{"list":"other","total":58,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"1801.07455","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2018-01-23","cited_by_count":1209},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"1906.02629","title":"When Does Label Smoothing Help?","created":"2019-06-06","cited_by_count":988},{"id":"1709.02371","title":"PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume","created":"2017-09-07","cited_by_count":968},{"id":"1612.01925","title":"FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks","created":"2016-12-06","cited_by_count":784},{"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":"2204.01697","title":"MaxViT: Multi-Axis Vision Transformer","created":"2022-04-04","cited_by_count":476},{"id":"1905.11881","title":"Why gradient clipping accelerates training: A theoretical justification for adaptivity","created":"2019-05-28","cited_by_count":341},{"id":"2107.12213","title":"Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition","created":"2021-07-26","cited_by_count":322},{"id":"2201.02973","title":"MAXIM: Multi-Axis MLP for Image Processing","created":"2022-01-09","cited_by_count":302},{"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":"1904.12659","title":"Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition","created":"2019-04-26","cited_by_count":228},{"id":"2012.11866","title":"Human Action Recognition from Various Data Modalities: A Review","created":"2020-12-22","cited_by_count":163},{"id":"1902.09130","title":"An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition","created":"2019-02-25","cited_by_count":151},{"id":"1607.07043","title":"Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition","created":"2016-07-24","cited_by_count":143},{"id":"1803.04831","title":"Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN","created":"2018-03-13","cited_by_count":143},{"id":"1904.01189","title":"Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition","created":"2019-04-02","cited_by_count":135},{"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":"2008.07404","title":"Skeleton-based Action Recognition via Spatial and Temporal Transformer Networks","created":"2020-08-17","cited_by_count":98},{"id":"2010.09978","title":"Stronger, Faster and More Explainable: A Graph Convolutional Baseline for Skeleton-based Action Recognition","created":"2020-10-20","cited_by_count":91},{"id":"2112.03590","title":"Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition","created":"2021-12-07","cited_by_count":90},{"id":"2106.15125","title":"Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition","created":"2021-06-29","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":"2205.09443","title":"PYSKL: Towards Good Practices for Skeleton Action Recognition","created":"2022-05-19","cited_by_count":83},{"id":"2007.14690","title":"Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action Recognition","created":"2020-07-29","cited_by_count":82},{"id":"2206.13028","title":"Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition","created":"2022-06-27","cited_by_count":71},{"id":"1911.04131","title":"Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching","created":"2019-11-11","cited_by_count":70},{"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":"2108.07181","title":"Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation","created":"2021-08-16","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":"2208.05318","title":"Generative Action Description Prompts for Skeleton-based Action Recognition","created":"2022-08-10","cited_by_count":43},{"id":"2303.10904","title":"Actionlet-Dependent Contrastive Learning for Unsupervised Skeleton-Based Action Recognition","created":"2023-03-20","cited_by_count":42},{"id":"2303.14474","title":"3Mformer: Multi-order Multi-mode Transformer for Skeletal Action Recognition","created":"2023-03-25","cited_by_count":40},{"id":"1611.02447","title":"Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networks","created":"2016-11-08","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":"1906.09955","title":"A Comparative Review of Recent Kinect-based Action Recognition Algorithms","created":"2019-06-24","cited_by_count":29},{"id":"2112.04178","title":"Topology-aware Convolutional Neural Network for Efficient Skeleton-based Action Recognition","created":"2021-12-08","cited_by_count":29},{"id":"1910.04963","title":"Interaction Relational Network for Mutual Action Recognition","created":"2019-10-11","cited_by_count":27},{"id":"1704.05645","title":"Skeleton based action recognition using translation-scale invariant image mapping and multi-scale deep cnn","created":"2017-04-19","cited_by_count":26},{"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":"2210.02693","title":"Focal and Global Spatial-Temporal Transformer for Skeleton-based Action Recognition","created":"2022-10-06","cited_by_count":18},{"id":"2110.13385","title":"IIP-Transformer: Intra-Inter-Part Transformer for Skeleton-Based Action Recognition","created":"2021-10-26","cited_by_count":17},{"id":"2212.04761","title":"Leveraging Spatio-Temporal Dependency for Skeleton-Based Action Recognition","created":"2022-12-09","cited_by_count":13},{"id":"1705.00835","title":"Investigation of Different Skeleton Features for CNN-based 3D Action Recognition","created":"2017-05-02","cited_by_count":12},{"id":"1801.02475","title":"Ensemble One-dimensional Convolution Neural Networks for Skeleton-based Action Recognition","created":"2018-01-08","cited_by_count":10},{"id":"2308.07571","title":"Ske2Grid: Skeleton-to-Grid Representation Learning for Action Recognition","created":"2023-08-15","cited_by_count":7}],"next_cursor":null}