{"total":67,"rows":[{"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":"2311.17076","title":"Compositional Chain-of-Thought Prompting for Large Multimodal Models","created":"2023-11-27","cited_by_count":164,"area":"lr"},{"id":"2106.11310","title":"Towards Long-Form Video Understanding","created":"2021-06-21","cited_by_count":146,"area":null},{"id":"2209.13064","title":"EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations","created":"2022-09-26","cited_by_count":140,"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":"2406.11815","title":"LLARVA: Vision-Action Instruction Tuning Enhances Robot Learning","created":"2024-06-17","cited_by_count":87,"area":"mllm"},{"id":"2308.07123","title":"An Outlook into the Future of Egocentric Vision","created":"2023-08-14","cited_by_count":84,"area":null},{"id":"2110.06915","title":"Object-Region Video Transformers","created":"2021-10-13","cited_by_count":73,"area":null},{"id":"2305.19595","title":"Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models","created":"2023-05-31","cited_by_count":72,"area":null},{"id":"2211.11733","title":"Teaching Structured Vision&Language Concepts to Vision&Language Models","created":"2022-11-21","cited_by_count":71,"area":null},{"id":"2102.00649","title":"Forecasting Action through Contact Representations from First Person Video","created":"2021-02-01","cited_by_count":46,"area":null},{"id":"2111.01024","title":"With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognition","created":"2021-11-01","cited_by_count":41,"area":null},{"id":"2304.00733","title":"Unbiased Scene Graph Generation in Videos","created":"2023-04-03","cited_by_count":39,"area":null},{"id":"2305.06343","title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","created":"2023-05-10","cited_by_count":39,"area":null},{"id":"2103.15662","title":"Unified Graph Structured Models for Video Understanding","created":"2021-03-29","cited_by_count":38,"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":"2106.13432","title":"Hierarchical Object-oriented Spatio-Temporal Reasoning for Video Question Answering","created":"2021-06-25","cited_by_count":29,"area":null},{"id":"2103.01302","title":"Coarse-Fine Networks for Temporal Activity Detection in Videos","created":"2021-03-01","cited_by_count":28,"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":"2404.01476","title":"TraveLER: A Modular Multi-LMM Agent Framework for Video Question-Answering","created":"2024-04-01","cited_by_count":25,"area":"mllm"},{"id":"2207.10075","title":"Is an Object-Centric Video Representation Beneficial for Transfer?","created":"2022-07-20","cited_by_count":24,"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":"2111.01936","title":"Revisiting spatio-temporal layouts for compositional action recognition","created":"2021-11-02","cited_by_count":19,"area":null},{"id":"2204.03101","title":"Hierarchical Self-supervised Representation Learning for Movie Understanding","created":"2022-04-06","cited_by_count":19,"area":null},{"id":"2212.06301","title":"Egocentric Video Task Translation","created":"2022-12-13","cited_by_count":19,"area":null},{"id":"2501.04336","title":"Building a Mind Palace: Structuring Environment-Grounded Semantic Graphs for Effective Long Video Analysis with LLMs","created":"2025-01-08","cited_by_count":19,"area":"mllm"},{"id":"2504.13915","title":"Memory-efficient Streaming VideoLLMs for Real-time Procedural Video Understanding","created":"2025-04-10","cited_by_count":19,"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":"2305.15699","title":"Cross-view Action Recognition Understanding From Exocentric to Egocentric Perspective","created":"2023-05-25","cited_by_count":14,"area":null},{"id":"2204.09303","title":"Attention in Attention: Modeling Context Correlation for Efficient Video Classification","created":"2022-04-20","cited_by_count":12,"area":null},{"id":"2311.17948","title":"Action-slot: Visual Action-centric Representations for Multi-label Atomic Activity Recognition in Traffic Scenes","created":"2023-11-29","cited_by_count":12,"area":null},{"id":"2109.04047","title":"ACP++: Action Co-occurrence Priors for Human-Object Interaction Detection","created":"2021-09-09","cited_by_count":11,"area":null},{"id":"2207.03656","title":"Video Dialog as Conversation about Objects Living in Space-Time","created":"2022-07-08","cited_by_count":11,"area":null},{"id":"2104.00646","title":"Motion Guided Attention Fusion to Recognize Interactions from Videos","created":"2021-04-01","cited_by_count":10,"area":null},{"id":"2206.04669","title":"Beyond RGB: Scene-Property Synthesis with Neural Radiance Fields","created":"2022-06-09","cited_by_count":10,"area":null},{"id":"2204.04796","title":"SOS! Self-supervised Learning Over Sets Of Handled Objects In Egocentric Action Recognition","created":"2022-04-10","cited_by_count":8,"area":null},{"id":"2207.03807","title":"Beyond Transfer Learning: Co-finetuning for Action Localisation","created":"2022-07-08","cited_by_count":8,"area":null},{"id":"2211.01781","title":"Video Event Extraction via Tracking Visual States of Arguments","created":"2022-11-03","cited_by_count":8,"area":null},{"id":"2404.11903","title":"Simultaneous Detection and Interaction Reasoning for Object-Centric Action Recognition","created":"2024-04-18","cited_by_count":8,"area":null},{"id":"2201.04906","title":"Hand-Object Interaction Reasoning","created":"2022-01-13","cited_by_count":7,"area":null},{"id":"2312.17345","title":"3VL: Using Trees to Improve Vision-Language Models' Interpretability","created":"2023-12-28","cited_by_count":7,"area":"mllm"},{"id":"2102.08065","title":"Learning to Recognize Actions on Objects in Egocentric Video with Attention Dictionaries","created":"2021-02-16","cited_by_count":6,"area":null},{"id":"2211.07501","title":"Discovering A Variety of Objects in Spatio-Temporal Human-Object Interactions","created":"2022-11-14","cited_by_count":6,"area":null},{"id":"2111.13675","title":"Weakly-guided Self-supervised Pretraining for Temporal Activity Detection","created":"2021-11-26","cited_by_count":5,"area":null},{"id":"2305.14577","title":"Difference-Masking: Choosing What to Mask in Continued Pretraining","created":"2023-05-23","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":"2104.11520","title":"Modeling long-term interactions to enhance action recognition","created":"2021-04-23","cited_by_count":3,"area":null},{"id":"2106.03162","title":"Transformed ROIs for Capturing Visual Transformations in Videos","created":"2021-06-06","cited_by_count":3,"area":null},{"id":"2506.20342","title":"Feature Hallucination for Self-supervised Action Recognition","created":"2025-06-25","cited_by_count":3,"area":null},{"id":"2204.09468","title":"THORN: Temporal Human-Object Relation Network for Action Recognition","created":"2022-04-20","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":"2503.18553","title":"ATARS: An Aerial Traffic Atomic Activity Recognition and Temporal Segmentation Dataset","created":"2025-03-24","cited_by_count":2,"area":null},{"id":"2112.09448","title":"Distillation of Human-Object Interaction Contexts for Action Recognition","created":"2021-12-17","cited_by_count":1,"area":null},{"id":"2305.02673","title":"Modelling Spatio-Temporal Interactions For Compositional Action Recognition","created":"2023-05-04","cited_by_count":1,"area":null},{"id":"2401.12480","title":"IDPro: Flexible Interactive Video Object Segmentation by ID-queried Concurrent Propagation","created":"2024-01-23","cited_by_count":1,"area":null},{"id":"2405.08204","title":"A Semantic and Motion-Aware Spatiotemporal Transformer Network for Action Detection","created":"2024-05-13","cited_by_count":1,"area":null},{"id":"2408.09511","title":"NAVERO: Unlocking Fine-Grained Semantics for Video-Language Compositionality","created":"2024-08-18","cited_by_count":1,"area":null},{"id":"2409.17356","title":"A vision-based framework for human behavior understanding in industrial assembly lines","created":"2024-09-25","cited_by_count":1,"area":null},{"id":"2601.06097","title":"Semantic Event Graphs for Long-Form Video Question Answering","created":"2026-01-02","cited_by_count":1,"area":"mllm"},{"id":"2203.12344","title":"How Do You Do It? Fine-Grained Action Understanding with Pseudo-Adverbs","created":"2022-03-23","cited_by_count":0,"area":null},{"id":"2206.06346","title":"Bringing Image Scene Structure to Video via Frame-Clip Consistency of Object Tokens","created":"2022-06-13","cited_by_count":0,"area":null},{"id":"2405.08695","title":"The impact of Compositionality in Zero-shot Multi-label action recognition for Object-based tasks","created":"2024-05-14","cited_by_count":0,"area":null},{"id":"2503.14524","title":"Salient Temporal Encoding for Dynamic Scene Graph Generation","created":"2025-03-15","cited_by_count":0,"area":null},{"id":"2508.17270","title":"Spatial-Temporal Human-Object Interaction Detection","created":"2025-08-24","cited_by_count":0,"area":null},{"id":"2604.08342","title":"EgoEverything: A Benchmark for Human Behavior Inspired Long Context Egocentric Video Understanding in AR Environment","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2609.24127","title":"Action-Slot: Structured Action-Centric Representation Learning for Multi-Agent Atomic Activity Understanding","created":"2026-09-21","cited_by_count":0,"area":null}],"next_cursor":null}