{"list":"other","total":149,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1706.02413","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","created":"2017-06-07","cited_by_count":4401},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"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":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"1801.07455","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2018-01-23","cited_by_count":1209},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"2012.00364","title":"Pre-Trained Image Processing Transformer","created":"2020-12-01","cited_by_count":893},{"id":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"id":"2111.11432","title":"Florence: A New Foundation Model for Computer Vision","created":"2021-11-22","cited_by_count":804},{"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":"2012.12556","title":"A Survey on Visual Transformer","created":"2020-12-23","cited_by_count":654},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"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":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"1411.4389","title":"Long-term Recurrent Convolutional Networks for Visual Recognition and Description","created":"2014-11-17","cited_by_count":484},{"id":"2011.14503","title":"End-to-End Video Instance Segmentation with Transformers","created":"2020-11-30","cited_by_count":443},{"id":"1711.10305","title":"Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks","created":"2017-11-28","cited_by_count":387},{"id":"1909.05840","title":"Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT","created":"2019-09-12","cited_by_count":359},{"id":"1905.12681","title":"What Makes Training Multi-Modal Classification Networks Hard?","created":"2019-05-29","cited_by_count":344},{"id":"2003.14111","title":"Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition","created":"2020-03-31","cited_by_count":343},{"id":"1808.01340","title":"A Short Note about Kinetics-600","created":"2018-08-03","cited_by_count":333},{"id":"2107.12213","title":"Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition","created":"2021-07-26","cited_by_count":322},{"id":"1812.02707","title":"Video Action Transformer Network","created":"2018-12-06","cited_by_count":316},{"id":"1911.03584","title":"On the Relationship between Self-Attention and Convolutional Layers","created":"2019-11-08","cited_by_count":300},{"id":"2102.00719","title":"Video Transformer Network","created":"2021-02-01","cited_by_count":272},{"id":"2104.13586","title":"Revisiting Skeleton-based Action Recognition","created":"2021-04-28","cited_by_count":257},{"id":"1503.08909","title":"Beyond Short Snippets: Deep Networks for Video Classification","created":"2015-03-31","cited_by_count":233},{"id":"1806.11230","title":"Human Action Recognition and Prediction: A Survey","created":"2018-06-28","cited_by_count":227},{"id":"1806.00187","title":"Scaling Neural Machine Translation","created":"2018-06-01","cited_by_count":204},{"id":"2012.11866","title":"Human Action Recognition from Various Data Modalities: A Review","created":"2020-12-22","cited_by_count":163},{"id":"2201.04288","title":"Multiview Transformers for Video Recognition","created":"2022-01-12","cited_by_count":148},{"id":"1607.07043","title":"Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition","created":"2016-07-24","cited_by_count":143},{"id":"1901.03429","title":"On the Turing Completeness of Modern Neural Network Architectures","created":"2019-01-10","cited_by_count":129},{"id":"2106.11297","title":"TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?","created":"2021-06-21","cited_by_count":127},{"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":"2001.07416","title":"Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunities","created":"2020-01-21","cited_by_count":126},{"id":"2002.02925","title":"BERT-of-Theseus: Compressing BERT by Progressive Module Replacing","created":"2020-02-07","cited_by_count":113},{"id":"1912.06971","title":"Skeleton-Based Action Recognition with Multi-Stream Adaptive Graph Convolutional Networks","created":"2019-12-15","cited_by_count":103},{"id":"2008.07404","title":"Skeleton-based Action Recognition via Spatial and Temporal Transformer Networks","created":"2020-08-17","cited_by_count":98},{"id":"2010.10864","title":"A Short Note on the Kinetics-700-2020 Human Action Dataset","created":"2020-10-21","cited_by_count":92},{"id":"1803.00455","title":"LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Images","created":"2018-03-01","cited_by_count":88},{"id":"2012.06567","title":"A Comprehensive Study of Deep Video Action Recognition","created":"2020-12-11","cited_by_count":88},{"id":"1604.04494","title":"Long-term Temporal Convolutions for Action Recognition","created":"2016-04-15","cited_by_count":84},{"id":"1806.07110","title":"Modality Distillation with Multiple Stream Networks for Action Recognition","created":"2018-06-19","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":"2012.06399","title":"Spatial Temporal Transformer Network for Skeleton-based Action Recognition","created":"2020-12-11","cited_by_count":77},{"id":"1704.02895","title":"ActionVLAD: Learning spatio-temporal aggregation for action classification","created":"2017-04-10","cited_by_count":73},{"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":"1607.01794","title":"VideoLSTM Convolves, Attends and Flows for Action Recognition","created":"2016-07-06","cited_by_count":60},{"id":"1505.04868","title":"Action Recognition with Trajectory-Pooled Deep-Convolutional Descriptors","created":"2015-05-19","cited_by_count":58},{"id":"2007.03056","title":"VPN: Learning Video-Pose Embedding for Activities of Daily Living","created":"2020-07-06","cited_by_count":57},{"id":"1711.01467","title":"Attentional Pooling for Action Recognition","created":"2017-11-04","cited_by_count":54},{"id":"2102.02751","title":"Semi-Supervised Action Recognition with Temporal Contrastive Learning","created":"2021-02-04","cited_by_count":50},{"id":"1511.04119","title":"Action Recognition using Visual Attention","created":"2015-11-12","cited_by_count":49},{"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":"2002.05907","title":"A Survey on 3D Skeleton-Based Action Recognition Using Learning Method","created":"2020-02-14","cited_by_count":47},{"id":"2108.09322","title":"MM-ViT: Multi-Modal Video Transformer for Compressed Video Action Recognition","created":"2021-08-20","cited_by_count":46},{"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":"2005.05501","title":"3DV: 3D Dynamic Voxel for Action Recognition in Depth Video","created":"2020-05-12","cited_by_count":41},{"id":"2112.07175","title":"Co-training Transformer with Videos and Images Improves Action Recognition","created":"2021-12-14","cited_by_count":41},{"id":"1504.06678","title":"Differential Recurrent Neural Networks for Action Recognition","created":"2015-04-25","cited_by_count":39},{"id":"2101.03904","title":"Trear: Transformer-based RGB-D Egocentric Action Recognition","created":"2021-01-05","cited_by_count":39},{"id":"1711.08362","title":"RGB-D-based Human Motion Recognition with Deep Learning: A Survey","created":"2017-10-31","cited_by_count":37},{"id":"2105.08141","title":"VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living","created":"2021-05-17","cited_by_count":35},{"id":"2107.08580","title":"UNIK: A Unified Framework for Real-world Skeleton-based Action Recognition","created":"2021-07-19","cited_by_count":35}],"next_cursor":"100"}