{"total":128,"rows":[{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556,"area":null},{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513,"area":"lr"},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490,"area":null},{"id":"2310.01852","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","created":"2023-10-03","cited_by_count":370,"area":null},{"id":"2305.15021","title":"EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought","created":"2023-05-24","cited_by_count":279,"area":"lr"},{"id":"2104.11181","title":"H2O: Two Hands Manipulating Objects for First Person Interaction Recognition","created":"2021-04-22","cited_by_count":254,"area":null},{"id":"2206.01670","title":"Egocentric Video-Language Pretraining","created":"2022-06-03","cited_by_count":232,"area":null},{"id":"2312.00785","title":"Sequential Modeling Enables Scalable Learning for Large Vision Models","created":"2023-12-01","cited_by_count":212,"area":null},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"area":null},{"id":"2212.04501","title":"Learning Video Representations from Large Language Models","created":"2022-12-08","cited_by_count":205,"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":"2307.05463","title":"EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone","created":"2023-07-11","cited_by_count":130,"area":null},{"id":"2210.03929","title":"EgoTaskQA: Understanding Human Tasks in Egocentric Videos","created":"2022-10-08","cited_by_count":115,"area":null},{"id":"2501.15368","title":"Baichuan-Omni-1.5 Technical Report","created":"2025-01-26","cited_by_count":111,"area":null},{"id":"2104.07905","title":"Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos","created":"2021-04-16","cited_by_count":99,"area":null},{"id":"2403.16182","title":"EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World","created":"2024-03-24","cited_by_count":95,"area":null},{"id":"2503.03803","title":"EgoLife: Towards Egocentric Life Assistant","created":"2025-03-05","cited_by_count":91,"area":null},{"id":"2501.07888","title":"Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video Understanding","created":"2025-01-14","cited_by_count":81,"area":"mllm"},{"id":"2312.06722","title":"EgoPlan-Bench: Benchmarking Multimodal Large Language Models for Human-Level Planning","created":"2023-12-11","cited_by_count":69,"area":"lr"},{"id":"2301.02311","title":"HierVL: Learning Hierarchical Video-Language Embeddings","created":"2023-01-05","cited_by_count":66,"area":null},{"id":"2303.09665","title":"LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Grounding","created":"2023-03-16","cited_by_count":64,"area":null},{"id":"2102.11585","title":"ROAD: The ROad event Awareness Dataset for Autonomous Driving","created":"2021-02-23","cited_by_count":54,"area":null},{"id":"2102.02751","title":"Semi-Supervised Action Recognition with Temporal Contrastive Learning","created":"2021-02-04","cited_by_count":50,"area":null},{"id":"2306.05526","title":"Learning Fine-grained View-Invariant Representations from Unpaired Ego-Exo Videos via Temporal Alignment","created":"2023-06-08","cited_by_count":46,"area":null},{"id":"2102.12321","title":"AGENT: A Benchmark for Core Psychological Reasoning","created":"2021-02-24","cited_by_count":42,"area":null},{"id":"2412.04447","title":"EgoPlan-Bench2: A Benchmark for Multimodal Large Language Model Planning in Real-World Scenarios","created":"2024-12-05","cited_by_count":41,"area":"lr"},{"id":"2303.13471","title":"Egocentric Audio-Visual Object Localization","created":"2023-03-23","cited_by_count":40,"area":null},{"id":"2104.03178","title":"The SARAS Endoscopic Surgeon Action Detection (ESAD) dataset: Challenges and methods","created":"2021-04-07","cited_by_count":38,"area":null},{"id":"2107.13411","title":"Predicting the Future from First Person (Egocentric) Vision: A Survey","created":"2021-07-28","cited_by_count":36,"area":null},{"id":"2406.08877","title":"EgoExo-Fitness: Towards Egocentric and Exocentric Full-Body Action Understanding","created":"2024-06-13","cited_by_count":36,"area":null},{"id":"2410.11623","title":"VidEgoThink: Assessing Egocentric Video Understanding Capabilities for Embodied AI","created":"2024-10-15","cited_by_count":34,"area":"lr"},{"id":"2412.04244","title":"GigaHands: A Massive Annotated Dataset of Bimanual Hand Activities","created":"2024-12-05","cited_by_count":33,"area":null},{"id":"2301.02217","title":"EgoDistill: Egocentric Head Motion Distillation for Efficient Video Understanding","created":"2023-01-05","cited_by_count":32,"area":null},{"id":"2403.06351","title":"Put Myself in Your Shoes: Lifting the Egocentric Perspective from Exocentric Videos","created":"2024-03-11","cited_by_count":32,"area":null},{"id":"2301.01380","title":"Ego-Only: Egocentric Action Detection without Exocentric Transferring","created":"2023-01-03","cited_by_count":31,"area":null},{"id":"2411.19083","title":"ObjectRelator: Enabling Cross-View Object Relation Understanding Across Ego-Centric and Exo-Centric Perspectives","created":"2024-11-28","cited_by_count":29,"area":null},{"id":"2304.11431","title":"A Review of Deep Learning for Video Captioning","created":"2023-04-22","cited_by_count":28,"area":null},{"id":"2405.10674","title":"From Sora What We Can See: A Survey of Text-to-Video Generation","created":"2024-05-17","cited_by_count":27,"area":null},{"id":"2108.05675","title":"Learning Visual Affordance Grounding from Demonstration Videos","created":"2021-08-12","cited_by_count":25,"area":null},{"id":"2212.06969","title":"EgoLoc: Revisiting 3D Object Localization from Egocentric Videos with Visual Queries","created":"2022-12-14","cited_by_count":25,"area":null},{"id":"2503.09143","title":"Exo2Ego: Exocentric Knowledge Guided MLLM for Egocentric Video Understanding","created":"2025-03-12","cited_by_count":25,"area":null},{"id":"2211.10528","title":"Where is my Wallet? Modeling Object Proposal Sets for Egocentric Visual Query Localization","created":"2022-11-18","cited_by_count":24,"area":null},{"id":"2410.07177","title":"MM-Ego: Towards Building Egocentric Multimodal LLMs for Video QA","created":"2024-10-09","cited_by_count":24,"area":"mllm"},{"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":"2207.11365","title":"EgoEnv: Human-centric environment representations from egocentric video","created":"2022-07-22","cited_by_count":22,"area":null},{"id":"2506.05287","title":"EOC-Bench: Can MLLMs Identify, Recall, and Forecast Objects in an Egocentric World?","created":"2025-06-05","cited_by_count":21,"area":"mllm"},{"id":"2305.03907","title":"Listen to Look into the Future: Audio-Visual Egocentric Gaze Anticipation","created":"2023-05-06","cited_by_count":20,"area":null},{"id":"2308.11489","title":"Learning from Semantic Alignment between Unpaired Multiviews for Egocentric Video Recognition","created":"2023-08-22","cited_by_count":20,"area":null},{"id":"2412.21080","title":"Vinci: A Real-time Embodied Smart Assistant based on Egocentric Vision-Language Model","created":"2024-12-30","cited_by_count":19,"area":"mllm"},{"id":"2503.24026","title":"HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation","created":"2025-03-31","cited_by_count":19,"area":null},{"id":"2103.16516","title":"Recognizing Actions in Videos from Unseen Viewpoints","created":"2021-03-30","cited_by_count":18,"area":null},{"id":"2211.15501","title":"Proactive Robot Assistance via Spatio-Temporal Object Modeling","created":"2022-11-28","cited_by_count":18,"area":null},{"id":"2311.00738","title":"Can Foundation Models Watch, Talk and Guide You Step by Step to Make a Cake?","created":"2023-11-01","cited_by_count":18,"area":null},{"id":"2309.02423","title":"EgoPCA: A New Framework for Egocentric Hand-Object Interaction Understanding","created":"2023-09-05","cited_by_count":15,"area":null},{"id":"2303.13505","title":"A Large-scale Study of Spatiotemporal Representation Learning with a New Benchmark on Action Recognition","created":"2023-03-23","cited_by_count":14,"area":null},{"id":"2304.08210","title":"ATTACH Dataset: Annotated Two-Handed Assembly Actions for Human Action Understanding","created":"2023-04-17","cited_by_count":14,"area":null},{"id":"2305.15699","title":"Cross-view Action Recognition Understanding From Exocentric to Egocentric Perspective","created":"2023-05-25","cited_by_count":14,"area":null},{"id":"2205.12886","title":"You Need to Read Again: Multi-granularity Perception Network for Moment Retrieval in Videos","created":"2022-05-25","cited_by_count":13,"area":null},{"id":"2206.11895","title":"Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D Space","created":"2022-06-23","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":"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":"2312.13008","title":"No More Shortcuts: Realizing the Potential of Temporal Self-Supervision","created":"2023-12-20","cited_by_count":11,"area":null},{"id":"2404.09991","title":"EgoPet: Egomotion and Interaction Data from an Animal's Perspective","created":"2024-04-15","cited_by_count":11,"area":null},{"id":"2506.01674","title":"MotionSight: Boosting Fine-Grained Motion Understanding in Multimodal LLMs","created":"2025-06-02","cited_by_count":11,"area":"mllm"},{"id":"2203.10694","title":"FAR: Fourier Aerial Video Recognition","created":"2022-03-21","cited_by_count":10,"area":null},{"id":"2501.05067","title":"LLaVA-Octopus: Unlocking Instruction-Driven Adaptive Projector Fusion for Video Understanding","created":"2025-01-09","cited_by_count":10,"area":"mllm"},{"id":"2404.09933","title":"HOI-Ref: Hand-Object Interaction Referral in Egocentric Vision","created":"2024-04-15","cited_by_count":9,"area":"mllm"},{"id":"2406.13719","title":"GUI Action Narrator: Where and When Did That Action Take Place?","created":"2024-06-19","cited_by_count":9,"area":"mllm"},{"id":"2210.02995","title":"Compressed Vision for Efficient Video Understanding","created":"2022-10-06","cited_by_count":8,"area":null},{"id":"2307.04760","title":"Learning Spatial Features from Audio-Visual Correspondence in Egocentric Videos","created":"2023-07-10","cited_by_count":8,"area":null},{"id":"2401.10039","title":"GPT4Ego: Unleashing the Potential of Pre-trained Models for Zero-Shot Egocentric Action Recognition","created":"2024-01-18","cited_by_count":8,"area":"mllm"},{"id":"2501.19061","title":"EgoMe: A New Dataset and Challenge for Following Me via Egocentric View in Real World","created":"2025-01-31","cited_by_count":8,"area":"offlinerl"},{"id":"2407.05576","title":"CaRe-Ego: Contact-aware Relationship Modeling for Egocentric Interactive Hand-object Segmentation","created":"2024-07-08","cited_by_count":7,"area":null},{"id":"2311.18572","title":"Source-free Video Domain Adaptation by Learning from Noisy Labels","created":"2023-11-30","cited_by_count":6,"area":null},{"id":"2410.01341","title":"Cognition Transferring and Decoupling for Text-supervised Egocentric Semantic Segmentation","created":"2024-10-02","cited_by_count":6,"area":null},{"id":"2410.20621","title":"Egocentric and Exocentric Methods: A Short Survey","created":"2024-10-27","cited_by_count":6,"area":null},{"id":"2503.19706","title":"Bootstrap Your Own Views: Masked Ego-Exo Modeling for Fine-grained View-invariant Video Representations","created":"2025-03-25","cited_by_count":6,"area":null},{"id":"2503.21055","title":"What Changed and What Could Have Changed? State-Change Counterfactuals for Procedure-Aware Video Representation Learning","created":"2025-03-27","cited_by_count":6,"area":null},{"id":"2505.21955","title":"Towards Comprehensive Scene Understanding: Integrating First and Third-Person Views for LVLMs","created":"2025-05-28","cited_by_count":6,"area":"mllm"},{"id":"2607.24744","title":"Data Pyramid for Embodied Manipulation: A Survey","created":"2026-07-27","cited_by_count":6,"area":null},{"id":"2306.02014","title":"Uncovering the Hidden Dynamics of Video Self-supervised Learning under Distribution Shifts","created":"2023-06-03","cited_by_count":4,"area":null},{"id":"2404.18934","title":"The Visual Experience Dataset: Over 200 Recorded Hours of Integrated Eye Movement, Odometry, and Egocentric Video","created":"2024-02-15","cited_by_count":4,"area":null},{"id":"2501.05711","title":"From My View to Yours: Learning Egocentric Cues from Exocentric Video using Privileged Egocentric Supervision","created":"2025-01-10","cited_by_count":4,"area":"mllm"},{"id":"2506.21080","title":"EgoAdapt: Adaptive Multisensory Distillation and Policy Learning for Efficient Egocentric Perception","created":"2025-06-26","cited_by_count":4,"area":null},{"id":"2511.16595","title":"TimeViper: A Hybrid Mamba-Transformer Vision-Language Model for Efficient Long Video Understanding","created":"2025-11-20","cited_by_count":4,"area":"mllm"},{"id":"2603.27593","title":"STRIDE: When to Speak Meets Sequence Denoising for Streaming Video Understanding","created":"2026-03-29","cited_by_count":4,"area":"lr"},{"id":"2606.08615","title":"Harnessing Streaming Video in the Wild","created":"2026-06-07","cited_by_count":4,"area":"mllm"},{"id":"2608.06867","title":"LLMRouter: Unified Infrastructure for Developing, Evaluating, and Deploying LLM Routers","created":"2026-08-07","cited_by_count":4,"area":null},{"id":"2104.07135","title":"Adaptive Intermediate Representations for Video Understanding","created":"2021-04-14","cited_by_count":3,"area":null},{"id":"2409.01448","title":"FinePseudo: Improving Pseudo-Labelling through Temporal-Alignablity for Semi-Supervised Fine-Grained Action Recognition","created":"2024-09-02","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":"2601.00092","title":"Spatial4D-Bench: A Versatile 4D Spatial Intelligence Benchmark","created":"2025-12-31","cited_by_count":3,"area":"lr"},{"id":"2603.02098","title":"Efficient and High-Fidelity Omni Modality Retrieval","created":"2026-03-02","cited_by_count":3,"area":null},{"id":"2607.29401","title":"OSEF: One-Step Evidence Fusion for Cross-Video Scene Procedure Planning","created":"2026-07-31","cited_by_count":3,"area":null},{"id":"2110.06827","title":"NoisyActions2M: A Multimedia Dataset for Video Understanding from Noisy Labels","created":"2021-10-13","cited_by_count":2,"area":null},{"id":"2303.08920","title":"EgoViT: Pyramid Video Transformer for Egocentric Action Recognition","created":"2023-03-15","cited_by_count":2,"area":null},{"id":"2509.08908","title":"Diffusion-Based Action Recognition Generalizes to Untrained Domains","created":"2025-09-10","cited_by_count":2,"area":null},{"id":"2603.09798","title":"Test-time Ego-Exo-centric Adaptation for Action Anticipation via Multi-Label Prototype Growing and Dual-Clue Consistency","created":"2026-03-10","cited_by_count":2,"area":null},{"id":"2202.08138","title":"When Did It Happen? Duration-informed Temporal Localization of Narrated Actions in Vlogs","created":"2022-02-16","cited_by_count":1,"area":null},{"id":"2212.03384","title":"DroneAttention: Sparse Weighted Temporal Attention for Drone-Camera Based Activity Recognition","created":"2022-12-07","cited_by_count":1,"area":null}],"next_cursor":"100"}