{"list":"other","total":110,"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":"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"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":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1904.08920","title":"Towards VQA Models That Can Read","created":"2019-04-18","cited_by_count":1718},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"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":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"1908.08530","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","created":"2019-08-22","cited_by_count":954},{"id":"1909.11059","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","created":"2019-09-24","cited_by_count":494},{"id":"1511.02799","title":"Neural Module Networks","created":"2015-11-09","cited_by_count":376},{"id":"1904.12584","title":"The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision","created":"2019-04-26","cited_by_count":372},{"id":"1906.10770","title":"Deep Modular Co-Attention Networks for Visual Question Answering","created":"2019-06-25","cited_by_count":339},{"id":"1905.13648","title":"Scene Text Visual Question Answering","created":"2019-05-31","cited_by_count":331},{"id":"1506.06726","title":"Skip-Thought Vectors","created":"2015-06-22","cited_by_count":322},{"id":"1511.03416","title":"Visual7W: Grounded Question Answering in Images","created":"2015-11-11","cited_by_count":318},{"id":"1810.02338","title":"Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding","created":"2018-10-04","cited_by_count":304},{"id":"2004.00849","title":"Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers","created":"2020-04-02","cited_by_count":288},{"id":"1909.03683","title":"Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases","created":"2019-09-09","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":"1511.02274","title":"Stacked Attention Networks for Image Question Answering","created":"2015-11-07","cited_by_count":273},{"id":"1606.01847","title":"Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding","created":"2016-06-06","cited_by_count":243},{"id":"2006.16934","title":"ERNIE-ViL: Knowledge Enhanced Vision-Language Representations Through Scene Graph","created":"2020-06-30","cited_by_count":211},{"id":"1906.10169","title":"RUBi: Reducing Unimodal Biases in Visual Question Answering","created":"2019-06-24","cited_by_count":185},{"id":"1803.03067","title":"Compositional Attention Networks for Machine Reasoning","created":"2018-03-08","cited_by_count":183},{"id":"1606.05433","title":"FVQA: Fact-based Visual Question Answering","created":"2016-06-17","cited_by_count":181},{"id":"1802.08129","title":"Multimodal Explanations: Justifying Decisions and Pointing to the Evidence","created":"2018-02-15","cited_by_count":179},{"id":"2001.03615","title":"In Defense of Grid Features for Visual Question Answering","created":"2020-01-10","cited_by_count":155},{"id":"1810.12440","title":"TallyQA: Answering Complex Counting Questions","created":"2018-10-29","cited_by_count":153},{"id":"2003.06576","title":"Counterfactual Samples Synthesizing for Robust Visual Question Answering","created":"2020-03-14","cited_by_count":153},{"id":"1505.02074","title":"Exploring Models and Data for Image Question Answering","created":"2015-05-08","cited_by_count":139},{"id":"1705.06676","title":"MUTAN: Multimodal Tucker Fusion for Visual Question Answering","created":"2017-05-18","cited_by_count":137},{"id":"1705.03633","title":"Inferring and Executing Programs for Visual Reasoning","created":"2017-05-10","cited_by_count":130},{"id":"1902.03751","title":"Taking a HINT: Leveraging Explanations to Make Vision and Language Models More Grounded","created":"2019-02-11","cited_by_count":128},{"id":"1704.05526","title":"Learning to Reason: End-to-End Module Networks for Visual Question Answering","created":"2017-04-18","cited_by_count":125},{"id":"1609.05600","title":"Graph-Structured Representations for Visual Question Answering","created":"2016-09-19","cited_by_count":123},{"id":"1606.07356","title":"Analyzing the Behavior of Visual Question Answering Models","created":"2016-06-23","cited_by_count":119},{"id":"1903.12314","title":"Relation-Aware Graph Attention Network for Visual Question Answering","created":"2019-03-29","cited_by_count":119},{"id":"1611.00471","title":"Dual Attention Networks for Multimodal Reasoning and Matching","created":"2016-11-02","cited_by_count":114},{"id":"1907.03950","title":"Learning by Abstraction: The Neural State Machine","created":"2019-07-09","cited_by_count":113},{"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":"1511.05099","title":"Yin and Yang: Balancing and Answering Binary Visual Questions","created":"2015-11-16","cited_by_count":109},{"id":"1912.07538","title":"Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editing","created":"2019-12-16","cited_by_count":108},{"id":"1810.03649","title":"Overcoming Language Priors in Visual Question Answering with Adversarial Regularization","created":"2018-10-08","cited_by_count":105},{"id":"1902.05660","title":"Cycle-Consistency for Robust Visual Question Answering","created":"2019-02-15","cited_by_count":105},{"id":"1812.01855","title":"Explainable and Explicit Visual Reasoning over Scene Graphs","created":"2018-12-05","cited_by_count":103},{"id":"1703.09684","title":"An Analysis of Visual Question Answering Algorithms","created":"2017-03-28","cited_by_count":90},{"id":"1511.02570","title":"Explicit Knowledge-based Reasoning for Visual Question Answering","created":"2015-11-09","cited_by_count":85},{"id":"1601.01705","title":"Learning to Compose Neural Networks for Question Answering","created":"2016-01-07","cited_by_count":85},{"id":"1708.03619","title":"Beyond Bilinear: Generalized Multimodal Factorized High-order Pooling for Visual Question Answering","created":"2017-08-10","cited_by_count":79},{"id":"1708.02711","title":"Tips and Tricks for Visual Question Answering: Learnings from the 2017 Challenge","created":"2017-08-09","cited_by_count":76},{"id":"1902.09487","title":"MUREL: Multimodal Relational Reasoning for Visual Question Answering","created":"2019-02-25","cited_by_count":68},{"id":"1511.05234","title":"Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering","created":"2015-11-17","cited_by_count":66},{"id":"2004.09034","title":"Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision","created":"2020-04-20","cited_by_count":66},{"id":"1511.07394","title":"Where To Look: Focus Regions for Visual Question Answering","created":"2015-11-23","cited_by_count":64},{"id":"1809.02805","title":"Faithful Multimodal Explanation for Visual Question Answering","created":"2018-09-08","cited_by_count":64},{"id":"2009.08566","title":"MUTANT: A Training Paradigm for Out-of-Distribution Generalization in Visual Question Answering","created":"2020-09-18","cited_by_count":63},{"id":"1902.00038","title":"BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship Detection","created":"2019-01-31","cited_by_count":62},{"id":"1905.09998","title":"Self-Critical Reasoning for Robust Visual Question Answering","created":"2019-05-24","cited_by_count":61},{"id":"1805.05492","title":"Did the Model Understand the Question?","created":"2018-05-14","cited_by_count":60},{"id":"1905.04405","title":"Language-Conditioned Graph Networks for Relational Reasoning","created":"2019-05-10","cited_by_count":55},{"id":"1807.08556","title":"Explainable Neural Computation via Stack Neural Module Networks","created":"2018-07-23","cited_by_count":54},{"id":"1803.05268","title":"Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning","created":"2018-03-14","cited_by_count":51},{"id":"1804.00775","title":"Improved Fusion of Visual and Language Representations by Dense Symmetric Co-Attention for Visual Question Answering","created":"2018-04-03","cited_by_count":51},{"id":"1806.07243","title":"Learning Conditioned Graph Structures for Interpretable Visual Question Answering","created":"2018-06-19","cited_by_count":45},{"id":"1603.02814","title":"Image Captioning and Visual Question Answering Based on Attributes and External Knowledge","created":"2016-03-09","cited_by_count":44},{"id":"1511.06973","title":"Ask Me Anything: Free-form Visual Question Answering Based on Knowledge from External Sources","created":"2015-11-22","cited_by_count":42},{"id":"1606.01455","title":"Multimodal Residual Learning for Visual QA","created":"2016-06-05","cited_by_count":42},{"id":"1802.05766","title":"Learning to Count Objects in Natural Images for Visual Question Answering","created":"2018-02-15","cited_by_count":40},{"id":"1809.01124","title":"Straight to the Facts: Learning Knowledge Base Retrieval for Factual Visual Question Answering","created":"2018-09-04","cited_by_count":30},{"id":"1808.00265","title":"Interpretable Visual Question Answering by Visual Grounding from Attention Supervision Mining","created":"2018-08-01","cited_by_count":28},{"id":"1902.05715","title":"Generating Natural Language Explanations for Visual Question Answering using Scene Graphs and Visual Attention","created":"2019-02-15","cited_by_count":26},{"id":"1511.05960","title":"ABC-CNN: An Attention Based Convolutional Neural Network for Visual Question Answering","created":"2015-11-18","cited_by_count":24},{"id":"1704.08243","title":"C-VQA: A Compositional Split of the Visual Question Answering (VQA) v1.0 Dataset","created":"2017-04-26","cited_by_count":24},{"id":"1711.04323","title":"High-Order Attention Models for Visual Question Answering","created":"2017-11-12","cited_by_count":22},{"id":"1801.09041","title":"Tell-and-Answer: Towards Explainable Visual Question Answering using Attributes and Captions","created":"2018-01-27","cited_by_count":22},{"id":"1907.09815","title":"Bilinear Graph Networks for Visual Question Answering","created":"2019-07-23","cited_by_count":22},{"id":"1712.08697","title":"Interpretable Counting for Visual Question Answering","created":"2017-12-23","cited_by_count":17},{"id":"1809.01810","title":"Interpretable Visual Question Answering by Reasoning on Dependency Trees","created":"2018-09-06","cited_by_count":15},{"id":"1711.06794","title":"Co-attending Free-form Regions and Detections with Multi-modal Multiplicative Feature Embedding for Visual Question Answering","created":"2017-11-18","cited_by_count":13},{"id":"1712.00733","title":"Incorporating External Knowledge to Answer Open-Domain Visual Questions with Dynamic Memory Networks","created":"2017-12-03","cited_by_count":12},{"id":"1808.09044","title":"Single Shot Scene Text Retrieval","created":"2018-08-27","cited_by_count":11},{"id":"1612.05386","title":"The VQA-Machine: Learning How to Use Existing Vision Algorithms to Answer New Questions","created":"2016-12-16","cited_by_count":10},{"id":"2011.11603","title":"Interpretable Visual Reasoning via Induced Symbolic Space","created":"2020-11-23","cited_by_count":10}],"next_cursor":"100"}