{"list":"other","total":175,"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"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":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"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":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"1411.4555","title":"Show and Tell: A Neural Image Caption Generator","created":"2014-11-17","cited_by_count":879},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"1605.05396","title":"Generative Adversarial Text to Image Synthesis","created":"2016-05-17","cited_by_count":735},{"id":"1809.02156","title":"Object Hallucination in Image Captioning","created":"2018-09-06","cited_by_count":669},{"id":"1511.06732","title":"Sequence Level Training with Recurrent Neural Networks","created":"2015-11-20","cited_by_count":576},{"id":"1612.00563","title":"Self-critical Sequence Training for Image Captioning","created":"2016-12-02","cited_by_count":547},{"id":"1909.11059","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","created":"2019-09-24","cited_by_count":494},{"id":"1411.4389","title":"Long-term Recurrent Convolutional Networks for Visual Recognition and Description","created":"2014-11-17","cited_by_count":484},{"id":"1812.08658","title":"nocaps: novel object captioning at scale","created":"2018-12-20","cited_by_count":444},{"id":"1803.08024","title":"Stacked Cross Attention for Image-Text Matching","created":"2018-03-21","cited_by_count":416},{"id":"2003.12462","title":"TextCaps: a Dataset for Image Captioning with Reading Comprehension","created":"2020-03-24","cited_by_count":400},{"id":"1912.08226","title":"Meshed-Memory Transformer for Image Captioning","created":"2019-12-17","cited_by_count":343},{"id":"2006.06666","title":"VirTex: Learning Visual Representations from Textual Annotations","created":"2020-06-11","cited_by_count":339},{"id":"2107.06383","title":"How Much Can CLIP Benefit Vision-and-Language Tasks?","created":"2021-07-13","cited_by_count":321},{"id":"1908.06954","title":"Attention on Attention for Image Captioning","created":"2019-08-19","cited_by_count":289},{"id":"2103.01913","title":"WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning","created":"2021-03-02","cited_by_count":287},{"id":"1603.03925","title":"Image Captioning with Semantic Attention","created":"2016-03-12","cited_by_count":260},{"id":"1812.02378","title":"Auto-Encoding Scene Graphs for Image Captioning","created":"2018-12-06","cited_by_count":255},{"id":"1605.00459","title":"Multi30K: Multilingual English-German Image Descriptions","created":"2016-05-02","cited_by_count":250},{"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":"1912.03098","title":"Connecting Vision and Language with Localized Narratives","created":"2019-12-06","cited_by_count":226},{"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":"1711.08195","title":"On the Automatic Generation of Medical Imaging Reports","created":"2017-11-22","cited_by_count":216},{"id":"1809.07041","title":"Exploring Visual Relationship for Image Captioning","created":"2018-09-19","cited_by_count":215},{"id":"1810.04020","title":"A Comprehensive Survey of Deep Learning for Image Captioning","created":"2018-10-06","cited_by_count":214},{"id":"1411.2539","title":"Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models","created":"2014-11-10","cited_by_count":198},{"id":"2003.14080","title":"X-Linear Attention Networks for Image Captioning","created":"2020-03-31","cited_by_count":198},{"id":"1605.05395","title":"Learning Deep Representations of Fine-grained Visual Descriptions","created":"2016-05-17","cited_by_count":182},{"id":"1511.07571","title":"DenseCap: Fully Convolutional Localization Networks for Dense Captioning","created":"2015-11-24","cited_by_count":176},{"id":"1906.05963","title":"Image Captioning: Transforming Objects into Words","created":"2019-06-14","cited_by_count":171},{"id":"2106.06963","title":"Exploring and Distilling Posterior and Prior Knowledge for Radiology Report Generation","created":"2021-06-13","cited_by_count":162},{"id":"1603.08507","title":"Generating Visual Explanations","created":"2016-03-28","cited_by_count":158},{"id":"2001.03615","title":"In Defense of Grid Features for Visual Question Answering","created":"2020-01-10","cited_by_count":155},{"id":"2010.03743","title":"Visual News: Benchmark and Challenges in News Image Captioning","created":"2020-10-08","cited_by_count":121},{"id":"1808.10584","title":"Learning to Describe Differences Between Pairs of Similar Images","created":"2018-08-31","cited_by_count":114},{"id":"1612.00370","title":"Improved Image Captioning via Policy Gradient optimization of SPIDEr","created":"2016-12-01","cited_by_count":113},{"id":"2002.08565","title":"Captioning Images Taken by People Who Are Blind","created":"2020-02-20","cited_by_count":110},{"id":"1411.4952","title":"From Captions to Visual Concepts and Back","created":"2014-11-18","cited_by_count":109},{"id":"1803.09845","title":"Neural Baby Talk","created":"2018-03-27","cited_by_count":107},{"id":"1612.00576","title":"Guided Open Vocabulary Image Captioning with Constrained Beam Search","created":"2016-12-02","cited_by_count":105},{"id":"1611.06607","title":"A Hierarchical Approach for Generating Descriptive Image Paragraphs","created":"2016-11-20","cited_by_count":104},{"id":"1703.10660","title":"Towards a Visual Privacy Advisor: Understanding and Predicting Privacy Risks in Images","created":"2017-03-30","cited_by_count":101},{"id":"1406.5679","title":"Deep Fragment Embeddings for Bidirectional Image Sentence Mapping","created":"2014-06-22","cited_by_count":99},{"id":"2012.04638","title":"TAP: Text-Aware Pre-training for Text-VQA and Text-Caption","created":"2020-12-08","cited_by_count":95},{"id":"1412.6632","title":"Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)","created":"2014-12-20","cited_by_count":94},{"id":"1807.09685","title":"Grounding Visual Explanations","created":"2018-07-25","cited_by_count":93},{"id":"2003.00387","title":"Say As You Wish: Fine-grained Control of Image Caption Generation with Abstract Scene Graphs","created":"2020-03-01","cited_by_count":87},{"id":"2006.11807","title":"Improving Image Captioning with Better Use of Captions","created":"2020-06-21","cited_by_count":84},{"id":"1903.10658","title":"Unpaired Image Captioning via Scene Graph Alignments","created":"2019-03-26","cited_by_count":82},{"id":"1805.08661","title":"COCO-CN for Cross-Lingual Image Tagging, Captioning and Retrieval","created":"2018-05-22","cited_by_count":80},{"id":"1811.10787","title":"Unsupervised Image Captioning","created":"2018-11-27","cited_by_count":79},{"id":"1611.01646","title":"Boosting Image Captioning with Attributes","created":"2016-11-05","cited_by_count":76},{"id":"2101.06462","title":"Dual-Level Collaborative Transformer for Image Captioning","created":"2021-01-16","cited_by_count":71},{"id":"1904.01475","title":"Good News, Everyone! Context driven entity-aware captioning for news images","created":"2019-04-02","cited_by_count":66},{"id":"1811.10652","title":"Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions","created":"2018-11-26","cited_by_count":65},{"id":"2003.08897","title":"Normalized and Geometry-Aware Self-Attention Network for Image Captioning","created":"2020-03-19","cited_by_count":63},{"id":"1703.06029","title":"Towards Diverse and Natural Image Descriptions via a Conditional GAN","created":"2017-03-17","cited_by_count":59},{"id":"1909.02050","title":"TIGEr: Text-to-Image Grounding for Image Caption Evaluation","created":"2019-09-04","cited_by_count":58},{"id":"1805.12589","title":"Fast, Diverse and Accurate Image Captioning Guided By Part-of-Speech","created":"2018-05-31","cited_by_count":55},{"id":"2101.10804","title":"CPTR: Full Transformer Network for Image Captioning","created":"2021-01-26","cited_by_count":55},{"id":"1710.02534","title":"Contrastive Learning for Image Captioning","created":"2017-10-06","cited_by_count":54},{"id":"1908.09317","title":"Towards Unsupervised Image Captioning with Shared Multimodal Embeddings","created":"2019-08-25","cited_by_count":54},{"id":"1806.06422","title":"Learning to Evaluate Image Captioning","created":"2018-06-17","cited_by_count":53},{"id":"1711.09151","title":"Convolutional Image Captioning","created":"2017-11-24","cited_by_count":52},{"id":"2004.08070","title":"Transform and Tell: Entity-Aware News Image Captioning","created":"2020-04-17","cited_by_count":52},{"id":"2007.11731","title":"Comprehensive Image Captioning via Scene Graph Decomposition","created":"2020-07-23","cited_by_count":52},{"id":"1810.10665","title":"Engaging Image Captioning Via Personality","created":"2018-10-25","cited_by_count":51},{"id":"2003.01473","title":"XGPT: Cross-modal Generative Pre-Training for Image Captioning","created":"2020-03-03","cited_by_count":51},{"id":"1611.08002","title":"Semantic Compositional Networks for Visual Captioning","created":"2016-11-23","cited_by_count":50},{"id":"2012.07061","title":"Improving Image Captioning by Leveraging Intra- and Inter-layer Global Representation in Transformer Network","created":"2020-12-13","cited_by_count":48},{"id":"1903.12020","title":"Describing like humans: on diversity in image captioning","created":"2019-03-28","cited_by_count":46},{"id":"1612.07600","title":"Re-evaluating Automatic Metrics for Image Captioning","created":"2016-12-22","cited_by_count":45},{"id":"1909.03918","title":"Hierarchy Parsing for Image Captioning","created":"2019-09-09","cited_by_count":44}],"next_cursor":"100"}