{"total":167,"rows":[{"id":"2203.05625","title":"PETR: Position Embedding Transformation for Multi-View 3D Object Detection","created":"2022-03-10","cited_by_count":552,"area":null},{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542,"area":null},{"id":"2212.04501","title":"Learning Video Representations from Large Language Models","created":"2022-12-08","cited_by_count":205,"area":null},{"id":"2312.17235","title":"A Simple LLM Framework for Long-Range Video Question-Answering","created":"2023-12-28","cited_by_count":178,"area":null},{"id":"2405.16009","title":"Streaming Long Video Understanding with Large Language Models","created":"2024-05-25","cited_by_count":167,"area":null},{"id":"2404.03384","title":"LongVLM: Efficient Long Video Understanding via Large Language Models","created":"2024-04-04","cited_by_count":147,"area":null},{"id":"2210.03929","title":"EgoTaskQA: Understanding Human Tasks in Egocentric Videos","created":"2022-10-08","cited_by_count":115,"area":null},{"id":"2411.04998","title":"HourVideo: 1-Hour Video-Language Understanding","created":"2024-11-07","cited_by_count":113,"area":null},{"id":"2308.07123","title":"An Outlook into the Future of Egocentric Vision","created":"2023-08-14","cited_by_count":84,"area":null},{"id":"2404.01297","title":"Streaming Dense Video Captioning","created":"2024-04-01","cited_by_count":82,"area":null},{"id":"2404.17176","title":"MovieChat+: Question-aware Sparse Memory for Long Video Question Answering","created":"2024-04-26","cited_by_count":73,"area":null},{"id":"2301.02311","title":"HierVL: Learning Hierarchical Video-Language Embeddings","created":"2023-01-05","cited_by_count":66,"area":null},{"id":"2406.12846","title":"DrVideo: Document Retrieval Based Long Video Understanding","created":"2024-06-18","cited_by_count":65,"area":null},{"id":"2205.08508","title":"A CLIP-Hitchhiker's Guide to Long Video Retrieval","created":"2022-05-17","cited_by_count":57,"area":null},{"id":"2404.04346","title":"Koala: Key frame-conditioned long video-LLM","created":"2024-04-05","cited_by_count":57,"area":null},{"id":"2403.14622","title":"Language Repository for Long Video Understanding","created":"2024-03-21","cited_by_count":55,"area":null},{"id":"2404.04808","title":"MemFlow: Optical Flow Estimation and Prediction with Memory","created":"2024-04-07","cited_by_count":55,"area":null},{"id":"2205.01230","title":"Retrieval-Enhanced Machine Learning","created":"2022-05-02","cited_by_count":47,"area":null},{"id":"2402.05861","title":"Memory Consolidation Enables Long-Context Video Understanding","created":"2024-02-08","cited_by_count":45,"area":null},{"id":"2210.02396","title":"Temporally Consistent Transformers for Video Generation","created":"2022-10-05","cited_by_count":44,"area":null},{"id":"2411.05222","title":"Don't Look Twice: Faster Video Transformers with Run-Length Tokenization","created":"2024-11-07","cited_by_count":43,"area":null},{"id":"2210.12649","title":"Anticipative Feature Fusion Transformer for Multi-Modal Action Anticipation","created":"2022-10-23","cited_by_count":41,"area":null},{"id":"2308.07893","title":"Memory-and-Anticipation Transformer for Online Action Understanding","created":"2023-08-15","cited_by_count":39,"area":null},{"id":"2211.14154","title":"Interaction Region Visual Transformer for Egocentric Action Anticipation","created":"2022-11-25","cited_by_count":37,"area":null},{"id":"2409.10917","title":"AMEGO: Active Memory from long EGOcentric videos","created":"2024-09-17","cited_by_count":36,"area":null},{"id":"2307.08763","title":"Video-Mined Task Graphs for Keystep Recognition in Instructional Videos","created":"2023-07-17","cited_by_count":35,"area":null},{"id":"2512.03627","title":"MemVerse: Multimodal Memory for Lifelong Learning Agents","created":"2025-12-03","cited_by_count":35,"area":null},{"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":"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":"2405.20305","title":"Can't make an Omelette without Breaking some Eggs: Plausible Action Anticipation using Large Video-Language Models","created":"2024-05-30","cited_by_count":33,"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":"2210.12686","title":"Holistic Interaction Transformer Network for Action Detection","created":"2022-10-23","cited_by_count":28,"area":null},{"id":"2211.09119","title":"Token Turing Machines","created":"2022-11-16","cited_by_count":25,"area":null},{"id":"2312.04817","title":"LvBench: A Benchmark for Long-form Video Understanding with Versatile Multi-modal Question Answering","created":"2023-12-08","cited_by_count":25,"area":null},{"id":"2308.04549","title":"Prune Spatio-temporal Tokens by Semantic-aware Temporal Accumulation","created":"2023-08-08","cited_by_count":24,"area":null},{"id":"2308.11488","title":"Opening the Vocabulary of Egocentric Actions","created":"2023-08-22","cited_by_count":23,"area":null},{"id":"2304.01143","title":"Use Your Head: Improving Long-Tail Video Recognition","created":"2023-04-03","cited_by_count":22,"area":null},{"id":"2301.09209","title":"Summarize the Past to Predict the Future: Natural Language Descriptions of Context Boost Multimodal Object Interaction Anticipation","created":"2023-01-22","cited_by_count":21,"area":null},{"id":"2206.09852","title":"M&M Mix: A Multimodal Multiview Transformer Ensemble","created":"2022-06-20","cited_by_count":20,"area":null},{"id":"2304.08451","title":"Efficient Video Action Detection with Token Dropout and Context Refinement","created":"2023-04-17","cited_by_count":20,"area":null},{"id":"2304.12160","title":"End-to-End Spatio-Temporal Action Localisation with Video Transformers","created":"2023-04-24","cited_by_count":20,"area":null},{"id":"2309.16669","title":"Training a Large Video Model on a Single Machine in a Day","created":"2023-09-28","cited_by_count":20,"area":null},{"id":"2503.15275","title":"Challenges and Trends in Egocentric Vision: A Survey","created":"2025-03-19","cited_by_count":20,"area":null},{"id":"2303.01765","title":"Diverse 3D Hand Gesture Prediction from Body Dynamics by Bilateral Hand Disentanglement","created":"2023-03-03","cited_by_count":18,"area":null},{"id":"2403.09805","title":"On the Utility of 3D Hand Poses for Action Recognition","created":"2024-03-14","cited_by_count":17,"area":null},{"id":"2503.20781","title":"BASKET: A Large-Scale Video Dataset for Fine-Grained Skill Estimation","created":"2025-03-26","cited_by_count":17,"area":null},{"id":"2308.08303","title":"Leveraging Next-Active Objects for Context-Aware Anticipation in Egocentric Videos","created":"2023-08-16","cited_by_count":16,"area":null},{"id":"2407.21757","title":"Learning Video Context as Interleaved Multimodal Sequences","created":"2024-07-31","cited_by_count":16,"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":"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":"2404.05559","title":"TIM: A Time Interval Machine for Audio-Visual Action Recognition","created":"2024-04-08","cited_by_count":15,"area":null},{"id":"2209.05044","title":"Predicting the Next Action by Modeling the Abstract Goal","created":"2022-09-12","cited_by_count":14,"area":null},{"id":"2212.04821","title":"PromptonomyViT: Multi-Task Prompt Learning Improves Video Transformers using Synthetic Scene Data","created":"2022-12-08","cited_by_count":14,"area":null},{"id":"2204.13340","title":"The Wisdom of Crowds: Temporal Progressive Attention for Early Action Prediction","created":"2022-04-28","cited_by_count":13,"area":null},{"id":"2306.15045","title":"Action Anticipation with Goal Consistency","created":"2023-06-26","cited_by_count":12,"area":null},{"id":"2311.18825","title":"CAST: Cross-Attention in Space and Time for Video Action Recognition","created":"2023-11-30","cited_by_count":12,"area":null},{"id":"2309.17257","title":"A Survey on Deep Learning Techniques for Action Anticipation","created":"2023-09-29","cited_by_count":11,"area":null},{"id":"2407.12982","title":"Retrieval-Enhanced Machine Learning: Synthesis and Opportunities","created":"2024-07-17","cited_by_count":11,"area":null},{"id":"2408.17443","title":"HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics","created":"2024-08-30","cited_by_count":11,"area":null},{"id":"2502.20879","title":"egoPPG: Heart Rate Estimation from Eye-Tracking Cameras in Egocentric Systems to Benefit Downstream Vision Tasks","created":"2025-02-28","cited_by_count":11,"area":null},{"id":"2303.17228","title":"Streaming Video Model","created":"2023-03-30","cited_by_count":10,"area":null},{"id":"2401.16424","title":"Computer Vision for Primate Behavior Analysis in the Wild","created":"2024-01-29","cited_by_count":10,"area":null},{"id":"2407.02309","title":"Semantically Guided Representation Learning For Action Anticipation","created":"2024-07-02","cited_by_count":10,"area":null},{"id":"2210.04485","title":"A Memory Transformer Network for Incremental Learning","created":"2022-10-10","cited_by_count":9,"area":null},{"id":"2210.14714","title":"TAMFormer: Multi-Modal Transformer with Learned Attention Mask for Early Intent Prediction","created":"2022-10-26","cited_by_count":9,"area":null},{"id":"2410.14045","title":"Human Action Anticipation: A Survey","created":"2024-10-17","cited_by_count":9,"area":null},{"id":"2412.00932","title":"FIction: 4D Future Interaction Prediction from Video","created":"2024-12-01","cited_by_count":9,"area":null},{"id":"2504.00072","title":"Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMs","created":"2025-03-31","cited_by_count":9,"area":null},{"id":"2305.12953","title":"Enhancing Next Active Object-based Egocentric Action Anticipation with Guided Attention","created":"2023-05-22","cited_by_count":8,"area":null},{"id":"2306.07703","title":"E2E-LOAD: End-to-End Long-form Online Action Detection","created":"2023-06-13","cited_by_count":8,"area":null},{"id":"2403.01915","title":"xT: Nested Tokenization for Larger Context in Large Images","created":"2024-03-04","cited_by_count":8,"area":null},{"id":"2408.02957","title":"Online Temporal Action Localization with Memory-Augmented Transformer","created":"2024-08-06","cited_by_count":8,"area":null},{"id":"2305.15775","title":"Concept-Centric Transformers: Enhancing Model Interpretability through Object-Centric Concept Learning within a Shared Global Workspace","created":"2023-05-25","cited_by_count":7,"area":null},{"id":"2308.05787","title":"Temporally-Adaptive Models for Efficient Video Understanding","created":"2023-08-10","cited_by_count":7,"area":null},{"id":"2312.00826","title":"DEVIAS: Learning Disentangled Video Representations of Action and Scene","created":"2023-11-30","cited_by_count":7,"area":null},{"id":"2312.04552","title":"Generating Illustrated Instructions","created":"2023-12-07","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":"2404.18648","title":"Uncertainty-boosted Robust Video Activity Anticipation","created":"2024-04-29","cited_by_count":7,"area":null},{"id":"2408.11687","title":"Interpretable Long-term Action Quality Assessment","created":"2024-08-21","cited_by_count":7,"area":null},{"id":"2411.13626","title":"Principles of Visual Tokens for Efficient Video Understanding","created":"2024-11-20","cited_by_count":7,"area":null},{"id":"2308.11244","title":"Are current long-term video understanding datasets long-term?","created":"2023-08-22","cited_by_count":6,"area":null},{"id":"2401.12972","title":"On the Efficacy of Text-Based Input Modalities for Action Anticipation","created":"2024-01-23","cited_by_count":6,"area":null},{"id":"2211.11293","title":"Beyond the Field-of-View: Enhancing Scene Visibility and Perception with Clip-Recurrent Transformer","created":"2022-11-21","cited_by_count":5,"area":null},{"id":"2301.02307","title":"What You Say Is What You Show: Visual Narration Detection in Instructional Videos","created":"2023-01-05","cited_by_count":5,"area":null},{"id":"2404.00973","title":"VideoDistill: Language-aware Vision Distillation for Video Question Answering","created":"2024-04-01","cited_by_count":5,"area":null},{"id":"2410.08860","title":"Audio Description Generation in the Era of LLMs and VLMs: A Review of Transferable Generative AI Technologies","created":"2024-10-11","cited_by_count":5,"area":null},{"id":"2507.00033","title":"Moment Sampling in Video LLMs for Long-Form Video QA","created":"2025-06-18","cited_by_count":5,"area":null},{"id":"2608.13416","title":"StreamTTT: Reconciling Real-Time Perception and Long-Term Memory in Streaming VLMs","created":"2026-08-13","cited_by_count":5,"area":null},{"id":"2308.04834","title":"View while Moving: Efficient Video Recognition in Long-untrimmed Videos","created":"2023-08-09","cited_by_count":4,"area":null},{"id":"2312.17686","title":"Multiscale Vision Transformers meet Bipartite Matching for efficient single-stage Action Localization","created":"2023-12-29","cited_by_count":4,"area":null},{"id":"2401.04023","title":"Efficient Multiscale Multimodal Bottleneck Transformer for Audio-Video Classification","created":"2024-01-08","cited_by_count":4,"area":null},{"id":"2503.13707","title":"Long-VMNet: Accelerating Long-Form Video Understanding via Fixed Memory","created":"2025-03-17","cited_by_count":4,"area":null},{"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":"2511.13993","title":"Learning Skill-Attributes for Transferable Assessment in Video","created":"2025-11-17","cited_by_count":4,"area":null},{"id":"2303.16118","title":"CycleACR: Cycle Modeling of Actor-Context Relations for Video Action Detection","created":"2023-03-28","cited_by_count":3,"area":null},{"id":"2306.16606","title":"EgoCOL: Egocentric Camera pose estimation for Open-world 3D object Localization @Ego4D challenge 2023","created":"2023-06-29","cited_by_count":3,"area":null},{"id":"2309.13353","title":"Beyond Grids: Exploring Elastic Input Sampling for Vision Transformers","created":"2023-09-23","cited_by_count":3,"area":null},{"id":"2407.02934","title":"PosMLP-Video: Spatial and Temporal Relative Position Encoding for Efficient Video Recognition","created":"2024-07-03","cited_by_count":3,"area":null},{"id":"2410.11702","title":"It's Just Another Day: Unique Video Captioning by Discriminative Prompting","created":"2024-10-15","cited_by_count":3,"area":null},{"id":"2411.01455","title":"HiMemFormer: Hierarchical Memory-Aware Transformer for Multi-Agent Action Anticipation","created":"2024-11-03","cited_by_count":3,"area":null}],"next_cursor":"100"}