited_by_count":1,"area":null},{"id":"2508.17932","title":"See What You Need: Query-Aware Visual Intelligence through Reasoning-Perception Loops","created":"2025-08-25","cited_by_count":1,"area":null},{"id":"2508.21451","title":"MM-SeR: Multimodal Self-Refinement for Lightweight Image Captioning","created":"2025-08-29","cited_by_count":1,"area":null},{"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":"2511.01617","title":"Vote-in-Context: Turning VLMs into Zero-Shot Rank Fusers","created":"2025-11-03","cited_by_count":1,"area":null}],"next_cursor":"100"}