{"list":"other","total":66,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"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":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"1611.07308","title":"Variational Graph Auto-Encoders","created":"2016-11-21","cited_by_count":1382},{"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":"2010.13902","title":"Graph Contrastive Learning with Augmentations","created":"2020-10-22","cited_by_count":1208},{"id":"1802.08773","title":"GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models","created":"2018-02-24","cited_by_count":413},{"id":"1805.11973","title":"MolGAN: An implicit generative model for small molecular graphs","created":"2018-05-30","cited_by_count":393},{"id":"1802.03480","title":"GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders","created":"2018-02-09","cited_by_count":383},{"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":"1906.10770","title":"Deep Modular Co-Attention Networks for Visual Question Answering","created":"2019-06-25","cited_by_count":339},{"id":"2006.06195","title":"Large-Scale Adversarial Training for Vision-and-Language Representation Learning","created":"2020-06-11","cited_by_count":327},{"id":"2001.09382","title":"GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation","created":"2020-01-26","cited_by_count":305},{"id":"2004.06100","title":"Pretrained Transformers Improve Out-of-Distribution Robustness","created":"2020-04-13","cited_by_count":294},{"id":"1805.07932","title":"Bilinear Attention Networks","created":"2018-05-21","cited_by_count":280},{"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":"1910.00760","title":"Efficient Graph Generation with Graph Recurrent Attention Networks","created":"2019-10-02","cited_by_count":234},{"id":"1809.07041","title":"Exploring Visual Relationship for Image Captioning","created":"2018-09-19","cited_by_count":215},{"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":"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":"1711.08267","title":"GraphGAN: Graph Representation Learning with Generative Adversarial Nets","created":"2017-11-22","cited_by_count":121},{"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":"1803.10459","title":"Graphite: Iterative Generative Modeling of Graphs","created":"2018-03-28","cited_by_count":112},{"id":"1511.05099","title":"Yin and Yang: Balancing and Answering Binary Visual Questions","created":"2015-11-16","cited_by_count":109},{"id":"1711.04203","title":"Building machines that adapt and compute like brains","created":"2017-11-11","cited_by_count":99},{"id":"2003.06988","title":"House-GAN: Relational Generative Adversarial Networks for Graph-constrained House Layout Generation","created":"2020-03-16","cited_by_count":87},{"id":"1802.04407","title":"Adversarially Regularized Graph Autoencoder for Graph Embedding","created":"2018-02-13","cited_by_count":84},{"id":"2008.09105","title":"Location-aware Graph Convolutional Networks for Video Question Answering","created":"2020-08-07","cited_by_count":80},{"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":"2006.05121","title":"Roses Are Red, Violets Are Blue... but Should Vqa Expect Them To?","created":"2020-06-09","cited_by_count":69},{"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":"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":"2004.08814","title":"Graph-Structured Referring Expression Reasoning in The Wild","created":"2020-04-19","cited_by_count":58},{"id":"2010.10802","title":"Removing Bias in Multi-modal Classifiers: Regularization by Maximizing Functional Entropies","created":"2020-10-21","cited_by_count":57},{"id":"1905.04405","title":"Language-Conditioned Graph Networks for Relational Reasoning","created":"2019-05-10","cited_by_count":55},{"id":"2006.09073","title":"Mucko: Multi-Layer Cross-Modal Knowledge Reasoning for Fact-based Visual Question Answering","created":"2020-06-16","cited_by_count":51},{"id":"1911.09042","title":"Learning Cross-modal Context Graph for Visual Grounding","created":"2019-11-20","cited_by_count":49},{"id":"2003.13962","title":"Multi-Modal Graph Neural Network for Joint Reasoning on Vision and Scene Text","created":"2020-03-31","cited_by_count":46},{"id":"2007.12146","title":"Spatially Aware Multimodal Transformers for TextVQA","created":"2020-07-23","cited_by_count":44},{"id":"2011.03856","title":"Learning to Model and Ignore Dataset Bias with Mixed Capacity Ensembles","created":"2020-11-07","cited_by_count":43},{"id":"2012.11528","title":"Overcoming Language Priors with Self-supervised Learning for Visual Question Answering","created":"2020-12-17","cited_by_count":43},{"id":"1910.03230","title":"Meta Module Network for Compositional Visual Reasoning","created":"2019-10-08","cited_by_count":39},{"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":"2010.16010","title":"Loss re-scaling VQA: Revisiting the LanguagePrior Problem from a Class-imbalance View","created":"2020-10-30","cited_by_count":36},{"id":"2002.11894","title":"Unshuffling Data for Improved Generalization","created":"2020-02-27","cited_by_count":35},{"id":"2007.06198","title":"Reducing Language Biases in Visual Question Answering with Visually-Grounded Question Encoder","created":"2020-07-13","cited_by_count":34},{"id":"1910.07762","title":"Learning Energy-Based Models in High-Dimensional Spaces with Multi-scale Denoising Score Matching","created":"2019-10-17","cited_by_count":26},{"id":"1711.07838","title":"Adversarial Network Embedding","created":"2017-11-21","cited_by_count":25},{"id":"1906.08430","title":"Adversarial Regularization for Visual Question Answering: Strengths, Shortcomings, and Side Effects","created":"2019-06-20","cited_by_count":25},{"id":"1908.02127","title":"Aligning Linguistic Words and Visual Semantic Units for Image Captioning","created":"2019-08-06","cited_by_count":25},{"id":"1905.04877","title":"Quantifying and Alleviating the Language Prior Problem in Visual Question Answering","created":"2019-05-13","cited_by_count":13},{"id":"1912.01899","title":"Distribution-induced Bidirectional Generative Adversarial Network for Graph Representation Learning","created":"2019-12-04","cited_by_count":13},{"id":"1904.02865","title":"Actively Seeking and Learning from Live Data","created":"2019-04-05","cited_by_count":9},{"id":"1906.01861","title":"Scalable Generative Models for Graphs with Graph Attention Mechanism","created":"2019-06-05","cited_by_count":8},{"id":"2012.11134","title":"Learning content and context with language bias for Visual Question Answering","created":"2020-12-21","cited_by_count":7}],"next_cursor":null}