{"list":"other","total":52,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"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":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"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":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"1712.00377","title":"Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering","created":"2017-12-01","cited_by_count":339},{"id":"1511.03416","title":"Visual7W: Grounded Question Answering in Images","created":"2015-11-11","cited_by_count":318},{"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":"2006.04315","title":"Counterfactual VQA: A Cause-Effect Look at Language Bias","created":"2020-06-08","cited_by_count":266},{"id":"1906.10169","title":"RUBi: Reducing Unimodal Biases in Visual Question Answering","created":"2019-06-24","cited_by_count":185},{"id":"2003.06576","title":"Counterfactual Samples Synthesizing for Robust Visual Question Answering","created":"2020-03-14","cited_by_count":153},{"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":"1606.07356","title":"Analyzing the Behavior of Visual Question Answering Models","created":"2016-06-23","cited_by_count":119},{"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":"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":"1708.03619","title":"Beyond Bilinear: Generalized Multimodal Factorized High-order Pooling for Visual Question Answering","created":"2017-08-10","cited_by_count":79},{"id":"2005.09241","title":"On the Value of Out-of-Distribution Testing: An Example of Goodhart's Law","created":"2020-05-19","cited_by_count":74},{"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":"1905.09998","title":"Self-Critical Reasoning for Robust Visual Question Answering","created":"2019-05-24","cited_by_count":61},{"id":"2010.10802","title":"Removing Bias in Multi-modal Classifiers: Regularization by Maximizing Functional Entropies","created":"2020-10-21","cited_by_count":57},{"id":"1708.04686","title":"VQS: Linking Segmentations to Questions and Answers for Supervised Attention in VQA and Question-Focused Semantic Segmentation","created":"2017-08-15","cited_by_count":50},{"id":"2002.08325","title":"VQA-LOL: Visual Question Answering under the Lens of Logic","created":"2020-02-19","cited_by_count":48},{"id":"2012.11528","title":"Overcoming Language Priors with Self-supervised Learning for Visual Question Answering","created":"2020-12-17","cited_by_count":43},{"id":"1709.07192","title":"Visual Question Generation as Dual Task of Visual Question Answering","created":"2017-09-21","cited_by_count":41},{"id":"1903.11207","title":"Information Maximizing Visual Question Generation","created":"2019-03-27","cited_by_count":40},{"id":"2012.08673","title":"A Closer Look at the Robustness of Vision-and-Language Pre-trained Models","created":"2020-12-15","cited_by_count":37},{"id":"1909.04696","title":"Sunny and Dark Outside?! Improving Answer Consistency in VQA through Entailed Question Generation","created":"2019-09-10","cited_by_count":36},{"id":"2102.08884","title":"MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection","created":"2021-02-17","cited_by_count":33},{"id":"2007.09592","title":"Semantic Equivalent Adversarial Data Augmentation for Visual Question Answering","created":"2020-07-19","cited_by_count":26},{"id":"1906.08430","title":"Adversarial Regularization for Visual Question Answering: Strengths, Shortcomings, and Side Effects","created":"2019-06-20","cited_by_count":25},{"id":"1907.12133","title":"An Empirical Study on Leveraging Scene Graphs for Visual Question Answering","created":"2019-07-28","cited_by_count":21},{"id":"2004.05704","title":"Visual Grounding Methods for VQA are Working for the Wrong Reasons!","created":"2020-04-12","cited_by_count":18},{"id":"1806.03726","title":"Cross-Dataset Adaptation for Visual Question Answering","created":"2018-06-10","cited_by_count":17},{"id":"1804.00298","title":"Differential Attention for Visual Question Answering","created":"2018-04-01","cited_by_count":12},{"id":"1704.07121","title":"Being Negative but Constructively: Lessons Learnt from Creating Better Visual Question Answering Datasets","created":"2017-04-24","cited_by_count":11},{"id":"1806.03724","title":"Learning Answer Embeddings for Visual Question Answering","created":"2018-06-10","cited_by_count":11},{"id":"1906.00513","title":"Generating Question Relevant Captions to Aid Visual Question Answering","created":"2019-06-03","cited_by_count":10},{"id":"1904.02865","title":"Actively Seeking and Learning from Live Data","created":"2019-04-05","cited_by_count":9},{"id":"2011.13406","title":"Learning from Lexical Perturbations for Consistent Visual Question Answering","created":"2020-11-26","cited_by_count":7},{"id":"1906.06216","title":"Improving Visual Question Answering by Referring to Generated Paragraph Captions","created":"2019-06-14","cited_by_count":6},{"id":"2010.06087","title":"Contrast and Classify: Training Robust VQA Models","created":"2020-10-13","cited_by_count":3},{"id":"2101.06399","title":"Latent Variable Models for Visual Question Answering","created":"2021-01-16","cited_by_count":2}],"next_cursor":null}