{"total":86,"rows":[{"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":"2203.14712","title":"Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities","created":"2022-03-28","cited_by_count":287,"area":null},{"id":"2306.16940","title":"BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion","created":"2023-06-29","cited_by_count":236,"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":"2210.10352","title":"Temporal Action Segmentation: An Analysis of Modern Techniques","created":"2022-10-19","cited_by_count":85,"area":null},{"id":"2204.11134","title":"Can Foundation Models Perform Zero-Shot Task Specification For Robot Manipulation?","created":"2022-04-23","cited_by_count":70,"area":null},{"id":"2407.07532","title":"Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation","created":"2024-07-10","cited_by_count":59,"area":null},{"id":"2212.14474","title":"Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton Formats","created":"2022-12-29","cited_by_count":50,"area":null},{"id":"2103.17260","title":"Learning by Aligning Videos in Time","created":"2021-03-31","cited_by_count":48,"area":null},{"id":"2310.17323","title":"IndustReal: A Dataset for Procedure Step Recognition Handling Execution Errors in Egocentric Videos in an Industrial-Like Setting","created":"2023-10-26","cited_by_count":48,"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":"2106.08827","title":"JRDB-Act: A Large-scale Dataset for Spatio-temporal Action, Social Group and Activity Detection","created":"2021-06-16","cited_by_count":39,"area":null},{"id":"2404.01933","title":"PREGO: online mistake detection in PRocedural EGOcentric videos","created":"2024-04-02","cited_by_count":39,"area":null},{"id":"2109.01305","title":"Video Pose Distillation for Few-Shot, Fine-Grained Sports Action Recognition","created":"2021-09-03","cited_by_count":29,"area":null},{"id":"2303.13519","title":"Learning and Verification of Task Structure in Instructional Videos","created":"2023-03-23","cited_by_count":26,"area":null},{"id":"2111.09301","title":"Learning to Align Sequential Actions in the Wild","created":"2021-11-17","cited_by_count":20,"area":null},{"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":"2307.05721","title":"HA-ViD: A Human Assembly Video Dataset for Comprehensive Assembly Knowledge Understanding","created":"2023-07-09","cited_by_count":18,"area":null},{"id":"2307.16453","title":"Every Mistake Counts in Assembly","created":"2023-07-31","cited_by_count":18,"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":"2301.00794","title":"STEPs: Self-Supervised Key Step Extraction and Localization from Unlabeled Procedural Videos","created":"2023-01-02","cited_by_count":13,"area":null},{"id":"2503.18359","title":"Context-Enhanced Memory-Refined Transformer for Online Action Detection","created":"2025-03-24","cited_by_count":13,"area":null},{"id":"2203.13309","title":"Weakly-Supervised Online Action Segmentation in Multi-View Instructional Videos","created":"2022-03-24","cited_by_count":12,"area":null},{"id":"2411.11409","title":"IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos","created":"2024-11-18","cited_by_count":12,"area":null},{"id":"2204.12223","title":"Context-Aware Sequence Alignment using 4D Skeletal Augmentation","created":"2022-04-26","cited_by_count":11,"area":null},{"id":"2212.11152","title":"OpenPack: A Large-scale Dataset for Recognizing Packaging Works in IoT-enabled Logistic Environments","created":"2022-12-10","cited_by_count":11,"area":null},{"id":"2307.03353","title":"A Survey of Deep Learning in Sports Applications: Perception, Comprehension, and Decision","created":"2023-07-07","cited_by_count":11,"area":null},{"id":"2503.16832","title":"Joint Self-Supervised Video Alignment and Action Segmentation","created":"2025-03-21","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":"2303.06346","title":"3DInAction: Understanding Human Actions in 3D Point Clouds","created":"2023-03-11","cited_by_count":10,"area":null},{"id":"2303.12370","title":"Weakly Supervised Video Representation Learning with Unaligned Text for Sequential Videos","created":"2023-03-22","cited_by_count":10,"area":null},{"id":"2303.13800","title":"Aligning Step-by-Step Instructional Diagrams to Video Demonstrations","created":"2023-03-24","cited_by_count":10,"area":null},{"id":"2309.09181","title":"From Cooking Recipes to Robot Task Trees -- Improving Planning Correctness and Task Efficiency by Leveraging LLMs with a Knowledge Network","created":"2023-09-17","cited_by_count":9,"area":null},{"id":"2410.14770","title":"A Survey on Computational Solutions for Reconstructing Complete Objects by Reassembling Their Fractured Parts","created":"2024-10-18","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":"2604.10409","title":"IMPACT: A Dataset for Multi-Granularity Human Procedural Action Understanding in Industrial Assembly","created":"2026-04-12","cited_by_count":8,"area":null},{"id":"2408.16638","title":"3D Pose-Based Temporal Action Segmentation for Figure Skating: A Fine-Grained and Jump Procedure-Aware Annotation Approach","created":"2024-08-29","cited_by_count":7,"area":null},{"id":"2410.07912","title":"Understanding Spatio-Temporal Relations in Human-Object Interaction using Pyramid Graph Convolutional Network","created":"2024-10-10","cited_by_count":7,"area":null},{"id":"2411.18011","title":"Manual-PA: Learning 3D Part Assembly from Instruction Diagrams","created":"2024-11-27","cited_by_count":7,"area":null},{"id":"2111.08614","title":"IKEA Object State Dataset: A 6DoF object pose estimation dataset and benchmark for multi-state assembly objects","created":"2021-11-16","cited_by_count":6,"area":null},{"id":"2306.05844","title":"How Object Information Improves Skeleton-based Human Action Recognition in Assembly Tasks","created":"2023-06-09","cited_by_count":6,"area":null},{"id":"2311.00556","title":"ProBio: A Protocol-guided Multimodal Dataset for Molecular Biology Lab","created":"2023-11-01","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":"2506.00915","title":"3D Skeleton-Based Action Recognition: A Review","created":"2025-06-01","cited_by_count":6,"area":null},{"id":"2211.14309","title":"FutureHuman3D: Forecasting Complex Long-Term 3D Human Behavior from Video Observations","created":"2022-11-25","cited_by_count":5,"area":null},{"id":"2311.06231","title":"Learning Human Action Recognition Representations Without Real Humans","created":"2023-11-10","cited_by_count":5,"area":null},{"id":"2509.02949","title":"ProMQA-Assembly: Multimodal Procedural QA Dataset on Assembly","created":"2025-09-03","cited_by_count":5,"area":null},{"id":"2407.12066","title":"Temporally Grounding Instructional Diagrams in Unconstrained Videos","created":"2024-07-16","cited_by_count":4,"area":null},{"id":"2410.21275","title":"Enhancing Action Recognition by Leveraging the Hierarchical Structure of Actions and Textual Context","created":"2024-10-28","cited_by_count":4,"area":null},{"id":"2512.02846","title":"Action Anticipation at a Glimpse: To What Extent Can Multimodal Cues Replace Video?","created":"2025-12-02","cited_by_count":4,"area":null},{"id":"2305.19480","title":"Learning by Aligning 2D Skeleton Sequences and Multi-Modality Fusion","created":"2023-05-31","cited_by_count":3,"area":null},{"id":"2408.02272","title":"COM Kitchens: An Unedited Overhead-view Video Dataset as a Vision-Language Benchmark","created":"2024-08-05","cited_by_count":3,"area":null},{"id":"2410.07917","title":"Understanding Human Activity with Uncertainty Measure for Novelty in Graph Convolutional Networks","created":"2024-10-10","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":"2510.12385","title":"Learning to Recognize Correctly Completed Procedure Steps in Egocentric Assembly Videos through Spatio-Temporal Modeling","created":"2025-10-14","cited_by_count":3,"area":null},{"id":"2407.15605","title":"Probing Fine-Grained Action Understanding and Cross-View Generalization of Foundation Models","created":"2024-07-22","cited_by_count":2,"area":null},{"id":"2503.18637","title":"Unbiasing through Textual Descriptions: Mitigating Representation Bias in Video Benchmarks","created":"2025-03-24","cited_by_count":2,"area":null},{"id":"2504.05700","title":"Pose-Aware Weakly-Supervised Action Segmentation","created":"2025-04-08","cited_by_count":2,"area":null},{"id":"2601.22039","title":"Understanding Multimodal Complementarity for Single-Frame Action Anticipation","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2602.18977","title":"Frame2Freq: Spectral Adapters for Fine-Grained Video Understanding","created":"2026-02-21","cited_by_count":2,"area":null},{"id":"2603.02390","title":"OpenMarcie: Dataset for Multimodal Action Recognition in Industrial Environments","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2603.09741","title":"ENIGMA-360: An Ego-Exo Dataset for Human Behavior Understanding in Industrial Scenarios","created":"2026-03-10","cited_by_count":2,"area":null},{"id":"2605.12845","title":"AssemblyBench: Physics-Aware Assembly of Complex Industrial Objects","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2605.26241","title":"RoMo: A Large-Scale, Richly Organized Dataset and Semantic Taxonomy for Human Motion Generation","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2304.03771","title":"Motion Capture Benchmark of Real Industrial Tasks and Traditional Crafts for Human Movement Analysis","created":"2023-04-03","cited_by_count":1,"area":null},{"id":"2304.08840","title":"GoferBot: A Visual Guided Human-Robot Collaborative Assembly System","created":"2023-04-18","cited_by_count":1,"area":null},{"id":"2307.09238","title":"Fusing Hand and Body Skeletons for Human Action Recognition in Assembly","created":"2023-07-18","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":"2507.00756","title":"Towards Open-World Human Action Segmentation Using Graph Convolutional Networks","created":"2025-07-01","cited_by_count":1,"area":null},{"id":"2509.23888","title":"AssemblyHands-X: Modeling 3D Hand-Body Coordination for Understanding Bimanual Human Activities","created":"2025-09-28","cited_by_count":1,"area":null},{"id":"2510.09731","title":"Multi Camera Connected Vision System with Multi View Analytics: A Comprehensive Survey","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2606.27593","title":"Odyssey: Constructing Verifiable Local Truth-Preserving Foundation Models","created":"2026-06-25","cited_by_count":1,"area":null},{"id":"2409.11671","title":"Anticipating Oblivious Opponents in Stochastic Games","created":"2024-09-18","cited_by_count":0,"area":null},{"id":"2501.12318","title":"BlanketGen2-Fit3D: Synthetic Blanket Augmentation Towards Improving Real-World In-Bed Blanket Occluded Human Pose Estimation","created":"2025-01-21","cited_by_count":0,"area":null},{"id":"2503.12519","title":"Multi Activity Sequence Alignment via Implicit Clustering","created":"2025-03-16","cited_by_count":0,"area":null},{"id":"2504.02512","title":"Towards Generalizing Temporal Action Segmentation to Unseen Views","created":"2025-04-03","cited_by_count":0,"area":null},{"id":"2506.18721","title":"Including Semantic Information via Word Embeddings for Skeleton-based Action Recognition","created":"2025-06-23","cited_by_count":0,"area":null},{"id":"2507.07519","title":"MUVOD: A Novel Multi-view Video Object Segmentation Dataset and A Benchmark for 3D Segmentation","created":"2025-07-10","cited_by_count":0,"area":null},{"id":"2508.03039","title":"VideoForest: Person-Anchored Hierarchical Reasoning for Cross-Video Question Answering","created":"2025-08-05","cited_by_count":0,"area":null},{"id":"2508.10281","title":"VIFSS: View-Invariant and Figure Skating-Specific Pose Representation Learning for Temporal Action Segmentation","created":"2025-08-14","cited_by_count":0,"area":null},{"id":"2508.17025","title":"Probabilistic Temporal Masked Attention for Cross-view Online Action Detection","created":"2025-08-23","cited_by_count":0,"area":null},{"id":"2601.20661","title":"ProSkill: Segment-Level Skill Assessment in Procedural Videos","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2605.14843","title":"MechVerse: Evaluating Physical Motion Consistency in Video Generation Models","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.22231","title":"REACH: Hand Pose Estimation from Room Corners","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2607.27729","title":"PrintAnything: Learning an Intermediate Representation for 3D printing G-code Generation","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2609.32592","title":"SPACE: Sparse Predictive Attractor via Counterfactual Eviction for Streaming Video Memory","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}