{"list":"other","total":132,"rows":[{"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":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1708.04896","title":"Random Erasing Data Augmentation","created":"2017-08-16","cited_by_count":1239},{"id":"1801.07455","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2018-01-23","cited_by_count":1209},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"1901.11196","title":"EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks","created":"2019-01-31","cited_by_count":807},{"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":"1811.05320","title":"T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Prediction","created":"2018-11-12","cited_by_count":401},{"id":"1604.06573","title":"Convolutional Two-Stream Network Fusion for Video Action Recognition","created":"2016-04-22","cited_by_count":384},{"id":"2107.12213","title":"Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition","created":"2021-07-26","cited_by_count":322},{"id":"1904.12659","title":"Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition","created":"2019-04-26","cited_by_count":228},{"id":"1411.4280","title":"Efficient Object Localization Using Convolutional Networks","created":"2014-11-16","cited_by_count":227},{"id":"1404.4661","title":"Learning Fine-grained Image Similarity with Deep Ranking","created":"2014-04-17","cited_by_count":190},{"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":"1611.06067","title":"An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data","created":"2016-11-18","cited_by_count":126},{"id":"1703.03492","title":"A New Representation of Skeleton Sequences for 3D Action Recognition","created":"2017-03-09","cited_by_count":126},{"id":"1804.06055","title":"Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregation","created":"2018-04-17","cited_by_count":106},{"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":"1912.06971","title":"Skeleton-Based Action Recognition with Multi-Stream Adaptive Graph Convolutional Networks","created":"2019-12-15","cited_by_count":103},{"id":"1703.07475","title":"PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding","created":"2017-03-22","cited_by_count":101},{"id":"2008.07404","title":"Skeleton-based Action Recognition via Spatial and Temporal Transformer Networks","created":"2020-08-17","cited_by_count":98},{"id":"2104.00946","title":"UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles","created":"2021-04-02","cited_by_count":96},{"id":"2204.08610","title":"Image Data Augmentation for Deep Learning: A Survey","created":"2022-04-19","cited_by_count":96},{"id":"2007.00394","title":"The IKEA ASM Dataset: Understanding People Assembling Furniture through Actions, Objects and Pose","created":"2020-07-01","cited_by_count":95},{"id":"1911.12409","title":"PREDICT & CLUSTER: Unsupervised Skeleton Based Action Recognition","created":"2019-11-27","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":"1704.04516","title":"Interpretable 3D Human Action Analysis with Temporal Convolutional Networks","created":"2017-04-14","cited_by_count":89},{"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":"2108.03656","title":"Skeleton-Contrastive 3D Action Representation Learning","created":"2021-08-08","cited_by_count":76},{"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":"2012.11101","title":"ResizeMix: Mixing Data with Preserved Object Information and True Labels","created":"2020-12-21","cited_by_count":69},{"id":"2103.13027","title":"AutoMix: Unveiling the Power of Mixup for Stronger Classifiers","created":"2021-03-24","cited_by_count":69},{"id":"1702.07432","title":"Multi-Context Attention for Human Pose Estimation","created":"2017-02-24","cited_by_count":66},{"id":"2203.16051","title":"Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Prediction","created":"2022-03-30","cited_by_count":66},{"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":"2008.00188","title":"Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM for Unsupervised Action Recognition","created":"2020-08-01","cited_by_count":60},{"id":"1704.07595","title":"Skeleton-based Action Recognition with Convolutional Neural Networks","created":"2017-04-25","cited_by_count":54},{"id":"1706.08276","title":"Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates","created":"2017-06-26","cited_by_count":54},{"id":"1910.02212","title":"Symbiotic Graph Neural Networks for 3D Skeleton-based Human Action Recognition and Motion Prediction","created":"2019-10-05","cited_by_count":50},{"id":"1704.02581","title":"Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks","created":"2017-04-09","cited_by_count":49},{"id":"1805.02335","title":"Skeleton-Based Action Recognition with Spatial Reasoning and Temporal Stack Learning","created":"2018-05-07","cited_by_count":47},{"id":"2002.05907","title":"A Survey on 3D Skeleton-Based Action Recognition Using Learning Method","created":"2020-02-14","cited_by_count":47},{"id":"2403.09508","title":"SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition","created":"2024-03-14","cited_by_count":47},{"id":"2303.06242","title":"HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations","created":"2023-03-10","cited_by_count":44},{"id":"1907.13025","title":"SkeleMotion: A New Representation of Skeleton Joint Sequences Based on Motion Information for 3D Action Recognition","created":"2019-07-30","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":"1612.05877","title":"Deep Learning on Lie Groups for Skeleton-based Action Recognition","created":"2016-12-18","cited_by_count":42},{"id":"1805.02513","title":"Long-Term Human Motion Prediction by Modeling Motion Context and Enhancing Motion Dynamic","created":"2018-05-07","cited_by_count":41},{"id":"2303.14474","title":"3Mformer: Multi-order Multi-mode Transformer for Skeletal Action Recognition","created":"2023-03-25","cited_by_count":40},{"id":"1504.06678","title":"Differential Recurrent Neural Networks for Action Recognition","created":"2015-04-25","cited_by_count":39},{"id":"2404.00532","title":"LLMs are Good Action Recognizers","created":"2024-03-31","cited_by_count":37},{"id":"1804.08254","title":"Memory Attention Networks for Skeleton-based Action Recognition","created":"2018-04-23","cited_by_count":36},{"id":"2211.09590","title":"Hypergraph Transformer for Skeleton-based Action Recognition","created":"2022-11-17","cited_by_count":36},{"id":"1611.02447","title":"Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networks","created":"2016-11-08","cited_by_count":32},{"id":"1911.00029","title":"Chirality Nets for Human Pose Regression","created":"2019-10-31","cited_by_count":31},{"id":"2207.12100","title":"IGFormer: Interaction Graph Transformer for Skeleton-based Human Interaction Recognition","created":"2022-07-25","cited_by_count":31},{"id":"2211.13466","title":"Hierarchical Consistent Contrastive Learning for Skeleton-Based Action Recognition with Growing Augmentations","created":"2022-11-24","cited_by_count":31},{"id":"2207.09644","title":"Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learning","created":"2022-07-20","cited_by_count":30},{"id":"2212.02082","title":"Hierarchical Contrast for Unsupervised Skeleton-based Action Representation Learning","created":"2022-12-05","cited_by_count":30},{"id":"1906.09955","title":"A Comparative Review of Recent Kinect-based Action Recognition Algorithms","created":"2019-06-24","cited_by_count":29},{"id":"1409.6813","title":"Histogram of Oriented Principal Components for Cross-View Action Recognition","created":"2014-09-24","cited_by_count":27},{"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":"2003.01920","title":"ETRI-Activity3D: A Large-Scale RGB-D Dataset for Robots to Recognize Daily Activities of the Elderly","created":"2020-03-04","cited_by_count":26},{"id":"2205.15608","title":"Weakly-supervised Action Transition Learning for Stochastic Human Motion Prediction","created":"2022-05-31","cited_by_count":26},{"id":"1909.05704","title":"Skeleton Image Representation for 3D Action Recognition based on Tree Structure and Reference Joints","created":"2019-09-11","cited_by_count":25},{"id":"2108.04536","title":"Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition","created":"2021-08-10","cited_by_count":25},{"id":"2302.09018","title":"Self-supervised Action Representation Learning from Partial Spatio-Temporal Skeleton Sequences","created":"2023-02-17","cited_by_count":25},{"id":"2304.00387","title":"HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of Actions","created":"2023-04-01","cited_by_count":25},{"id":"2308.03950","title":"Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximization","created":"2023-08-07","cited_by_count":24},{"id":"1705.08106","title":"Two-Stream 3D Convolutional Neural Network for Skeleton-Based Action Recognition","created":"2017-05-23","cited_by_count":23},{"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":"2210.16820","title":"Temporal-Viewpoint Transportation Plan for Skeletal Few-shot Action Recognition","created":"2022-10-30","cited_by_count":22},{"id":"2305.00666","title":"Part Aware Contrastive Learning for Self-Supervised Action Recognition","created":"2023-05-01","cited_by_count":21},{"id":"2212.05638","title":"Cross-Modal Learning with 3D Deformable Attention for Action Recognition","created":"2022-12-12","cited_by_count":20},{"id":"2111.11051","title":"Contrast-reconstruction Representation Learning for Self-supervised Skeleton-based Action Recognition","created":"2021-11-22","cited_by_count":19},{"id":"2308.03975","title":"Prompted Contrast with Masked Motion Modeling: Towards Versatile 3D Action Representation Learning","created":"2023-08-08","cited_by_count":19},{"id":"2407.13460","title":"SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by Disentangled Variational Autoencoders","created":"2024-07-18","cited_by_count":19},{"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":"2201.02849","title":"Spatio-Temporal Tuples Transformer for Skeleton-Based Action Recognition","created":"2022-01-08","cited_by_count":17}],"next_cursor":"100"}