{"list":"other","total":58,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"1612.03928","title":"Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer","created":"2016-12-12","cited_by_count":1077},{"id":"1506.03340","title":"Teaching Machines to Read and Comprehend","created":"2015-06-10","cited_by_count":1049},{"id":"1508.04025","title":"Effective Approaches to Attention-based Neural Machine Translation","created":"2015-08-17","cited_by_count":1026},{"id":"1809.02983","title":"Dual Attention Network for Scene Segmentation","created":"2018-09-09","cited_by_count":1003},{"id":"1506.03134","title":"Pointer Networks","created":"2015-06-09","cited_by_count":895},{"id":"1903.07293","title":"Heterogeneous Graph Attention Network","created":"2019-03-18","cited_by_count":734},{"id":"1410.5401","title":"Neural Turing Machines","created":"2014-10-20","cited_by_count":644},{"id":"1603.08983","title":"Adaptive Computation Time for Recurrent Neural Networks","created":"2016-03-29","cited_by_count":506},{"id":"1606.05908","title":"Tutorial on Variational Autoencoders","created":"2016-06-19","cited_by_count":409},{"id":"1410.3916","title":"Memory Networks","created":"2014-10-15","cited_by_count":363},{"id":"1406.6247","title":"Recurrent Models of Visual Attention","created":"2014-06-24","cited_by_count":349},{"id":"1608.00507","title":"Top-down Neural Attention by Excitation Backprop","created":"2016-08-01","cited_by_count":321},{"id":"1901.05761","title":"Attentive Neural Processes","created":"2019-01-17","cited_by_count":283},{"id":"1805.07932","title":"Bilinear Attention Networks","created":"2018-05-21","cited_by_count":280},{"id":"1606.00061","title":"Hierarchical Question-Image Co-Attention for Visual Question Answering","created":"2016-05-31","cited_by_count":278},{"id":"1611.01603","title":"Bidirectional Attention Flow for Machine Comprehension","created":"2016-11-05","cited_by_count":278},{"id":"1808.08114","title":"Attention Gated Networks: Learning to Leverage Salient Regions in Medical Images","created":"2018-08-22","cited_by_count":272},{"id":"1505.00387","title":"Highway Networks","created":"2015-05-03","cited_by_count":260},{"id":"1612.01887","title":"Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning","created":"2016-12-06","cited_by_count":232},{"id":"1502.04623","title":"DRAW: A Recurrent Neural Network For Image Generation","created":"2015-02-16","cited_by_count":191},{"id":"1803.03067","title":"Compositional Attention Networks for Machine Reasoning","created":"2018-03-08","cited_by_count":183},{"id":"1810.11579","title":"$A^2$-Nets: Double Attention Networks","created":"2018-10-27","cited_by_count":136},{"id":"1904.02874","title":"An Attentive Survey of Attention Models","created":"2019-04-05","cited_by_count":124},{"id":"1506.07285","title":"Ask Me Anything: Dynamic Memory Networks for Natural Language Processing","created":"2015-06-24","cited_by_count":117},{"id":"2003.03772","title":"IMRAM: Iterative Matching with Recurrent Attention Memory for Cross-Modal Image-Text Retrieval","created":"2020-03-08","cited_by_count":115},{"id":"1611.00471","title":"Dual Attention Networks for Multimodal Reasoning and Matching","created":"2016-11-02","cited_by_count":114},{"id":"1902.02181","title":"Attention in Natural Language Processing","created":"2019-02-04","cited_by_count":101},{"id":"1702.00887","title":"Structured Attention Networks","created":"2017-02-03","cited_by_count":95},{"id":"1602.03001","title":"A Convolutional Attention Network for Extreme Summarization of Source Code","created":"2016-02-09","cited_by_count":91},{"id":"1709.04696","title":"DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understanding","created":"2017-09-14","cited_by_count":71},{"id":"1912.03046","title":"Hyperbolic Graph Attention Network","created":"2019-12-06","cited_by_count":70},{"id":"1509.06664","title":"Reasoning about Entailment with Neural Attention","created":"2015-09-22","cited_by_count":69},{"id":"1603.01417","title":"Dynamic Memory Networks for Visual and Textual Question Answering","created":"2016-03-04","cited_by_count":62},{"id":"1611.01604","title":"Dynamic Coattention Networks For Question Answering","created":"2016-11-05","cited_by_count":49},{"id":"2006.16981","title":"Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules","created":"2020-06-30","cited_by_count":38},{"id":"2007.02036","title":"Modality Shifting Attention Network for Multi-modal Video Question Answering","created":"2020-07-04","cited_by_count":38},{"id":"1807.03756","title":"Latent Alignment and Variational Attention","created":"2018-07-10","cited_by_count":36},{"id":"1809.03702","title":"Sparse Attentive Backtracking: Temporal CreditAssignment Through Reminding","created":"2018-09-11","cited_by_count":34},{"id":"1606.04695","title":"Strategic Attentive Writer for Learning Macro-Actions","created":"2016-06-15","cited_by_count":30},{"id":"1709.07992","title":"Visual Reference Resolution using Attention Memory for Visual Dialog","created":"2017-09-23","cited_by_count":28},{"id":"1710.10304","title":"Few-shot Autoregressive Density Estimation: Towards Learning to Learn Distributions","created":"2017-10-27","cited_by_count":24},{"id":"2103.00336","title":"Transformers with Competitive Ensembles of Independent Mechanisms","created":"2021-02-27","cited_by_count":19},{"id":"1407.3068","title":"Deep Networks with Internal Selective Attention through Feedback Connections","created":"2014-07-11","cited_by_count":17},{"id":"1611.01867","title":"Latent Attention For If-Then Program Synthesis","created":"2016-11-07","cited_by_count":10},{"id":"1411.5140","title":"Attentional Neural Network: Feature Selection Using Cognitive Feedback","created":"2014-11-19","cited_by_count":8},{"id":"1312.6110","title":"Learning Generative Models with Visual Attention","created":"2013-12-20","cited_by_count":5},{"id":"1711.02326","title":"Sparse Attentive Backtracking: Long-Range Credit Assignment in Recurrent Networks","created":"2017-11-07","cited_by_count":3},{"id":"2006.07438","title":"Attentive Feature Reuse for Multi Task Meta learning","created":"2020-06-12","cited_by_count":3},{"id":"2008.10849","title":"LSTM Networks for Online Cross-Network Recommendations","created":"2020-08-25","cited_by_count":3}],"next_cursor":null}