{"total":114,"rows":[{"id":"2311.17076","title":"Compositional Chain-of-Thought Prompting for Large Multimodal Models","created":"2023-11-27","cited_by_count":164,"area":"lr"},{"id":"2502.13130","title":"Magma: A Foundation Model for Multimodal AI Agents","created":"2025-02-18","cited_by_count":139,"area":"agents"},{"id":"2401.08399","title":"TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understanding","created":"2024-01-16","cited_by_count":88,"area":null},{"id":"2109.05488","title":"ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis","created":"2021-09-12","cited_by_count":76,"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":"2103.16564","title":"Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning","created":"2021-03-30","cited_by_count":68,"area":null},{"id":"2103.07372","title":"ACTION-Net: Multipath Excitation for Action Recognition","created":"2021-03-11","cited_by_count":63,"area":null},{"id":"2203.13049","title":"Compositional Temporal Grounding with Structured Variational Cross-Graph Correspondence Learning","created":"2022-03-24","cited_by_count":59,"area":null},{"id":"2207.14299","title":"Graph Inverse Reinforcement Learning from Diverse Videos","created":"2022-07-28","cited_by_count":46,"area":"offlinerl"},{"id":"2304.10465","title":"Implicit Temporal Modeling with Learnable Alignment for Video Recognition","created":"2023-04-20","cited_by_count":46,"area":null},{"id":"2103.15662","title":"Unified Graph Structured Models for Video Understanding","created":"2021-03-29","cited_by_count":38,"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":"2212.04155","title":"Latent Graph Representations for Critical View of Safety Assessment","created":"2022-12-08","cited_by_count":37,"area":null},{"id":"2312.11782","title":"Learning Object State Changes in Videos: An Open-World Perspective","created":"2023-12-19","cited_by_count":36,"area":null},{"id":"2404.14735","title":"Rank2Reward: Learning Shaped Reward Functions from Passive Video","created":"2024-04-23","cited_by_count":32,"area":"deeprl"},{"id":"2102.07092","title":"Learning Self-Similarity in Space and Time as Generalized Motion for Video Action Recognition","created":"2021-02-14","cited_by_count":31,"area":null},{"id":"2308.07918","title":"Helping Hands: An Object-Aware Ego-Centric Video Recognition Model","created":"2023-08-15","cited_by_count":31,"area":null},{"id":"2204.05845","title":"Probabilistic Compositional Embeddings for Multimodal Image Retrieval","created":"2022-04-12","cited_by_count":29,"area":null},{"id":"2205.02717","title":"BasicTAD: an Astounding RGB-Only Baseline for Temporal Action Detection","created":"2022-05-05","cited_by_count":28,"area":null},{"id":"2210.12686","title":"Holistic Interaction Transformer Network for Action Detection","created":"2022-10-23","cited_by_count":28,"area":null},{"id":"2307.07483","title":"Multimodal Distillation for Egocentric Action Recognition","created":"2023-07-14","cited_by_count":28,"area":"distill"},{"id":"2503.09143","title":"Exo2Ego: Exocentric Knowledge Guided MLLM for Egocentric Video Understanding","created":"2025-03-12","cited_by_count":25,"area":null},{"id":"2207.10075","title":"Is an Object-Centric Video Representation Beneficial for Transfer?","created":"2022-07-20","cited_by_count":24,"area":null},{"id":"2311.00180","title":"Object-centric Video Representation for Long-term Action Anticipation","created":"2023-10-31","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":"2306.11726","title":"How can objects help action recognition?","created":"2023-06-20","cited_by_count":21,"area":null},{"id":"2112.01194","title":"Video-Text Pre-training with Learned Regions","created":"2021-12-02","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":"2112.05892","title":"COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modality","created":"2021-12-11","cited_by_count":19,"area":null},{"id":"2301.09071","title":"Variational Cross-Graph Reasoning and Adaptive Structured Semantics Learning for Compositional Temporal Grounding","created":"2023-01-22","cited_by_count":19,"area":null},{"id":"2408.07147","title":"Controlling the World by Sleight of Hand","created":"2024-08-13","cited_by_count":19,"area":null},{"id":"2407.08101","title":"What to Say and When to Say it: Live Fitness Coaching as a Testbed for Situated Interaction","created":"2024-07-11","cited_by_count":18,"area":"mllm"},{"id":"2207.09425","title":"Geometric Features Informed Multi-person Human-object Interaction Recognition in Videos","created":"2022-07-19","cited_by_count":17,"area":null},{"id":"2107.10771","title":"EAN: Event Adaptive Network for Enhanced Action Recognition","created":"2021-07-22","cited_by_count":16,"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":"2203.14272","title":"Discovering Human-Object Interaction Concepts via Self-Compositional Learning","created":"2022-03-27","cited_by_count":15,"area":null},{"id":"2205.01657","title":"Cross-modal Representation Learning for Zero-shot Action Recognition","created":"2022-05-03","cited_by_count":15,"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":"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":"2306.17778","title":"Look, Remember and Reason: Grounded reasoning in videos with language models","created":"2023-06-30","cited_by_count":14,"area":"lr"},{"id":"2312.06829","title":"Encoding Surgical Videos as Latent Spatiotemporal Graphs for Object and Anatomy-Driven Reasoning","created":"2023-12-11","cited_by_count":14,"area":null},{"id":"2405.19917","title":"Multimodal Cross-Domain Few-Shot Learning for Egocentric Action Recognition","created":"2024-05-30","cited_by_count":14,"area":"distill"},{"id":"2104.00616","title":"Composable Augmentation Encoding for Video Representation Learning","created":"2021-04-01","cited_by_count":13,"area":null},{"id":"2110.14994","title":"Skeleton-Based Mutually Assisted Interacted Object Localization and Human Action Recognition","created":"2021-10-28","cited_by_count":13,"area":null},{"id":"2304.07647","title":"LASER: A Neuro-Symbolic Framework for Learning Spatial-Temporal Scene Graphs with Weak Supervision","created":"2023-04-15","cited_by_count":13,"area":null},{"id":"2309.14339","title":"Chop & Learn: Recognizing and Generating Object-State Compositions","created":"2023-09-25","cited_by_count":13,"area":null},{"id":"2108.08633","title":"Spatio-Temporal Interaction Graph Parsing Networks for Human-Object Interaction Recognition","created":"2021-08-19","cited_by_count":12,"area":null},{"id":"2203.05928","title":"TFCNet: Temporal Fully Connected Networks for Static Unbiased Temporal Reasoning","created":"2022-03-11","cited_by_count":12,"area":null},{"id":"2303.09756","title":"Video Action Recognition with Attentive Semantic Units","created":"2023-03-17","cited_by_count":12,"area":"mllm"},{"id":"2412.11785","title":"InterDyn: Controllable Interactive Dynamics with Video Diffusion Models","created":"2024-12-16","cited_by_count":12,"area":"diffusion"},{"id":"2104.00646","title":"Motion Guided Attention Fusion to Recognize Interactions from Videos","created":"2021-04-01","cited_by_count":10,"area":null},{"id":"2211.13500","title":"Multi-Task Learning of Object State Changes from Uncurated Videos","created":"2022-11-24","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":"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":"2407.06113","title":"C2C: Component-to-Composition Learning for Zero-Shot Compositional Action Recognition","created":"2024-07-08","cited_by_count":9,"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":"2407.06871","title":"Rethinking Image-to-Video Adaptation: An Object-centric Perspective","created":"2024-07-09","cited_by_count":8,"area":null},{"id":"2510.14874","title":"TOUCH: Text-guided Controllable Generation of Free-Form Hand-Object Interactions","created":"2025-10-16","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":"2211.01783","title":"Quantifying and Learning Static vs. Dynamic Information in Deep Spatiotemporal Networks","created":"2022-11-03","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":"2207.01708","title":"Disentangled Action Recognition with Knowledge Bases","created":"2022-07-04","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":"2312.12250","title":"ST(OR)2: Spatio-Temporal Object Level Reasoning for Activity Recognition in the Operating Room","created":"2023-12-19","cited_by_count":6,"area":null},{"id":"2412.19542","title":"Interacted Object Grounding in Spatio-Temporal Human-Object Interactions","created":"2024-12-27","cited_by_count":6,"area":null},{"id":"2304.04688","title":"Interaction-Aware Prompting for Zero-Shot Spatio-Temporal Action Detection","created":"2023-04-10","cited_by_count":5,"area":null},{"id":"2108.12957","title":"Searching for Two-Stream Models in Multivariate Space for Video Recognition","created":"2021-08-30","cited_by_count":4,"area":null},{"id":"2306.04822","title":"Optimizing ViViT Training: Time and Memory Reduction for Action Recognition","created":"2023-06-07","cited_by_count":4,"area":null},{"id":"2402.12706","title":"Learning Causal Domain-Invariant Temporal Dynamics for Few-Shot Action Recognition","created":"2024-02-20","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":"2508.02320","title":"Zero-shot Compositional Action Recognition with Neural Logic Constraints","created":"2025-08-04","cited_by_count":4,"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":"2206.04003","title":"Patch-based Object-centric Transformers for Efficient Video Generation","created":"2022-06-08","cited_by_count":3,"area":null},{"id":"2308.12447","title":"MOFO: MOtion FOcused Self-Supervision for Video Understanding","created":"2023-08-23","cited_by_count":3,"area":null},{"id":"2506.03440","title":"Geometric Visual Fusion Graph Neural Networks for Multi-Person Human-Object Interaction Recognition in Videos","created":"2025-06-03","cited_by_count":3,"area":null},{"id":"2201.09169","title":"Rich Action-semantic Consistent Knowledge for Early Action Prediction","created":"2022-01-23","cited_by_count":2,"area":null},{"id":"2210.04331","title":"Students taught by multimodal teachers are superior action recognizers","created":"2022-10-09","cited_by_count":2,"area":"distill"},{"id":"2307.06527","title":"Free-Form Composition Networks for Egocentric Action Recognition","created":"2023-07-13","cited_by_count":2,"area":null},{"id":"2501.07100","title":"Collaborative Learning for 3D Hand-Object Reconstruction and Compositional Action Recognition from Egocentric RGB Videos Using Superquadrics","created":"2025-01-13","cited_by_count":2,"area":null},{"id":"2107.05319","title":"Human-like Relational Models for Activity Recognition in Video","created":"2021-07-12","cited_by_count":1,"area":null},{"id":"2110.13280","title":"A Variational Graph Autoencoder for Manipulation Action Recognition and Prediction","created":"2021-10-25","cited_by_count":1,"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":"2209.13459","title":"EgoSpeed-Net: Forecasting Speed-Control in Driver Behavior from Egocentric Video Data","created":"2022-09-27","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":"2307.08506","title":"Does Visual Pretraining Help End-to-End Reasoning?","created":"2023-07-17","cited_by_count":1,"area":"lr"},{"id":"2309.15683","title":"End-to-End Streaming Video Temporal Action Segmentation with Reinforce Learning","created":"2023-09-27","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":"2508.00085","title":"Punching Bag vs. Punching Person: Motion Transferability in Videos","created":"2025-07-31","cited_by_count":1,"area":null},{"id":"2509.20899","title":"Concepts in Motion: Temporal Concept Bottleneck Model for Interpretable Video Classification","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2509.21783","title":"Prompt-guided Disentangled Representation for Action Recognition","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2601.03667","title":"TRec: Learning Hand-Object Interactions through 2D Point Track Motion","created":"2026-01-07","cited_by_count":1,"area":null},{"id":"2601.11990","title":"DAOS: A Multimodal In-cabin Behavior Monitoring with Driver Action-Object Synergy Dataset","created":"2026-01-17","cited_by_count":1,"area":null},{"id":"2605.31115","title":"Polyphony: Diffusion-based Dual-Hand Action Segmentation with Alternating Vision Transformer and Semantic Conditioning","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2607.01117","title":"MoHallBench: A Benchmark for Motion Hallucination in Video Large Language Models","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2608.10765","title":"Compositional Benchmark Synthesis for Hierarchical Human Action Recognition","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2610.00064","title":"Reachability Is Not Generalization: Understanding Verb--Noun Decomposition in Assembly Action Recognition","created":"2026-09-04","cited_by_count":1,"area":null},{"id":"2108.05331","title":"Two is a crowd: tracking relations in videos","created":"2021-08-11","cited_by_count":0,"area":null},{"id":"2112.04710","title":"Auto-X3D: Ultra-Efficient Video Understanding via Finer-Grained Neural Architecture Search","created":"2021-12-09","cited_by_count":0,"area":null}],"next_cursor":"100"}