{"list":"other","total":52,"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":"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"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":"1705.09406","title":"Multimodal Machine Learning: A Survey and Taxonomy","created":"2017-05-26","cited_by_count":1013},{"id":"1411.4555","title":"Show and Tell: A Neural Image Caption Generator","created":"2014-11-17","cited_by_count":879},{"id":"1811.10830","title":"From Recognition to Cognition: Visual Commonsense Reasoning","created":"2018-11-27","cited_by_count":556},{"id":"1508.01991","title":"Bidirectional LSTM-CRF Models for Sequence Tagging","created":"2015-08-09","cited_by_count":546},{"id":"1811.08883","title":"Rethinking ImageNet Pre-training","created":"2018-11-21","cited_by_count":377},{"id":"1511.02799","title":"Neural Module Networks","created":"2015-11-09","cited_by_count":376},{"id":"1906.10770","title":"Deep Modular Co-Attention Networks for Visual Question Answering","created":"2019-06-25","cited_by_count":339},{"id":"1608.00187","title":"Visual Relationship Detection with Language Priors","created":"2016-07-31","cited_by_count":334},{"id":"1904.09223","title":"ERNIE: Enhanced Representation through Knowledge Integration","created":"2019-04-19","cited_by_count":302},{"id":"1908.06954","title":"Attention on Attention for Image Captioning","created":"2019-08-19","cited_by_count":289},{"id":"1812.02378","title":"Auto-Encoding Scene Graphs for Image Captioning","created":"2018-12-06","cited_by_count":255},{"id":"1701.05923","title":"Gate-Variants of Gated Recurrent Unit (GRU) Neural Networks","created":"2017-01-20","cited_by_count":242},{"id":"1504.07889","title":"Bilinear CNNs for Fine-grained Visual Recognition","created":"2015-04-29","cited_by_count":228},{"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":"1502.04623","title":"DRAW: A Recurrent Neural Network For Image Generation","created":"2015-02-16","cited_by_count":191},{"id":"1409.2329","title":"Recurrent Neural Network Regularization","created":"2014-09-08","cited_by_count":189},{"id":"1606.05433","title":"FVQA: Fact-based Visual Question Answering","created":"2016-06-17","cited_by_count":181},{"id":"1705.06676","title":"MUTAN: Multimodal Tucker Fusion for Visual Question Answering","created":"2017-05-18","cited_by_count":137},{"id":"1701.01779","title":"Towards Accurate Multi-person Pose Estimation in the Wild","created":"2017-01-06","cited_by_count":131},{"id":"1607.05910","title":"Visual Question Answering: A Survey of Methods and Datasets","created":"2016-07-20","cited_by_count":123},{"id":"1506.07285","title":"Ask Me Anything: Dynamic Memory Networks for Natural Language Processing","created":"2015-06-24","cited_by_count":117},{"id":"1601.01705","title":"Learning to Compose Neural Networks for Question Answering","created":"2016-01-07","cited_by_count":85},{"id":"1907.07237","title":"FAHT: An Adaptive Fairness-aware Decision Tree Classifier","created":"2019-07-16","cited_by_count":63},{"id":"1603.01417","title":"Dynamic Memory Networks for Visual and Textual Question Answering","created":"2016-03-04","cited_by_count":62},{"id":"1505.01121","title":"Ask Your Neurons: A Neural-based Approach to Answering Questions about Images","created":"2015-05-05","cited_by_count":51},{"id":"1606.01455","title":"Multimodal Residual Learning for Visual QA","created":"2016-06-05","cited_by_count":42},{"id":"1607.03476","title":"End-to-end training of object class detectors for mean average precision","created":"2016-07-12","cited_by_count":35},{"id":"2005.13837","title":"Generating Diverse and Consistent QA pairs from Contexts with Information-Maximizing Hierarchical Conditional VAEs","created":"2020-05-28","cited_by_count":31},{"id":"2010.07276","title":"Disentangled Dynamic Graph Deep Generation","created":"2020-10-14","cited_by_count":27},{"id":"1901.10170","title":"Mask-RCNN and U-net Ensembled for Nuclei Segmentation","created":"2019-01-29","cited_by_count":23},{"id":"1808.08315","title":"A Deterministic Self-Organizing Map Approach and its Application on Satellite Data based Cloud Type Classification","created":"2018-08-24","cited_by_count":22},{"id":"1903.00366","title":"Answer Them All! Toward Universal Visual Question Answering Models","created":"2019-03-01","cited_by_count":17},{"id":"2012.03151","title":"Using Machine Learning to Automate Mammogram Images Analysis","created":"2020-12-06","cited_by_count":15},{"id":"2010.08146","title":"Online and Customizable Fairness-aware Learning","created":"2020-10-15","cited_by_count":14},{"id":"2103.14804","title":"LSTM Based Sentiment Analysis for Cryptocurrency Prediction","created":"2021-03-27","cited_by_count":14},{"id":"1606.03647","title":"Training Recurrent Answering Units with Joint Loss Minimization for VQA","created":"2016-06-12","cited_by_count":9},{"id":"2012.03190","title":"A Data-driven Human Responsibility Management System","created":"2020-12-06","cited_by_count":8},{"id":"2004.09376","title":"Conditional-UNet: A Condition-aware Deep Model for Coherent Human Activity Recognition From Wearables","created":"2020-04-15","cited_by_count":7},{"id":"2102.07246","title":"Responsibility Management through Responsibility Networks","created":"2021-02-14","cited_by_count":3}],"next_cursor":null}