{"list":"other","total":77,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"2102.04306","title":"TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation","created":"2021-02-08","cited_by_count":1558},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"1804.03999","title":"Attention U-Net: Learning Where to Look for the Pancreas","created":"2018-04-11","cited_by_count":1435},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"1707.07998","title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering","created":"2017-07-25","cited_by_count":1312},{"id":"1409.1259","title":"On the Properties of Neural Machine Translation: Encoder-Decoder Approaches","created":"2014-09-03","cited_by_count":1304},{"id":"1508.04025","title":"Effective Approaches to Attention-based Neural Machine Translation","created":"2015-08-17","cited_by_count":1026},{"id":"1904.06690","title":"BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer","created":"2019-04-14","cited_by_count":964},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"1805.08318","title":"Self-Attention Generative Adversarial Networks","created":"2018-05-21","cited_by_count":809},{"id":"2009.06732","title":"Efficient Transformers: A Survey","created":"2020-09-14","cited_by_count":790},{"id":"1802.05751","title":"Image Transformer","created":"2018-02-15","cited_by_count":772},{"id":"1710.09829","title":"Dynamic Routing Between Capsules","created":"2017-10-26","cited_by_count":689},{"id":"1410.5401","title":"Neural Turing Machines","created":"2014-10-20","cited_by_count":644},{"id":"1908.04626","title":"Attention is not not Explanation","created":"2019-08-13","cited_by_count":636},{"id":"1506.07503","title":"Attention-Based Models for Speech Recognition","created":"2015-06-24","cited_by_count":401},{"id":"1406.6247","title":"Recurrent Models of Visual Attention","created":"2014-06-24","cited_by_count":349},{"id":"1912.08226","title":"Meshed-Memory Transformer for Image Captioning","created":"2019-12-17","cited_by_count":343},{"id":"1809.02108","title":"Deep Audio-Visual Speech Recognition","created":"2018-09-06","cited_by_count":322},{"id":"1703.03130","title":"A Structured Self-attentive Sentence Embedding","created":"2017-03-09","cited_by_count":318},{"id":"2004.13621","title":"Exploring Self-attention for Image Recognition","created":"2020-04-28","cited_by_count":313},{"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":"1511.02274","title":"Stacked Attention Networks for Image Question Answering","created":"2015-11-07","cited_by_count":273},{"id":"1609.06773","title":"Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learning","created":"2016-09-21","cited_by_count":257},{"id":"1711.08195","title":"On the Automatic Generation of Medical Imaging Reports","created":"2017-11-22","cited_by_count":216},{"id":"1804.00819","title":"End-to-End Dense Video Captioning with Masked Transformer","created":"2018-04-03","cited_by_count":214},{"id":"2005.00743","title":"Synthesizer: Rethinking Self-Attention in Transformer Models","created":"2020-05-02","cited_by_count":205},{"id":"1804.09541","title":"QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension","created":"2018-04-23","cited_by_count":164},{"id":"1508.04395","title":"End-to-End Attention-based Large Vocabulary Speech Recognition","created":"2015-08-18","cited_by_count":151},{"id":"2004.11886","title":"Lite Transformer with Long-Short Range Attention","created":"2020-04-24","cited_by_count":127},{"id":"1904.02874","title":"An Attentive Survey of Attention Models","created":"2019-04-05","cited_by_count":124},{"id":"1606.03556","title":"Human Attention in Visual Question Answering: Do Humans and Deep Networks Look at the Same Regions?","created":"2016-06-11","cited_by_count":111},{"id":"2004.11648","title":"GCAN: Graph-aware Co-Attention Networks for Explainable Fake News Detection on Social Media","created":"2020-04-24","cited_by_count":109},{"id":"1711.03905","title":"Attend and Diagnose: Clinical Time Series Analysis using Attention Models","created":"2017-11-10","cited_by_count":105},{"id":"1803.03735","title":"Attention-based Graph Neural Network for Semi-supervised Learning","created":"2018-03-10","cited_by_count":101},{"id":"1909.10681","title":"Knowledge-Enriched Transformer for Emotion Detection in Textual Conversations","created":"2019-09-24","cited_by_count":92},{"id":"1709.00893","title":"Interactive Attention Networks for Aspect-Level Sentiment Classification","created":"2017-09-04","cited_by_count":91},{"id":"1906.02849","title":"Multi-scale self-guided attention for medical image segmentation","created":"2019-06-07","cited_by_count":84},{"id":"1911.10715","title":"Multi-Agent Game Abstraction via Graph Attention Neural Network","created":"2019-11-25","cited_by_count":82},{"id":"1709.04696","title":"DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understanding","created":"2017-09-14","cited_by_count":71},{"id":"1812.01969","title":"Summarizing Videos with Attention","created":"2018-12-05","cited_by_count":69},{"id":"1806.02311","title":"Unsupervised Attention-guided Image to Image Translation","created":"2018-06-06","cited_by_count":58},{"id":"1703.03906","title":"Massive Exploration of Neural Machine Translation Architectures","created":"2017-03-11","cited_by_count":55},{"id":"1905.07374","title":"Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs","created":"2019-05-17","cited_by_count":53},{"id":"1511.04119","title":"Action Recognition using Visual Attention","created":"2015-11-12","cited_by_count":49},{"id":"2004.14243","title":"Towards Transparent and Explainable Attention Models","created":"2020-04-29","cited_by_count":47},{"id":"1712.00975","title":"Temporal Attention augmented Bilinear Network for Financial Time-Series Data Analysis","created":"2017-12-04","cited_by_count":46},{"id":"1605.09553","title":"Attention Correctness in Neural Image Captioning","created":"2016-05-31","cited_by_count":35},{"id":"1701.07149","title":"Hierarchical Recurrent Attention Network for Response Generation","created":"2017-01-25","cited_by_count":34},{"id":"1811.05544","title":"An Introductory Survey on Attention Mechanisms in NLP Problems","created":"2018-11-12","cited_by_count":32},{"id":"1907.10255","title":"HA-CCN: Hierarchical Attention-based Crowd Counting Network","created":"2019-07-24","cited_by_count":32},{"id":"1801.09251","title":"Multi-Pointer Co-Attention Networks for Recommendation","created":"2018-01-28","cited_by_count":25},{"id":"1808.00300","title":"Learning Visual Question Answering by Bootstrapping Hard Attention","created":"2018-08-01","cited_by_count":24},{"id":"2004.05645","title":"Residual Attention U-Net for Automated Multi-Class Segmentation of COVID-19 Chest CT Images","created":"2020-04-12","cited_by_count":24},{"id":"1702.04521","title":"Frustratingly Short Attention Spans in Neural Language Modeling","created":"2017-02-15","cited_by_count":18},{"id":"1707.06029","title":"Supervising Neural Attention Models for Video Captioning by Human Gaze Data","created":"2017-07-19","cited_by_count":18},{"id":"1904.10788","title":"Speech Emotion Recognition Using Multi-hop Attention Mechanism","created":"2019-04-23","cited_by_count":18},{"id":"1601.06823","title":"Survey on the attention based RNN model and its applications in computer vision","created":"2016-01-25","cited_by_count":15},{"id":"1801.10296","title":"Reinforced Self-Attention Network: a Hybrid of Hard and Soft Attention for Sequence Modeling","created":"2018-01-31","cited_by_count":15},{"id":"1804.07983","title":"Dynamic Meta-Embeddings for Improved Sentence Representations","created":"2018-04-21","cited_by_count":15},{"id":"1808.06414","title":"Next Item Recommendation with Self-Attention","created":"2018-08-20","cited_by_count":15},{"id":"1904.01356","title":"Aiding Intra-Text Representations with Visual Context for Multimodal Named Entity Recognition","created":"2019-04-02","cited_by_count":15},{"id":"1901.10055","title":"Self-Attention Networks for Connectionist Temporal Classification in Speech Recognition","created":"2019-01-22","cited_by_count":14},{"id":"1906.09890","title":"Self Multi-Head Attention for Speaker Recognition","created":"2019-06-24","cited_by_count":13},{"id":"1802.00892","title":"Left-Center-Right Separated Neural Network for Aspect-based Sentiment Analysis with Rotatory Attention","created":"2018-02-03","cited_by_count":10},{"id":"1607.06416","title":"Hierarchical Attention Network for Action Recognition in Videos","created":"2016-07-21","cited_by_count":8},{"id":"1606.02245","title":"Iterative Alternating Neural Attention for Machine Reading","created":"2016-06-07","cited_by_count":6},{"id":"1803.02353","title":"Multi-level Attention Model for Weakly Supervised Audio Classification","created":"2018-03-06","cited_by_count":4},{"id":"1704.07415","title":"Ruminating Reader: Reasoning with Gated Multi-Hop Attention","created":"2017-04-24","cited_by_count":3},{"id":"1703.06052","title":"Attention and Localization based on a Deep Convolutional Recurrent Model for Weakly Supervised Audio Tagging","created":"2017-03-17","cited_by_count":2}],"next_cursor":null}