{"list":"other","total":393,"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1901.00596","title":"A Comprehensive Survey on Graph Neural Networks","created":"2019-01-03","cited_by_count":2919},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"1609.08144","title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","created":"2016-09-26","cited_by_count":1475},{"id":"1804.03999","title":"Attention U-Net: Learning Where to Look for the Pancreas","created":"2018-04-11","cited_by_count":1435},{"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":"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":"1704.04368","title":"Get To The Point: Summarization with Pointer-Generator Networks","created":"2017-04-14","cited_by_count":1292},{"id":"1807.02758","title":"Image Super-Resolution Using Very Deep Residual Channel Attention Networks","created":"2018-07-08","cited_by_count":1264},{"id":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"id":"1803.02155","title":"Self-Attention with Relative Position Representations","created":"2018-03-06","cited_by_count":1120},{"id":"1802.04712","title":"Attention-based Deep Multiple Instance Learning","created":"2018-02-13","cited_by_count":1095},{"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":"1905.05950","title":"BERT Rediscovers the Classical NLP Pipeline","created":"2019-05-15","cited_by_count":1059},{"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":"1906.04341","title":"What Does BERT Look At? An Analysis of BERT's Attention","created":"2019-06-11","cited_by_count":1003},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"1506.03134","title":"Pointer Networks","created":"2015-06-09","cited_by_count":895},{"id":"1411.4555","title":"Show and Tell: A Neural Image Caption Generator","created":"2014-11-17","cited_by_count":879},{"id":"1602.06023","title":"Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond","created":"2016-02-19","cited_by_count":812},{"id":"1805.08318","title":"Self-Attention Generative Adversarial Networks","created":"2018-05-21","cited_by_count":809},{"id":"1705.00754","title":"Dense-Captioning Events in Videos","created":"2017-05-02","cited_by_count":793},{"id":"1802.05751","title":"Image Transformer","created":"2018-02-15","cited_by_count":772},{"id":"1903.07293","title":"Heterogeneous Graph Attention Network","created":"2019-03-18","cited_by_count":734},{"id":"1803.10892","title":"Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks","created":"2018-03-29","cited_by_count":690},{"id":"1710.09829","title":"Dynamic Routing Between Capsules","created":"2017-10-26","cited_by_count":689},{"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":"1801.01423","title":"Overcoming catastrophic forgetting with hard attention to the task","created":"2018-01-04","cited_by_count":681},{"id":"1711.10485","title":"AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks","created":"2017-11-28","cited_by_count":664},{"id":"1807.03819","title":"Universal Transformers","created":"2018-07-10","cited_by_count":647},{"id":"1908.04626","title":"Attention is not not Explanation","created":"2019-08-13","cited_by_count":636},{"id":"1801.07892","title":"Generative Image Inpainting with Contextual Attention","created":"2018-01-24","cited_by_count":580},{"id":"1508.01211","title":"Listen, Attend and Spell","created":"2015-08-05","cited_by_count":543},{"id":"1803.10704","title":"End-to-End Multi-Task Learning with Attention","created":"2018-03-28","cited_by_count":534},{"id":"2006.10637","title":"Temporal Graph Networks for Deep Learning on Dynamic Graphs","created":"2020-06-18","cited_by_count":530},{"id":"1603.08983","title":"Adaptive Computation Time for Recurrent Neural Networks","created":"2016-03-29","cited_by_count":506},{"id":"1804.05685","title":"A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents","created":"2018-04-16","cited_by_count":478},{"id":"1904.00607","title":"Video Object Segmentation using Space-Time Memory Networks","created":"2019-04-01","cited_by_count":438},{"id":"1801.08186","title":"MAttNet: Modular Attention Network for Referring Expression Comprehension","created":"2018-01-24","cited_by_count":431},{"id":"1803.08024","title":"Stacked Cross Attention for Image-Text Matching","created":"2018-03-21","cited_by_count":416},{"id":"1506.07503","title":"Attention-Based Models for Speech Recognition","created":"2015-06-24","cited_by_count":401},{"id":"1509.00685","title":"A Neural Attention Model for Abstractive Sentence Summarization","created":"2015-09-02","cited_by_count":396},{"id":"1901.11390","title":"MONet: Unsupervised Scene Decomposition and Representation","created":"2019-01-22","cited_by_count":392},{"id":"1906.03731","title":"Is Attention Interpretable?","created":"2019-06-09","cited_by_count":389},{"id":"1704.06904","title":"Residual Attention Network for Image Classification","created":"2017-04-23","cited_by_count":386},{"id":"1705.04304","title":"A Deep Reinforced Model for Abstractive Summarization","created":"2017-05-11","cited_by_count":365},{"id":"1904.09925","title":"Attention Augmented Convolutional Networks","created":"2019-04-22","cited_by_count":363},{"id":"1406.6247","title":"Recurrent Models of Visual Attention","created":"2014-06-24","cited_by_count":349},{"id":"1712.00377","title":"Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering","created":"2017-12-01","cited_by_count":339},{"id":"1611.01734","title":"Deep Biaffine Attention for Neural Dependency Parsing","created":"2016-11-06","cited_by_count":334},{"id":"1608.00507","title":"Top-down Neural Attention by Excitation Backprop","created":"2016-08-01","cited_by_count":321},{"id":"1511.03416","title":"Visual7W: Grounded Question Answering in Images","created":"2015-11-11","cited_by_count":318},{"id":"1703.03130","title":"A Structured Self-attentive Sentence Embedding","created":"2017-03-09","cited_by_count":318},{"id":"1812.02707","title":"Video Action Transformer Network","created":"2018-12-06","cited_by_count":316},{"id":"1909.07528","title":"Emergent Tool Use From Multi-Agent Autocurricula","created":"2019-09-17","cited_by_count":313},{"id":"1806.01482","title":"SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraints","created":"2018-06-05","cited_by_count":298},{"id":"2004.06100","title":"Pretrained Transformers Improve Out-of-Distribution Robustness","created":"2020-04-13","cited_by_count":294},{"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":"1511.02274","title":"Stacked Attention Networks for Image Question Answering","created":"2015-11-07","cited_by_count":273},{"id":"1808.08114","title":"Attention Gated Networks: Learning to Leverage Salient Regions in Medical Images","created":"2018-08-22","cited_by_count":272},{"id":"2011.07231","title":"ActBERT: Learning Global-Local Video-Text Representations","created":"2020-11-14","cited_by_count":267},{"id":"1603.03925","title":"Image Captioning with Semantic Attention","created":"2016-03-12","cited_by_count":260},{"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":"1704.02971","title":"A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction","created":"2017-04-07","cited_by_count":245},{"id":"1906.04284","title":"Analyzing the Structure of Attention in a Transformer Language Model","created":"2019-06-07","cited_by_count":243},{"id":"1711.10678","title":"AttGAN: Facial Attribute Editing by Only Changing What You Want","created":"2017-11-29","cited_by_count":242},{"id":"1711.04725","title":"Neural Attentive Session-based Recommendation","created":"2017-11-13","cited_by_count":237},{"id":"1903.10082","title":"Residual Non-local Attention Networks for Image Restoration","created":"2019-03-24","cited_by_count":236},{"id":"1703.07326","title":"One-Shot Imitation Learning","created":"2017-03-21","cited_by_count":233},{"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":"1809.10853","title":"Adaptive Input Representations for Neural Language Modeling","created":"2018-09-28","cited_by_count":226},{"id":"1612.08220","title":"Understanding Neural Networks through Representation Erasure","created":"2016-12-24","cited_by_count":224},{"id":"1606.03126","title":"Key-Value Memory Networks for Directly Reading Documents","created":"2016-06-09","cited_by_count":223},{"id":"1611.05594","title":"SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning","created":"2016-11-17","cited_by_count":219},{"id":"1909.10893","title":"Recurrent Independent Mechanisms","created":"2019-09-24","cited_by_count":219},{"id":"1811.00405","title":"DialogueRNN: An Attentive RNN for Emotion Detection in Conversations","created":"2018-11-01","cited_by_count":218},{"id":"1606.01933","title":"A Decomposable Attention Model for Natural Language Inference","created":"2016-06-06","cited_by_count":215},{"id":"1809.07041","title":"Exploring Visual Relationship for Image Captioning","created":"2018-09-19","cited_by_count":215},{"id":"1804.00819","title":"End-to-End Dense Video Captioning with Masked Transformer","created":"2018-04-03","cited_by_count":214},{"id":"1802.08122","title":"Harmonious Attention Network for Person Re-Identification","created":"2018-02-22","cited_by_count":211},{"id":"1809.04281","title":"Music Transformer","created":"2018-09-12","cited_by_count":211},{"id":"1711.10098","title":"Attentive Generative Adversarial Network for Raindrop Removal from a Single Image","created":"2017-11-28","cited_by_count":204}],"next_cursor":"100"}