{"list":"other","total":85,"rows":[{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"id":"1502.02791","title":"Learning Transferable Features with Deep Adaptation Networks","created":"2015-02-10","cited_by_count":1329},{"id":"1801.07455","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2018-01-23","cited_by_count":1209},{"id":"1607.08022","title":"Instance Normalization: The Missing Ingredient for Fast Stylization","created":"2016-07-27","cited_by_count":1198},{"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":"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":"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":"2104.11181","title":"H2O: Two Hands Manipulating Objects for First Person Interaction Recognition","created":"2021-04-22","cited_by_count":254},{"id":"1704.02463","title":"First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations","created":"2017-04-08","cited_by_count":230},{"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":"1507.06228","title":"Training Very Deep Networks","created":"2015-07-22","cited_by_count":173},{"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":"1607.02643","title":"Hierarchical Deep Temporal Models for Group Activity Recognition","created":"2016-07-09","cited_by_count":89},{"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":"2003.12737","title":"Actor-Transformers for Group Activity Recognition","created":"2020-03-28","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":"1904.10117","title":"Learning Actor Relation Graphs for Group Activity Recognition","created":"2019-04-23","cited_by_count":83},{"id":"2205.09443","title":"PYSKL: Towards Good Practices for Skeleton Action Recognition","created":"2022-05-19","cited_by_count":83},{"id":"2105.08825","title":"Multi-Person Extreme Motion Prediction","created":"2021-05-18","cited_by_count":75},{"id":"2304.12301","title":"AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation","created":"2023-04-24","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":"2303.02936","title":"UniHCP: A Unified Model for Human-Centric Perceptions","created":"2023-03-06","cited_by_count":59},{"id":"2108.12630","title":"GroupFormer: Group Activity Recognition with Clustered Spatial-Temporal Transformer","created":"2021-08-28","cited_by_count":54},{"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":"2108.11743","title":"Spatio-Temporal Dynamic Inference Network for Group Activity Recognition","created":"2021-08-26","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":"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":"1904.03308","title":"Convolutional Relational Machine for Group Activity Recognition","created":"2019-04-05","cited_by_count":34},{"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":"2204.02148","title":"Dual-AI: Dual-path Actor Interaction Learning for Group Activity Recognition","created":"2022-04-05","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":"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":"2207.05254","title":"Hunting Group Clues with Transformers for Social Group Activity Recognition","created":"2022-07-12","cited_by_count":22},{"id":"2209.00065","title":"ViA: View-invariant Skeleton Action Representation Learning via Motion Retargeting","created":"2022-08-31","cited_by_count":22},{"id":"2112.05892","title":"COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modality","created":"2021-12-11","cited_by_count":19},{"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":"2110.13385","title":"IIP-Transformer: Intra-Inter-Part Transformer for Skeleton-Based Action Recognition","created":"2021-10-26","cited_by_count":17},{"id":"2301.10900","title":"Graph Contrastive Learning for Skeleton-based Action Recognition","created":"2023-01-26","cited_by_count":17},{"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":"2108.04186","title":"Pose is all you need: The pose only group activity recognition system (POGARS)","created":"2021-08-09","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":"2411.01796","title":"Constrained Human-AI Cooperation: An Inclusive Embodied Social Intelligence Challenge","created":"2024-11-04","cited_by_count":13},{"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":"2308.08529","title":"Diagnosing Human-object Interaction Detectors","created":"2023-08-16","cited_by_count":11},{"id":"2407.14744","title":"A Comprehensive Review of Few-shot Action Recognition","created":"2024-07-20","cited_by_count":11},{"id":"2411.14796","title":"Adaptive Hyper-Graph Convolution Network for Skeleton-based Human Action Recognition with Virtual Connections","created":"2024-11-22","cited_by_count":11},{"id":"2508.12586","title":"Foundation Model for Skeleton-Based Human Action Understanding","created":"2025-08-18","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":"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":"2306.16772","title":"M3Act: Learning from Synthetic Human Group Activities","created":"2023-06-29","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":"2407.12312","title":"Shap-Mix: Shapley Value Guided Mixing for Long-Tailed Skeleton Based Action Recognition","created":"2024-07-17","cited_by_count":5},{"id":"2505.10679","title":"Are Spatial-Temporal Graph Convolution Networks for Human Action Recognition Over-Parameterized?","created":"2025-05-15","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},{"id":"2410.23641","title":"Recovering Complete Actions for Cross-dataset Skeleton Action Recognition","created":"2024-10-31","cited_by_count":2},{"id":"2310.06437","title":"Skeleton Ground Truth Extraction: Methodology, Annotation Tool and Benchmarks","created":"2023-10-10","cited_by_count":1},{"id":"2404.09964","title":"Design and Analysis of Efficient Attention in Transformers for Social Group Activity Recognition","created":"2024-04-15","cited_by_count":1},{"id":"2507.03936","title":"Learning Adaptive Node Selection with External Attention for Human Interaction Recognition","created":"2025-07-05","cited_by_count":1}],"next_cursor":null}