{"list":"other","total":100,"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"1411.1784","title":"Conditional Generative Adversarial Nets","created":"2014-11-06","cited_by_count":2162},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1602.07261","title":"Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning","created":"2016-02-23","cited_by_count":1512},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"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":"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":"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":"2012.00364","title":"Pre-Trained Image Processing Transformer","created":"2020-12-01","cited_by_count":893},{"id":"1411.4555","title":"Show and Tell: A Neural Image Caption Generator","created":"2014-11-17","cited_by_count":879},{"id":"1606.05328","title":"Conditional Image Generation with PixelCNN Decoders","created":"2016-06-16","cited_by_count":862},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"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":"2111.09734","title":"ClipCap: CLIP Prefix for Image Captioning","created":"2021-11-18","cited_by_count":559},{"id":"1705.03122","title":"Convolutional Sequence to Sequence Learning","created":"2017-05-08","cited_by_count":552},{"id":"1811.00982","title":"The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale","created":"2018-11-02","cited_by_count":544},{"id":"1909.11059","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","created":"2019-09-24","cited_by_count":494},{"id":"1701.02426","title":"Scene Graph Generation by Iterative Message Passing","created":"2017-01-10","cited_by_count":462},{"id":"1812.08658","title":"nocaps: novel object captioning at scale","created":"2018-12-20","cited_by_count":444},{"id":"1711.06640","title":"Neural Motifs: Scene Graph Parsing with Global Context","created":"2017-11-17","cited_by_count":414},{"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":"1503.04069","title":"LSTM: A Search Space Odyssey","created":"2015-03-13","cited_by_count":316},{"id":"1711.11575","title":"Relation Networks for Object Detection","created":"2017-11-30","cited_by_count":305},{"id":"1808.00191","title":"Graph R-CNN for Scene Graph Generation","created":"2018-08-01","cited_by_count":298},{"id":"1908.06954","title":"Attention on Attention for Image Captioning","created":"2019-08-19","cited_by_count":289},{"id":"1511.02274","title":"Stacked Attention Networks for Image Question Answering","created":"2015-11-07","cited_by_count":273},{"id":"1603.03925","title":"Image Captioning with Semantic Attention","created":"2016-03-12","cited_by_count":260},{"id":"1812.01880","title":"Learning to Compose Dynamic Tree Structures for Visual Contexts","created":"2018-12-05","cited_by_count":259},{"id":"1812.02378","title":"Auto-Encoding Scene Graphs for Image Captioning","created":"2018-12-06","cited_by_count":255},{"id":"1606.01847","title":"Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding","created":"2016-06-06","cited_by_count":243},{"id":"1912.03098","title":"Connecting Vision and Language with Localized Narratives","created":"2019-12-06","cited_by_count":226},{"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":"2003.14080","title":"X-Linear Attention Networks for Image Captioning","created":"2020-03-31","cited_by_count":198},{"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":"1707.09700","title":"Scene Graph Generation from Objects, Phrases and Region Captions","created":"2017-07-31","cited_by_count":154},{"id":"1612.00370","title":"Improved Image Captioning via Policy Gradient optimization of SPIDEr","created":"2016-12-01","cited_by_count":113},{"id":"1702.08319","title":"Visual Translation Embedding Network for Visual Relation Detection","created":"2017-02-27","cited_by_count":112},{"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":"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":"1904.00560","title":"Scene Graph Generation with External Knowledge and Image Reconstruction","created":"2019-04-01","cited_by_count":102},{"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":"1704.03114","title":"Detecting Visual Relationships with Deep Relational Networks","created":"2017-04-11","cited_by_count":97},{"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":"1903.10658","title":"Unpaired Image Captioning via Scene Graph Alignments","created":"2019-03-26","cited_by_count":82},{"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":"1811.10652","title":"Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions","created":"2018-11-26","cited_by_count":65},{"id":"2101.10804","title":"CPTR: Full Transformer Network for Image Captioning","created":"2021-01-26","cited_by_count":55},{"id":"1611.02344","title":"A Convolutional Encoder Model for Neural Machine Translation","created":"2016-11-07","cited_by_count":54},{"id":"1711.09151","title":"Convolutional Image Captioning","created":"2017-11-24","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":"1510.01431","title":"SentiCap: Generating Image Descriptions with Sentiments","created":"2015-10-06","cited_by_count":48},{"id":"1807.09986","title":"Recurrent Fusion Network for Image Captioning","created":"2018-07-26","cited_by_count":43},{"id":"2112.05230","title":"Injecting Semantic Concepts into End-to-End Image Captioning","created":"2021-12-09","cited_by_count":41},{"id":"1803.08314","title":"Show, Tell and Discriminate: Image Captioning by Self-retrieval with Partially Labeled Data","created":"2018-03-22","cited_by_count":37},{"id":"1506.01144","title":"What value do explicit high level concepts have in vision to language problems?","created":"2015-06-03","cited_by_count":31},{"id":"1905.13302","title":"A Survey on Biomedical Image Captioning","created":"2019-05-26","cited_by_count":30},{"id":"2004.14231","title":"Image Captioning through Image Transformer","created":"2020-04-29","cited_by_count":29},{"id":"1709.03376","title":"Stack-Captioning: Coarse-to-Fine Learning for Image Captioning","created":"2017-09-11","cited_by_count":27},{"id":"1803.05526","title":"Unpaired Image Captioning by Language Pivoting","created":"2018-03-14","cited_by_count":27},{"id":"2107.14178","title":"ReFormer: The Relational Transformer for Image Captioning","created":"2021-07-29","cited_by_count":23},{"id":"1803.09189","title":"Scene Graph Parsing as Dependency Parsing","created":"2018-03-25","cited_by_count":21},{"id":"2002.12585","title":"Exploring and Distilling Cross-Modal Information for Image Captioning","created":"2020-02-28","cited_by_count":19},{"id":"2012.11696","title":"Image Captioning as an Assistive Technology: Lessons Learned from VizWiz 2020 Challenge","created":"2020-12-21","cited_by_count":17},{"id":"2104.12471","title":"Contextualized Keyword Representations for Multi-modal Retinal Image Captioning","created":"2021-04-26","cited_by_count":16},{"id":"1805.07112","title":"Improving Image Captioning with Conditional Generative Adversarial Nets","created":"2018-05-18","cited_by_count":14},{"id":"1909.09953","title":"Learning Visual Relation Priors for Image-Text Matching and Image Captioning with Neural Scene Graph Generators","created":"2019-09-22","cited_by_count":13},{"id":"1805.09019","title":"CNN+CNN: Convolutional Decoders for Image Captioning","created":"2018-05-23","cited_by_count":9},{"id":"2105.08106","title":"Multi-Modal Image Captioning for the Visually Impaired","created":"2021-05-17","cited_by_count":8},{"id":"2107.13114","title":"A Thorough Review on Recent Deep Learning Methodologies for Image Captioning","created":"2021-07-28","cited_by_count":4}],"next_cursor":null}