{"list":"other","total":68,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"id":"1811.12231","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","created":"2018-11-29","cited_by_count":1432},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"1903.07291","title":"Semantic Image Synthesis with Spatially-Adaptive Normalization","created":"2019-03-18","cited_by_count":1299},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"1711.11585","title":"High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs","created":"2017-11-30","cited_by_count":1179},{"id":"1711.07280","title":"Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments","created":"2017-11-20","cited_by_count":1027},{"id":"1912.01734","title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks","created":"2019-12-03","cited_by_count":783},{"id":"1807.06757","title":"On Evaluation of Embodied Navigation Agents","created":"2018-07-18","cited_by_count":547},{"id":"2010.07954","title":"Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding","created":"2020-10-15","cited_by_count":414},{"id":"1712.04621","title":"The Effectiveness of Data Augmentation in Image Classification using Deep Learning","created":"2017-12-13","cited_by_count":370},{"id":"1610.07629","title":"A Learned Representation For Artistic Style","created":"2016-10-24","cited_by_count":341},{"id":"1806.02724","title":"Speaker-Follower Models for Vision-and-Language Navigation","created":"2018-06-07","cited_by_count":340},{"id":"2107.06383","title":"How Much Can CLIP Benefit Vision-and-Language Tasks?","created":"2021-07-13","cited_by_count":321},{"id":"1811.10092","title":"Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation","created":"2018-11-25","cited_by_count":305},{"id":"2011.13922","title":"A Recurrent Vision-and-Language BERT for Navigation","created":"2020-11-26","cited_by_count":302},{"id":"2110.13309","title":"History Aware Multimodal Transformer for Vision-and-Language Navigation","created":"2021-10-25","cited_by_count":271},{"id":"1907.04957","title":"Vision-and-Dialog Navigation","created":"2019-07-10","cited_by_count":250},{"id":"1904.04195","title":"Learning to Navigate Unseen Environments: Back Translation with Environmental Dropout","created":"2019-04-08","cited_by_count":244},{"id":"1811.12354","title":"Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments","created":"2018-11-29","cited_by_count":239},{"id":"1705.02894","title":"Geometric GAN","created":"2017-05-08","cited_by_count":233},{"id":"2002.10638","title":"Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training","created":"2020-02-25","cited_by_count":231},{"id":"1911.07883","title":"Vision-Language Navigation with Self-Supervised Auxiliary Reasoning Tasks","created":"2019-11-18","cited_by_count":179},{"id":"2004.14973","title":"Improving Vision-and-Language Navigation with Image-Text Pairs from the Web","created":"2020-04-30","cited_by_count":177},{"id":"1901.03035","title":"Self-Monitoring Navigation Agent via Auxiliary Progress Estimation","created":"2019-01-10","cited_by_count":176},{"id":"1912.06203","title":"ManiGAN: Text-Guided Image Manipulation","created":"2019-12-12","cited_by_count":156},{"id":"1807.10225","title":"Medical Image Synthesis for Data Augmentation and Anonymization using Generative Adversarial Networks","created":"2018-07-26","cited_by_count":147},{"id":"1905.12255","title":"Stay on the Path: Instruction Fidelity in Vision-and-Language Navigation","created":"2019-05-29","cited_by_count":130},{"id":"2108.09105","title":"Airbert: In-domain Pretraining for Vision-and-Language Navigation","created":"2021-08-20","cited_by_count":130},{"id":"2103.17138","title":"SOON: Scenario Oriented Object Navigation with Graph-based Exploration","created":"2021-03-31","cited_by_count":119},{"id":"2105.08756","title":"Pathdreamer: A World Model for Indoor Navigation","created":"2021-05-18","cited_by_count":118},{"id":"1810.10863","title":"GAN Augmentation: Augmenting Training Data using Generative Adversarial Networks","created":"2018-10-25","cited_by_count":107},{"id":"2103.10951","title":"Paint by Word","created":"2021-03-19","cited_by_count":107},{"id":"1907.05446","title":"General Evaluation for Instruction Conditioned Navigation using Dynamic Time Warping","created":"2019-07-11","cited_by_count":105},{"id":"1809.00786","title":"Mapping Instructions to Actions in 3D Environments with Visual Goal Prediction","created":"2018-09-04","cited_by_count":101},{"id":"1909.01871","title":"Help, Anna! Visual Navigation with Natural Multimodal Assistance via Retrospective Curiosity-Encouraging Imitation Learning","created":"2019-09-04","cited_by_count":100},{"id":"2010.09304","title":"Language and Visual Entity Relationship Graph for Agent Navigation","created":"2020-10-19","cited_by_count":100},{"id":"1801.02929","title":"Data Augmentation by Pairing Samples for Images Classification","created":"2018-01-09","cited_by_count":96},{"id":"1810.11919","title":"Text-Adaptive Generative Adversarial Networks: Manipulating Images with Natural Language","created":"2018-10-29","cited_by_count":90},{"id":"1705.06830","title":"Exploring the structure of a real-time, arbitrary neural artistic stylization network","created":"2017-05-18","cited_by_count":89},{"id":"1707.06873","title":"Semantic Image Synthesis via Adversarial Learning","created":"2017-07-21","cited_by_count":87},{"id":"1809.05375","title":"Style Augmentation: Data Augmentation via Style Randomization","created":"2018-09-14","cited_by_count":79},{"id":"2106.07876","title":"Vision-Language Navigation with Random Environmental Mixup","created":"2021-06-15","cited_by_count":70},{"id":"1811.09845","title":"Tell, Draw, and Repeat: Generating and Modifying Images Based on Continual Linguistic Instruction","created":"2018-11-24","cited_by_count":61},{"id":"1711.06288","title":"Language-Based Image Editing with Recurrent Attentive Models","created":"2017-11-16","cited_by_count":53},{"id":"2110.14143","title":"SOAT: A Scene- and Object-Aware Transformer for Vision-and-Language Navigation","created":"2021-10-27","cited_by_count":53},{"id":"1506.04089","title":"Listen, Attend, and Walk: Neural Mapping of Navigational Instructions to Action Sequences","created":"2015-06-12","cited_by_count":50},{"id":"2005.04625","title":"BabyWalk: Going Farther in Vision-and-Language Navigation by Taking Baby Steps","created":"2020-05-10","cited_by_count":49},{"id":"1908.03409","title":"Transferable Representation Learning in Vision-and-Language Navigation","created":"2019-08-09","cited_by_count":48},{"id":"2101.10504","title":"On the Evaluation of Vision-and-Language Navigation Instructions","created":"2021-01-26","cited_by_count":45},{"id":"2003.00443","title":"Environment-agnostic Multitask Learning for Natural Language Grounded Navigation","created":"2020-03-01","cited_by_count":43},{"id":"2005.03086","title":"Diagnosing the Environment Bias in Vision-and-Language Navigation","created":"2020-05-06","cited_by_count":41},{"id":"1812.08352","title":"Sequential Attention GAN for Interactive Image Editing","created":"2018-12-20","cited_by_count":33},{"id":"2104.09580","title":"Improving Cross-Modal Alignment in Vision Language Navigation via Syntactic Information","created":"2021-04-19","cited_by_count":31},{"id":"1903.00401","title":"Learning To Follow Directions in Street View","created":"2019-03-01","cited_by_count":29},{"id":"2008.04200","title":"Describe What to Change: A Text-guided Unsupervised Image-to-Image Translation Approach","created":"2020-08-10","cited_by_count":29},{"id":"2007.00229","title":"Multimodal Text Style Transfer for Outdoor Vision-and-Language Navigation","created":"2020-07-01","cited_by_count":22},{"id":"1909.01056","title":"STaDA: Style Transfer as Data Augmentation","created":"2019-09-03","cited_by_count":21},{"id":"1711.00648","title":"Data Augmentation in Emotion Classification Using Generative Adversarial Networks","created":"2017-11-02","cited_by_count":19},{"id":"1911.12377","title":"Multimodal Attention Networks for Low-Level Vision-and-Language Navigation","created":"2019-11-27","cited_by_count":17},{"id":"1802.08645","title":"Interactive Image Manipulation with Natural Language Instruction Commands","created":"2018-02-23","cited_by_count":4}],"next_cursor":null}