{"list":"other","total":51,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"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":"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":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"id":"2007.07314","title":"Long-tail learning via logit adjustment","created":"2020-07-14","cited_by_count":618},{"id":"1603.01360","title":"Neural Architectures for Named Entity Recognition","created":"2016-03-04","cited_by_count":550},{"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":"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":"1511.02274","title":"Stacked Attention Networks for Image Question Answering","created":"2015-11-07","cited_by_count":273},{"id":"2006.04315","title":"Counterfactual VQA: A Cause-Effect Look at Language Bias","created":"2020-06-08","cited_by_count":266},{"id":"1908.11540","title":"DialogueGCN: A Graph Convolutional Neural Network for Emotion Recognition in Conversation","created":"2019-08-30","cited_by_count":186},{"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":"1903.12314","title":"Relation-Aware Graph Attention Network for Visual Question Answering","created":"2019-03-29","cited_by_count":119},{"id":"1907.03950","title":"Learning by Abstraction: The Neural State Machine","created":"2019-07-09","cited_by_count":113},{"id":"1810.03649","title":"Overcoming Language Priors in Visual Question Answering with Adversarial Regularization","created":"2018-10-08","cited_by_count":105},{"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":"1902.09487","title":"MUREL: Multimodal Relational Reasoning for Visual Question Answering","created":"2019-02-25","cited_by_count":68},{"id":"2004.09034","title":"Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision","created":"2020-04-20","cited_by_count":66},{"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":"1601.05150","title":"Factors in Finetuning Deep Model for object detection","created":"2016-01-20","cited_by_count":53},{"id":"2012.11528","title":"Overcoming Language Priors with Self-supervised Learning for Visual Question Answering","created":"2020-12-17","cited_by_count":43},{"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":"2107.12651","title":"Greedy Gradient Ensemble for Robust Visual Question Answering","created":"2021-07-27","cited_by_count":34},{"id":"1906.08430","title":"Adversarial Regularization for Visual Question Answering: Strengths, Shortcomings, and Side Effects","created":"2019-06-20","cited_by_count":25},{"id":"2012.02356","title":"WeaQA: Weak Supervision via Captions for Visual Question Answering","created":"2020-12-04","cited_by_count":25},{"id":"1909.11983","title":"Subjective and Objective De-raining Quality Assessment Towards Authentic Rain Image","created":"2019-09-26","cited_by_count":18},{"id":"2004.05704","title":"Visual Grounding Methods for VQA are Working for the Wrong Reasons!","created":"2020-04-12","cited_by_count":18},{"id":"2105.01993","title":"AdaVQA: Overcoming Language Priors with Adapted Margin Cosine Loss","created":"2021-05-05","cited_by_count":18},{"id":"2106.04605","title":"Check It Again: Progressive Visual Question Answering via Visual Entailment","created":"2021-06-08","cited_by_count":18},{"id":"2105.14300","title":"LPF: A Language-Prior Feedback Objective Function for De-biased Visual Question Answering","created":"2021-05-29","cited_by_count":17},{"id":"2012.07192","title":"Knowledge-Routed Visual Question Reasoning: Challenges for Deep Representation Embedding","created":"2020-12-14","cited_by_count":16},{"id":"1910.05886","title":"A New Local Transformation Module for Few-shot Segmentation","created":"2019-10-14","cited_by_count":15},{"id":"2107.11576","title":"X-GGM: Graph Generative Modeling for Out-of-Distribution Generalization in Visual Question Answering","created":"2021-07-24","cited_by_count":10},{"id":"1904.02865","title":"Actively Seeking and Learning from Live Data","created":"2019-04-05","cited_by_count":9},{"id":"2012.11134","title":"Learning content and context with language bias for Visual Question Answering","created":"2020-12-21","cited_by_count":7},{"id":"2104.01888","title":"Non-Homogeneous Haze Removal via Artificial Scene Prior and Bidimensional Graph Reasoning","created":"2021-04-05","cited_by_count":6},{"id":"1909.08754","title":"A New Few-shot Segmentation Network Based on Class Representation","created":"2019-09-19","cited_by_count":4},{"id":"2106.13445","title":"A Picture May Be Worth a Hundred Words for Visual Question Answering","created":"2021-06-25","cited_by_count":3},{"id":"2006.05726","title":"Estimating semantic structure for the VQA answer space","created":"2020-06-10","cited_by_count":1}],"next_cursor":null}