{"list":"other","total":55,"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":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"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":"2103.14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","created":"2021-03-27","cited_by_count":806},{"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":"2112.09133","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","created":"2021-12-16","cited_by_count":576},{"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":"2104.11178","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","created":"2021-04-22","cited_by_count":429},{"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":"1908.08593","title":"Revealing the Dark Secrets of BERT","created":"2019-08-21","cited_by_count":301},{"id":"2104.13586","title":"Revisiting Skeleton-based Action Recognition","created":"2021-04-28","cited_by_count":257},{"id":"1904.12659","title":"Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition","created":"2019-04-26","cited_by_count":228},{"id":"1803.07294","title":"GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs","created":"2018-03-20","cited_by_count":165},{"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":"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":"2008.07404","title":"Skeleton-based Action Recognition via Spatial and Temporal Transformer Networks","created":"2020-08-17","cited_by_count":98},{"id":"2106.05786","title":"CAT: Cross Attention in Vision Transformer","created":"2021-06-10","cited_by_count":92},{"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":"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":"1811.12006","title":"Global Second-order Pooling Convolutional Networks","created":"2018-11-29","cited_by_count":66},{"id":"2112.01514","title":"Self-supervised Video Transformer","created":"2021-12-02","cited_by_count":64},{"id":"1711.01467","title":"Attentional Pooling for Action Recognition","created":"2017-11-04","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":"2212.01026","title":"Spectral Feature Augmentation for Graph Contrastive Learning and Beyond","created":"2022-12-02","cited_by_count":49},{"id":"2206.04726","title":"COSTA: Covariance-Preserving Feature Augmentation for Graph Contrastive Learning","created":"2022-06-09","cited_by_count":39},{"id":"2110.14416","title":"Transformers Generalize DeepSets and Can be Extended to Graphs and Hypergraphs","created":"2021-10-27","cited_by_count":35},{"id":"1512.01848","title":"Rank Pooling for Action Recognition","created":"2015-12-06","cited_by_count":29},{"id":"1906.09955","title":"A Comparative Review of Recent Kinect-based Action Recognition Algorithms","created":"2019-06-24","cited_by_count":29},{"id":"2012.14371","title":"Tensor Representations for Action Recognition","created":"2020-12-28","cited_by_count":28},{"id":"2012.13975","title":"Power Normalizations in Fine-grained Image, Few-shot Image and Graph Classification","created":"2020-12-27","cited_by_count":27},{"id":"2001.04627","title":"Self-supervising Action Recognition by Statistical Moment and Subspace Descriptors","created":"2020-01-14","cited_by_count":24},{"id":"2201.05493","title":"Contrastive Laplacian Eigenmaps","created":"2022-01-14","cited_by_count":24},{"id":"2105.01563","title":"Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition","created":"2021-05-04","cited_by_count":22},{"id":"2210.16820","title":"Temporal-Viewpoint Transportation Plan for Skeletal Few-shot Action Recognition","created":"2022-10-30","cited_by_count":22},{"id":"2103.11770","title":"AdaSGN: Adapting Joint Number and Model Size for Efficient Skeleton-Based Action Recognition","created":"2021-03-22","cited_by_count":21},{"id":"2211.00005","title":"Uncertainty-DTW for Time Series and Sequences","created":"2022-10-30","cited_by_count":21},{"id":"1906.11465","title":"Loss Switching Fusion with Similarity Search for Video Classification","created":"2019-06-27","cited_by_count":15},{"id":"2110.05216","title":"High-order Tensor Pooling with Attention for Action Recognition","created":"2021-10-11","cited_by_count":14},{"id":"1808.07503","title":"Second-order Democratic Aggregation","created":"2018-08-22","cited_by_count":12},{"id":"2112.12668","title":"3D Skeleton-based Few-shot Action Recognition with JEANIE is not so Na\\\"ive","created":"2021-12-23","cited_by_count":10},{"id":"2210.16897","title":"Time-rEversed diffusioN tEnsor Transformer: A new TENET of Few-Shot Object Detection","created":"2022-10-30","cited_by_count":10},{"id":"2112.08626","title":"Analysis and Evaluation of Kinect-based Action Recognition Algorithms","created":"2021-12-16","cited_by_count":9},{"id":"2112.10570","title":"Dynamic Hypergraph Convolutional Networks for Skeleton-Based Action Recognition","created":"2021-12-20","cited_by_count":9},{"id":"2204.00452","title":"Vision Transformer with Cross-attention by Temporal Shift for Efficient Action Recognition","created":"2022-04-01","cited_by_count":5},{"id":"1701.05432","title":"Higher-order Pooling of CNN Features via Kernel Linearization for Action Recognition","created":"2017-01-19","cited_by_count":4},{"id":"2112.07338","title":"Temporal Transformer Networks with Self-Supervision for Action Recognition","created":"2021-12-14","cited_by_count":2}],"next_cursor":null}