{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"1411.1784","title":"Conditional Generative Adversarial Nets","created":"2014-11-06","cited_by_count":2162},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"1802.05957","title":"Spectral Normalization for Generative Adversarial Networks","created":"2018-02-16","cited_by_count":1636},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1903.07291","title":"Semantic Image Synthesis with Spatially-Adaptive Normalization","created":"2019-03-18","cited_by_count":1299},{"id":"1711.11585","title":"High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs","created":"2017-11-30","cited_by_count":1179},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"1605.05396","title":"Generative Adversarial Text to Image Synthesis","created":"2016-05-17","cited_by_count":735},{"id":"1801.04406","title":"Which Training Methods for GANs do actually Converge?","created":"2018-01-13","cited_by_count":679},{"id":"1711.10485","title":"AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks","created":"2017-11-28","cited_by_count":664},{"id":"1612.03242","title":"StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks","created":"2016-12-10","cited_by_count":577},{"id":"1611.08669","title":"Visual Dialog","created":"2016-11-26","cited_by_count":377},{"id":"1912.08226","title":"Meshed-Memory Transformer for Image Captioning","created":"2019-12-17","cited_by_count":343},{"id":"2010.07468","title":"AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradients","created":"2020-10-15","cited_by_count":283},{"id":"1802.05637","title":"cGANs with Projection Discriminator","created":"2018-02-15","cited_by_count":254},{"id":"1812.07119","title":"Composing Text and Image for Image Retrieval - An Empirical Odyssey","created":"2018-12-18","cited_by_count":236},{"id":"1705.02894","title":"Geometric GAN","created":"2017-05-08","cited_by_count":233},{"id":"1701.02096","title":"Improved Texture Networks: Maximizing Quality and Diversity in Feed-forward Stylization and Texture Synthesis","created":"2017-01-09","cited_by_count":215},{"id":"1803.03067","title":"Compositional Attention Networks for Machine Reasoning","created":"2018-03-08","cited_by_count":183},{"id":"1912.06203","title":"ManiGAN: Text-Guided Image Manipulation","created":"2019-12-12","cited_by_count":156},{"id":"2001.07966","title":"ImageBERT: Cross-modal Pre-training with Large-scale Weak-supervised Image-Text Data","created":"2020-01-22","cited_by_count":137},{"id":"2002.12655","title":"A U-Net Based Discriminator for Generative Adversarial Networks","created":"2020-02-28","cited_by_count":128},{"id":"1611.08481","title":"GuessWhat?! Visual object discovery through multi-modal dialogue","created":"2016-11-23","cited_by_count":113},{"id":"1411.4952","title":"From Captions to Visual Concepts and Back","created":"2014-11-18","cited_by_count":109},{"id":"1801.05091","title":"Inferring Semantic Layout for Hierarchical Text-to-Image Synthesis","created":"2018-01-16","cited_by_count":101},{"id":"1810.11919","title":"Text-Adaptive Generative Adversarial Networks: Manipulating Images with Natural Language","created":"2018-10-29","cited_by_count":90},{"id":"1612.09542","title":"A Joint Speaker-Listener-Reinforcer Model for Referring Expressions","created":"2016-12-30","cited_by_count":74},{"id":"1901.00850","title":"CLEVR-Ref+: Diagnosing Visual Reasoning with Referring Expressions","created":"2019-01-03","cited_by_count":73},{"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":"1701.03439","title":"Comprehension-guided referring expressions","created":"2017-01-12","cited_by_count":52},{"id":"1904.05880","title":"Factor Graph Attention","created":"2019-04-11","cited_by_count":41},{"id":"2009.09566","title":"SSCR: Iterative Language-Based Image Editing via Self-Supervised Counterfactual Reasoning","created":"2020-09-21","cited_by_count":32},{"id":"2008.04556","title":"Text as Neural Operator: Image Manipulation by Text Instruction","created":"2020-08-11","cited_by_count":26},{"id":"1612.06530","title":"Automatic Generation of Grounded Visual Questions","created":"2016-12-20","cited_by_count":19},{"id":"1703.05423","title":"End-to-end optimization of goal-driven and visually grounded dialogue systems","created":"2017-03-15","cited_by_count":17},{"id":"1809.03408","title":"Beyond task success: A closer look at jointly learning to see, ask, and GuessWhat","created":"2018-09-10","cited_by_count":15},{"id":"1908.07094","title":"Unpaired Image-to-Speech Synthesis with Multimodal Information Bottleneck","created":"2019-08-19","cited_by_count":15},{"id":"1907.12021","title":"What Should I Ask? Using Conversationally Informative Rewards for Goal-Oriented Visual Dialog","created":"2019-07-28","cited_by_count":14},{"id":"1911.07928","title":"Visual Dialogue State Tracking for Question Generation","created":"2019-11-12","cited_by_count":13},{"id":"1711.07614","title":"Asking the Difficult Questions: Goal-Oriented Visual Question Generation via Intermediate Rewards","created":"2017-11-21","cited_by_count":7},{"id":"1806.03847","title":"A Multimodal Classifier Generative Adversarial Network for Carry and Place Tasks from Ambiguous Language Instructions","created":"2018-06-11","cited_by_count":7},{"id":"1812.06398","title":"Gold Seeker: Information Gain from Policy Distributions for Goal-oriented Vision-and-Langauge Reasoning","created":"2018-12-16","cited_by_count":5},{"id":"1812.06401","title":"What's to know? Uncertainty as a Guide to Asking Goal-oriented Questions","created":"2018-12-16","cited_by_count":5}],"next_cursor":null}