{"list":"other","total":79,"rows":[{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"1801.07455","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2018-01-23","cited_by_count":1209},{"id":"1604.02808","title":"NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis","created":"2016-04-11","cited_by_count":686},{"id":"2006.04131","title":"Deep Graph Contrastive Representation Learning","created":"2020-06-07","cited_by_count":539},{"id":"1905.04757","title":"NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding","created":"2019-05-12","cited_by_count":533},{"id":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528},{"id":"2003.14111","title":"Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition","created":"2020-03-31","cited_by_count":343},{"id":"2107.12213","title":"Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition","created":"2021-07-26","cited_by_count":322},{"id":"2203.14712","title":"Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities","created":"2022-03-28","cited_by_count":287},{"id":"2104.13586","title":"Revisiting Skeleton-based Action Recognition","created":"2021-04-28","cited_by_count":257},{"id":"2104.11181","title":"H2O: Two Hands Manipulating Objects for First Person Interaction Recognition","created":"2021-04-22","cited_by_count":254},{"id":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229},{"id":"1904.12659","title":"Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition","created":"2019-04-26","cited_by_count":228},{"id":"2304.05684","title":"InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions","created":"2023-04-12","cited_by_count":206},{"id":"2210.06551","title":"MotionBERT: A Unified Perspective on Learning Human Motion Representations","created":"2022-10-12","cited_by_count":193},{"id":"1607.07043","title":"Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition","created":"2016-07-24","cited_by_count":143},{"id":"1904.05349","title":"H+O: Unified Egocentric Recognition of 3D Hand-Object Poses and Interactions","created":"2019-04-10","cited_by_count":141},{"id":"2403.08629","title":"Scaling Up Dynamic Human-Scene Interaction Modeling","created":"2024-03-13","cited_by_count":137},{"id":"1405.2941","title":"Cross-view Action Modeling, Learning and Recognition","created":"2014-05-12","cited_by_count":134},{"id":"1703.08274","title":"View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data","created":"2017-03-24","cited_by_count":105},{"id":"2312.16051","title":"Inter-X: Towards Versatile Human-Human Interaction Analysis","created":"2023-12-26","cited_by_count":98},{"id":"2303.17602","title":"Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks","created":"2023-03-30","cited_by_count":96},{"id":"2303.15380","title":"Hi4D: 4D Instance Segmentation of Close Human Interaction","created":"2023-03-27","cited_by_count":87},{"id":"2208.10741","title":"Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2022-08-23","cited_by_count":85},{"id":"1804.07453","title":"View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognition","created":"2018-04-20","cited_by_count":84},{"id":"2308.07123","title":"An Outlook into the Future of Egocentric Vision","created":"2023-08-14","cited_by_count":84},{"id":"2205.09443","title":"PYSKL: Towards Good Practices for Skeleton Action Recognition","created":"2022-05-19","cited_by_count":83},{"id":"1904.09882","title":"You2Me: Inferring Body Pose in Egocentric Video via First and Second Person Interactions","created":"2019-04-22","cited_by_count":82},{"id":"2304.12301","title":"AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation","created":"2023-04-24","cited_by_count":64},{"id":"2409.04431","title":"Theory, Analysis, and Best Practices for Sigmoid Self-Attention","created":"2024-09-06","cited_by_count":64},{"id":"1603.07772","title":"Co-occurrence Feature Learning for Skeleton based Action Recognition using Regularized Deep LSTM Networks","created":"2016-03-24","cited_by_count":63},{"id":"1707.05740","title":"Skeleton-Based Human Action Recognition with Global Context-Aware Attention LSTM Networks","created":"2017-07-18","cited_by_count":62},{"id":"2303.03729","title":"Learning Discriminative Representations for Skeleton Based Action Recognition","created":"2023-03-07","cited_by_count":62},{"id":"2303.02936","title":"UniHCP: A Unified Model for Human-Centric Perceptions","created":"2023-03-06","cited_by_count":59},{"id":"2403.09508","title":"SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition","created":"2024-03-14","cited_by_count":47},{"id":"2208.05318","title":"Generative Action Description Prompts for Skeleton-based Action Recognition","created":"2022-08-10","cited_by_count":43},{"id":"2210.07503","title":"STAR-Transformer: A Spatio-temporal Cross Attention Transformer for Human Action Recognition","created":"2022-10-14","cited_by_count":43},{"id":"2207.01685","title":"Interaction Transformer for Human Reaction Generation","created":"2022-07-04","cited_by_count":42},{"id":"2308.07092","title":"Masked Motion Predictors are Strong 3D Action Representation Learners","created":"2023-08-14","cited_by_count":41},{"id":"2303.05675","title":"HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining","created":"2023-03-10","cited_by_count":38},{"id":"2211.09590","title":"Hypergraph Transformer for Skeleton-based Action Recognition","created":"2022-11-17","cited_by_count":36},{"id":"2105.08141","title":"VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living","created":"2021-05-17","cited_by_count":35},{"id":"2209.09484","title":"Hierarchical Temporal Transformer for 3D Hand Pose Estimation and Action Recognition from Egocentric RGB Videos","created":"2022-09-20","cited_by_count":35},{"id":"2310.20695","title":"HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception","created":"2023-10-31","cited_by_count":33},{"id":"2304.01199","title":"On the Benefits of 3D Pose and Tracking for Human Action Recognition","created":"2023-04-03","cited_by_count":32},{"id":"2207.12100","title":"IGFormer: Interaction Graph Transformer for Skeleton-based Human Interaction Recognition","created":"2022-07-25","cited_by_count":31},{"id":"2310.07189","title":"SpikePoint: An Efficient Point-based Spiking Neural Network for Event Cameras Action Recognition","created":"2023-10-11","cited_by_count":30},{"id":"1910.04963","title":"Interaction Relational Network for Mutual Action Recognition","created":"2019-10-11","cited_by_count":27},{"id":"2305.12398","title":"Language Knowledge-Assisted Representation Learning for Skeleton-Based Action Recognition","created":"2023-05-21","cited_by_count":27},{"id":"2203.13815","title":"Versatile Multi-Modal Pre-Training for Human-Centric Perception","created":"2022-03-25","cited_by_count":26},{"id":"2208.07308","title":"Pose Forecasting in Industrial Human-Robot Collaboration","created":"2022-07-24","cited_by_count":25},{"id":"2307.07469","title":"Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action Recognition","created":"2023-07-14","cited_by_count":23},{"id":"2312.01697","title":"Hulk: A Universal Knowledge Translator for Human-Centric Tasks","created":"2023-12-04","cited_by_count":22},{"id":"1902.03084","title":"Skeleton-Based Online Action Prediction Using Scale Selection Network","created":"2019-02-08","cited_by_count":20},{"id":"2212.05638","title":"Cross-Modal Learning with 3D Deformable Attention for Action Recognition","created":"2022-12-12","cited_by_count":20},{"id":"2311.18840","title":"Just Add $\\pi$! Pose Induced Video Transformers for Understanding Activities of Daily Living","created":"2023-11-30","cited_by_count":19},{"id":"2312.06330","title":"Navigating Open Set Scenarios for Skeleton-based Action Recognition","created":"2023-12-11","cited_by_count":17},{"id":"2403.09805","title":"On the Utility of 3D Hand Poses for Action Recognition","created":"2024-03-14","cited_by_count":17},{"id":"2406.04659","title":"LocLLM: Exploiting Generalizable Human Keypoint Localization via Large Language Model","created":"2024-06-07","cited_by_count":17},{"id":"2304.08799","title":"Self-Supervised 3D Action Representation Learning with Skeleton Cloud Colorization","created":"2023-04-18","cited_by_count":16},{"id":"2208.05775","title":"PSUMNet: Unified Modality Part Streams are All You Need for Efficient Pose-based Action Recognition","created":"2022-08-11","cited_by_count":14},{"id":"2404.04458","title":"JRDB-Social: A Multifaceted Robotic Dataset for Understanding of Context and Dynamics of Human Interactions Within Social Groups","created":"2024-04-06","cited_by_count":13},{"id":"2307.07286","title":"One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matching","created":"2023-07-14","cited_by_count":12},{"id":"2404.09308","title":"In My Perspective, In My Hands: Accurate Egocentric 2D Hand Pose and Action Recognition","created":"2024-04-14","cited_by_count":12},{"id":"2407.15706","title":"Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition","created":"2024-07-22","cited_by_count":12},{"id":"2405.20606","title":"Vision-Language Meets the Skeleton: Progressively Distillation with Cross-Modal Knowledge for 3D Action Representation Learning","created":"2024-05-31","cited_by_count":11},{"id":"2312.03288","title":"STEP CATFormer: Spatial-Temporal Effective Body-Part Cross Attention Transformer for Skeleton-based Action Recognition","created":"2023-12-06","cited_by_count":10},{"id":"2402.04599","title":"Meet JEANIE: a Similarity Measure for 3D Skeleton Sequences via Temporal-Viewpoint Alignment","created":"2024-02-07","cited_by_count":10},{"id":"2211.09146","title":"A Unified Multimodal De- and Re-coupling Framework for RGB-D Motion Recognition","created":"2022-11-16","cited_by_count":9},{"id":"2401.02138","title":"Explore Human Parsing Modality for Action Recognition","created":"2024-01-04","cited_by_count":8},{"id":"2403.12710","title":"Selective, Interpretable, and Motion Consistent Privacy Attribute Obfuscation for Action Recognition","created":"2024-03-19","cited_by_count":8},{"id":"2501.07711","title":"Pedestrian Trajectory Prediction Based on Social Interactions Learning With Random Weights","created":"2025-01-13","cited_by_count":8},{"id":"2205.07611","title":"Noise-Tolerant Learning for Audio-Visual Action Recognition","created":"2022-05-16","cited_by_count":7},{"id":"2403.14447","title":"Exploring 3D Human Pose Estimation and Forecasting from the Robot's Perspective: The HARPER Dataset","created":"2024-03-21","cited_by_count":6},{"id":"2304.11631","title":"TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential","created":"2023-04-23","cited_by_count":5},{"id":"2402.02431","title":"Learning Mutual Excitation for Hand-to-Hand and Human-to-Human Interaction Recognition","created":"2024-02-04","cited_by_count":5},{"id":"2410.07153","title":"CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition","created":"2024-10-09","cited_by_count":3}],"next_cursor":null}