{"list":"other","total":65,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"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":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"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":"1801.07455","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2018-01-23","cited_by_count":1209},{"id":"1511.07122","title":"Multi-Scale Context Aggregation by Dilated Convolutions","created":"2015-11-23","cited_by_count":1133},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"1809.02983","title":"Dual Attention Network for Scene Segmentation","created":"2018-09-09","cited_by_count":1003},{"id":"1805.08318","title":"Self-Attention Generative Adversarial Networks","created":"2018-05-21","cited_by_count":809},{"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":"1410.5401","title":"Neural Turing Machines","created":"2014-10-20","cited_by_count":644},{"id":"1906.05909","title":"Stand-Alone Self-Attention in Vision Models","created":"2019-06-13","cited_by_count":542},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"1712.04851","title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","created":"2017-12-13","cited_by_count":521},{"id":"1711.10305","title":"Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks","created":"2017-11-28","cited_by_count":387},{"id":"2101.11605","title":"Bottleneck Transformers for Visual Recognition","created":"2021-01-27","cited_by_count":364},{"id":"1410.3916","title":"Memory Networks","created":"2014-10-15","cited_by_count":363},{"id":"1904.09925","title":"Attention Augmented Convolutional Networks","created":"2019-04-22","cited_by_count":363},{"id":"1904.11492","title":"GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond","created":"2019-04-25","cited_by_count":331},{"id":"1711.08496","title":"Temporal Relational Reasoning in Videos","created":"2017-11-22","cited_by_count":324},{"id":"2004.13621","title":"Exploring Self-attention for Image Recognition","created":"2020-04-28","cited_by_count":313},{"id":"1605.07725","title":"Adversarial Training Methods for Semi-Supervised Text Classification","created":"2016-05-25","cited_by_count":280},{"id":"1812.05038","title":"Long-Term Feature Banks for Detailed Video Understanding","created":"2018-12-12","cited_by_count":239},{"id":"1806.01810","title":"Videos as Space-Time Region Graphs","created":"2018-06-05","cited_by_count":221},{"id":"1904.11491","title":"Local Relation Networks for Image Recognition","created":"2019-04-25","cited_by_count":210},{"id":"1511.01432","title":"Semi-supervised Sequence Learning","created":"2015-11-04","cited_by_count":198},{"id":"1704.01444","title":"Learning to Generate Reviews and Discovering Sentiment","created":"2017-04-05","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":"2006.06668","title":"Disentangled Non-Local Neural Networks","created":"2020-06-11","cited_by_count":132},{"id":"1506.07285","title":"Ask Me Anything: Dynamic Memory Networks for Natural Language Processing","created":"2015-06-24","cited_by_count":117},{"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":"1708.00107","title":"Learned in Translation: Contextualized Word Vectors","created":"2017-08-01","cited_by_count":104},{"id":"1612.04426","title":"Improving Neural Language Models with a Continuous Cache","created":"2016-12-13","cited_by_count":82},{"id":"1806.01822","title":"Relational recurrent neural networks","created":"2018-06-05","cited_by_count":65},{"id":"1603.01417","title":"Dynamic Memory Networks for Visual and Textual Question Answering","created":"2016-03-04","cited_by_count":62},{"id":"1606.01305","title":"Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations","created":"2016-06-03","cited_by_count":54},{"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":"1412.1058","title":"Effective Use of Word Order for Text Categorization with Convolutional Neural Networks","created":"2014-12-01","cited_by_count":40},{"id":"1908.00300","title":"Simple and Effective Text Matching with Richer Alignment Features","created":"2019-08-01","cited_by_count":29},{"id":"1611.01702","title":"TopicRNN: A Recurrent Neural Network with Long-Range Semantic Dependency","created":"2016-11-05","cited_by_count":27},{"id":"1512.00843","title":"Protein secondary structure prediction using deep convolutional neural fields","created":"2015-12-02","cited_by_count":12},{"id":"1602.02373","title":"Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings","created":"2016-02-07","cited_by_count":11},{"id":"1605.00064","title":"Higher Order Recurrent Neural Networks","created":"2016-04-30","cited_by_count":11},{"id":"1807.04445","title":"Adding Attentiveness to the Neurons in Recurrent Neural Networks","created":"2018-07-12","cited_by_count":11},{"id":"1403.1347","title":"Deep Supervised and Convolutional Generative Stochastic Network for Protein Secondary Structure Prediction","created":"2014-03-06","cited_by_count":8},{"id":"1612.00385","title":"Temporal Attention-Gated Model for Robust Sequence Classification","created":"2016-12-01","cited_by_count":8},{"id":"1603.04713","title":"Modeling Time Series Similarity with Siamese Recurrent Networks","created":"2016-03-15","cited_by_count":5},{"id":"1806.05662","title":"GLoMo: Unsupervisedly Learned Relational Graphs as Transferable Representations","created":"2018-06-14","cited_by_count":5},{"id":"1604.07176","title":"Protein Secondary Structure Prediction Using Cascaded Convolutional and Recurrent Neural Networks","created":"2016-04-25","cited_by_count":4},{"id":"1802.08314","title":"High Order Recurrent Neural Networks for Acoustic Modelling","created":"2018-02-22","cited_by_count":2},{"id":"1908.09535","title":"Non-local Recurrent Neural Memory for Supervised Sequence Modeling","created":"2019-08-26","cited_by_count":2}],"next_cursor":null}