{"list":"other","total":65,"rows":[{"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":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"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":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"1409.7495","title":"Unsupervised Domain Adaptation by Backpropagation","created":"2014-09-26","cited_by_count":1917},{"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":"1812.01754","title":"Moment Matching for Multi-Source Domain Adaptation","created":"2018-12-04","cited_by_count":1331},{"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":"1711.03213","title":"CyCADA: Cycle-Consistent Adversarial Domain Adaptation","created":"2017-11-08","cited_by_count":1082},{"id":"1802.08218","title":"VizWiz Grand Challenge: Answering Visual Questions from Blind People","created":"2018-02-22","cited_by_count":858},{"id":"1903.06864","title":"Domain Generalization by Solving Jigsaw Puzzles","created":"2019-03-16","cited_by_count":450},{"id":"1803.03243","title":"Domain Adaptive Faster R-CNN for Object Detection in the Wild","created":"2018-03-08","cited_by_count":443},{"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":"1706.01427","title":"A simple neural network module for relational reasoning","created":"2017-06-05","cited_by_count":346},{"id":"2006.06195","title":"Large-Scale Adversarial Training for Vision-and-Language Representation Learning","created":"2020-06-11","cited_by_count":327},{"id":"2003.08505","title":"A Metric Learning Reality Check","created":"2020-03-18","cited_by_count":321},{"id":"1608.06019","title":"Domain Separation Networks","created":"2016-08-22","cited_by_count":320},{"id":"1511.03416","title":"Visual7W: Grounded Question Answering in Images","created":"2015-11-11","cited_by_count":318},{"id":"1904.10620","title":"Bidirectional Learning for Domain Adaptation of Semantic Segmentation","created":"2019-04-24","cited_by_count":308},{"id":"2003.13216","title":"Learning to Learn Single Domain Generalization","created":"2020-03-30","cited_by_count":296},{"id":"1909.00889","title":"Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Data","created":"2019-09-02","cited_by_count":246},{"id":"1902.00113","title":"Episodic Training for Domain Generalization","created":"2019-01-31","cited_by_count":245},{"id":"1909.11740","title":"UNITER: UNiversal Image-TExt Representation Learning","created":"2019-09-25","cited_by_count":228},{"id":"2006.16934","title":"ERNIE-ViL: Knowledge Enhanced Vision-Language Representations Through Scene Graph","created":"2020-06-30","cited_by_count":211},{"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":"2001.03615","title":"In Defense of Grid Features for Visual Question Answering","created":"2020-01-10","cited_by_count":155},{"id":"1804.10427","title":"Open Set Domain Adaptation by Backpropagation","created":"2018-04-27","cited_by_count":150},{"id":"1904.11227","title":"Transferrable Prototypical Networks for Unsupervised Domain Adaptation","created":"2019-04-25","cited_by_count":141},{"id":"1505.02074","title":"Exploring Models and Data for Image Question Answering","created":"2015-05-08","cited_by_count":139},{"id":"1705.03633","title":"Inferring and Executing Programs for Visual Reasoning","created":"2017-05-10","cited_by_count":130},{"id":"1808.04205","title":"Partial Adversarial Domain Adaptation","created":"2018-08-10","cited_by_count":127},{"id":"1907.03950","title":"Learning by Abstraction: The Neural State Machine","created":"2019-07-09","cited_by_count":113},{"id":"1707.09465","title":"Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes","created":"2017-07-29","cited_by_count":105},{"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":"2001.07437","title":"Evaluating Weakly Supervised Object Localization Methods Right","created":"2020-01-21","cited_by_count":105},{"id":"1611.07865","title":"Controlling Perceptual Factors in Neural Style Transfer","created":"2016-11-23","cited_by_count":100},{"id":"1803.09210","title":"Importance Weighted Adversarial Nets for Partial Domain Adaptation","created":"2018-03-25","cited_by_count":90},{"id":"1903.12230","title":"Learning to Transfer Examples for Partial Domain Adaptation","created":"2019-03-28","cited_by_count":87},{"id":"1909.03403","title":"Open Compound Domain Adaptation","created":"2019-09-08","cited_by_count":76},{"id":"2004.06042","title":"Adversarial Style Mining for One-Shot Unsupervised Domain Adaptation","created":"2020-04-13","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":"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":"2002.08325","title":"VQA-LOL: Visual Question Answering under the Lens of Logic","created":"2020-02-19","cited_by_count":48},{"id":"1911.10033","title":"Domain Adaptation for Object Detection via Style Consistency","created":"2019-11-22","cited_by_count":45},{"id":"1902.07864","title":"Probabilistic Neural-symbolic Models for Interpretable Visual Question Answering","created":"2019-02-21","cited_by_count":38},{"id":"2006.11524","title":"Neuro-Symbolic Visual Reasoning: Disentangling \"Visual\" from \"Reasoning\"","created":"2020-06-20","cited_by_count":35},{"id":"1910.10563","title":"Domain Bridge for Unpaired Image-to-Image Translation and Unsupervised Domain Adaptation","created":"2019-10-23","cited_by_count":32},{"id":"1801.01726","title":"Semantic-aware Grad-GAN for Virtual-to-Real Urban Scene Adaption","created":"2018-01-05","cited_by_count":27},{"id":"1711.06232","title":"A Novel Framework for Robustness Analysis of Visual QA Models","created":"2017-11-16","cited_by_count":20},{"id":"1807.09384","title":"Domain Stylization: A Strong, Simple Baseline for Synthetic to Real Image Domain Adaptation","created":"2018-07-24","cited_by_count":18},{"id":"1806.03726","title":"Cross-Dataset Adaptation for Visual Question Answering","created":"2018-06-10","cited_by_count":17},{"id":"1803.08896","title":"Explicit Reasoning over End-to-End Neural Architectures for Visual Question Answering","created":"2018-03-23","cited_by_count":12},{"id":"1911.04058","title":"Open-Ended Visual Question Answering by Multi-Modal Domain Adaptation","created":"2019-11-11","cited_by_count":12},{"id":"1811.08481","title":"VQA with no questions-answers training","created":"2018-11-20","cited_by_count":7},{"id":"1812.11139","title":"Artistic Object Recognition by Unsupervised Style Adaptation","created":"2018-12-28","cited_by_count":5},{"id":"1911.03385","title":"Low-Level Linguistic Controls for Style Transfer and Content Preservation","created":"2019-11-08","cited_by_count":3}],"next_cursor":null}