{"list":"other","total":57,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1904.01038","title":"fairseq: A Fast, Extensible Toolkit for Sequence Modeling","created":"2019-04-01","cited_by_count":1488},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"1605.05396","title":"Generative Adversarial Text to Image Synthesis","created":"2016-05-17","cited_by_count":735},{"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":"1612.03242","title":"StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks","created":"2016-12-10","cited_by_count":577},{"id":"1705.03122","title":"Convolutional Sequence to Sequence Learning","created":"2017-05-08","cited_by_count":552},{"id":"1904.03493","title":"VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research","created":"2019-04-06","cited_by_count":414},{"id":"1904.01310","title":"DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis","created":"2019-04-02","cited_by_count":308},{"id":"2103.01913","title":"WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning","created":"2021-03-02","cited_by_count":287},{"id":"2101.04702","title":"Cross-Modal Contrastive Learning for Text-to-Image Generation","created":"2021-01-12","cited_by_count":259},{"id":"1605.00459","title":"Multi30K: Multilingual English-German Image Descriptions","created":"2016-05-02","cited_by_count":250},{"id":"1909.02701","title":"Visual Semantic Reasoning for Image-Text Matching","created":"2019-09-06","cited_by_count":185},{"id":"1903.05854","title":"MirrorGAN: Learning Text-to-image Generation by Redescription","created":"2019-03-14","cited_by_count":176},{"id":"1911.12423","title":"AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning","created":"2019-11-27","cited_by_count":160},{"id":"2011.04305","title":"Learning the Best Pooling Strategy for Visual Semantic Embedding","created":"2020-11-09","cited_by_count":137},{"id":"2010.06775","title":"Vokenization: Improving Language Understanding with Contextualized, Visual-Grounded Supervision","created":"2020-10-14","cited_by_count":94},{"id":"1806.07110","title":"Modality Distillation with Multiple Stream Networks for Action Recognition","created":"2018-06-19","cited_by_count":83},{"id":"1710.07177","title":"Findings of the Second Shared Task on Multimodal Machine Translation and Multilingual Image Description","created":"2017-10-19","cited_by_count":76},{"id":"1903.08678","title":"Probing the Need for Visual Context in Multimodal Machine Translation","created":"2019-03-20","cited_by_count":54},{"id":"2007.08742","title":"A Novel Graph-based Multi-modal Fusion Encoder for Neural Machine Translation","created":"2020-07-17","cited_by_count":51},{"id":"1906.02890","title":"Visually Grounded Neural Syntax Acquisition","created":"2019-06-07","cited_by_count":48},{"id":"1702.01287","title":"Doubly-Attentive Decoder for Multi-modal Neural Machine Translation","created":"2017-02-04","cited_by_count":46},{"id":"2105.14462","title":"Good for Misconceived Reasons: An Empirical Revisiting on the Need for Visual Context in Multimodal Machine Translation","created":"2021-05-30","cited_by_count":44},{"id":"2009.02016","title":"Dynamic Context-guided Capsule Network for Multimodal Machine Translation","created":"2020-09-04","cited_by_count":36},{"id":"1712.00108","title":"Graph Distillation for Action Detection with Privileged Modalities","created":"2017-11-30","cited_by_count":35},{"id":"2009.12404","title":"Visually Grounded Compound PCFGs","created":"2020-09-25","cited_by_count":34},{"id":"1906.07701","title":"Distilling Translations with Visual Awareness","created":"2019-06-18","cited_by_count":30},{"id":"2003.05078","title":"Visual Grounding in Video for Unsupervised Word Translation","created":"2020-03-11","cited_by_count":27},{"id":"1707.06320","title":"Learning Visually Grounded Sentence Representations","created":"2017-07-19","cited_by_count":24},{"id":"1808.08266","title":"A Visual Attention Grounding Neural Model for Multimodal Machine Translation","created":"2018-08-24","cited_by_count":22},{"id":"2005.03119","title":"Unsupervised Multimodal Neural Machine Translation with Pseudo Visual Pivoting","created":"2020-05-06","cited_by_count":22},{"id":"2009.09654","title":"Generative Imagination Elevates Machine Translation","created":"2020-09-21","cited_by_count":22},{"id":"2103.12975","title":"VLGrammar: Grounded Grammar Induction of Vision and Language","created":"2021-03-24","cited_by_count":22},{"id":"2107.02681","title":"VidLanKD: Improving Language Understanding via Video-Distilled Knowledge Transfer","created":"2021-07-06","cited_by_count":22},{"id":"2103.08862","title":"Gumbel-Attention for Multi-modal Machine Translation","created":"2021-03-16","cited_by_count":20},{"id":"2101.10044","title":"Cross-lingual Visual Pre-training for Multimodal Machine Translation","created":"2021-01-25","cited_by_count":19},{"id":"2109.11321","title":"Transferring Knowledge from Vision to Language: How to Achieve it and how to Measure it?","created":"2021-09-23","cited_by_count":18},{"id":"2104.04369","title":"Video-aided Unsupervised Grammar Induction","created":"2021-04-09","cited_by_count":17},{"id":"1811.11365","title":"Unsupervised Multi-modal Neural Machine Translation","created":"2018-11-28","cited_by_count":15},{"id":"2002.02734","title":"Incorporating Visual Semantics into Sentence Representations within a Grounded Space","created":"2020-02-07","cited_by_count":15},{"id":"2103.13942","title":"Visual Grounding Strategies for Text-Only Natural Language Processing","created":"2021-03-25","cited_by_count":7},{"id":"1905.12260","title":"Learning Multilingual Word Embeddings Using Image-Text Data","created":"2019-05-29","cited_by_count":2}],"next_cursor":null}