{"list":"other","total":61,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1710.10196","title":"Progressive Growing of GANs for Improved Quality, Stability, and Variation","created":"2017-10-27","cited_by_count":2988},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1803.02155","title":"Self-Attention with Relative Position Representations","created":"2018-03-06","cited_by_count":1120},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"1802.05751","title":"Image Transformer","created":"2018-02-15","cited_by_count":772},{"id":"1605.05396","title":"Generative Adversarial Text to Image Synthesis","created":"2016-05-17","cited_by_count":735},{"id":"2105.13290","title":"CogView: Mastering Text-to-Image Generation via Transformers","created":"2021-05-26","cited_by_count":694},{"id":"1801.04406","title":"Which Training Methods for GANs do actually Converge?","created":"2018-01-13","cited_by_count":679},{"id":"1708.06519","title":"Learning Efficient Convolutional Networks through Network Slimming","created":"2017-08-22","cited_by_count":676},{"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":"1906.05909","title":"Stand-Alone Self-Attention in Vision Models","created":"2019-06-13","cited_by_count":542},{"id":"2102.04906","title":"Dynamic Neural Networks: A Survey","created":"2021-02-09","cited_by_count":408},{"id":"1804.01622","title":"Image Generation from Scene Graphs","created":"2018-04-04","cited_by_count":324},{"id":"1904.01310","title":"DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis","created":"2019-04-02","cited_by_count":308},{"id":"2101.04702","title":"Cross-Modal Contrastive Learning for Text-to-Image Generation","created":"2021-01-12","cited_by_count":259},{"id":"1705.02894","title":"Geometric GAN","created":"2017-05-08","cited_by_count":233},{"id":"1710.10916","title":"StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks","created":"2017-10-19","cited_by_count":229},{"id":"1504.07889","title":"Bilinear CNNs for Fine-grained Visual Recognition","created":"2015-04-29","cited_by_count":228},{"id":"1801.01973","title":"A Note on the Inception Score","created":"2018-01-06","cited_by_count":226},{"id":"1909.07083","title":"Controllable Text-to-Image Generation","created":"2019-09-16","cited_by_count":187},{"id":"1903.05854","title":"MirrorGAN: Learning Text-to-image Generation by Redescription","created":"2019-03-14","cited_by_count":176},{"id":"1803.08495","title":"Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings","created":"2018-03-22","cited_by_count":169},{"id":"1511.06297","title":"Conditional Computation in Neural Networks for faster models","created":"2015-11-19","cited_by_count":167},{"id":"1702.07811","title":"Adaptive Neural Networks for Efficient Inference","created":"2017-02-25","cited_by_count":163},{"id":"1711.11503","title":"Convolutional Networks with Adaptive Inference Graphs","created":"2017-11-30","cited_by_count":148},{"id":"2003.07326","title":"Resolution Adaptive Networks for Efficient Inference","created":"2020-03-16","cited_by_count":146},{"id":"1810.11579","title":"$A^2$-Nets: Double Attention Networks","created":"2018-10-27","cited_by_count":136},{"id":"2103.01209","title":"Generative Adversarial Transformers","created":"2021-03-01","cited_by_count":120},{"id":"1902.10740","title":"Object-driven Text-to-Image Synthesis via Adversarial Training","created":"2019-02-27","cited_by_count":117},{"id":"1910.13321","title":"Semantic Object Accuracy for Generative Text-to-Image Synthesis","created":"2019-10-29","cited_by_count":89},{"id":"2003.10401","title":"Learning Dynamic Routing for Semantic Segmentation","created":"2020-03-23","cited_by_count":79},{"id":"1904.01480","title":"Semantics Disentangling for Text-to-Image Generation","created":"2019-04-02","cited_by_count":61},{"id":"2009.11278","title":"X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers","created":"2020-09-23","cited_by_count":59},{"id":"2106.07631","title":"Improved Transformer for High-Resolution GANs","created":"2021-06-14","cited_by_count":59},{"id":"1711.08389","title":"Conditional Image-Text Embedding Networks","created":"2017-11-22","cited_by_count":50},{"id":"1909.11416","title":"Focus Your Attention: A Bidirectional Focal Attention Network for Image-Text Matching","created":"2019-09-25","cited_by_count":49},{"id":"2108.12141","title":"DAE-GAN: Dynamic Aspect-aware GAN for Text-to-Image Synthesis","created":"2021-08-27","cited_by_count":45},{"id":"1901.00686","title":"Generating Multiple Objects at Spatially Distinct Locations","created":"2019-01-03","cited_by_count":41},{"id":"2110.09753","title":"Unifying Multimodal Transformer for Bi-directional Image and Text Generation","created":"2021-10-19","cited_by_count":41},{"id":"2010.12136","title":"Lightweight Generative Adversarial Networks for Text-Guided Image Manipulation","created":"2020-10-23","cited_by_count":33},{"id":"2007.08617","title":"Preserving Semantic Neighborhoods for Robust Cross-modal Retrieval","created":"2020-07-16","cited_by_count":20},{"id":"2004.12198","title":"Quantifying the Contextualization of Word Representations with Semantic Class Probing","created":"2020-04-25","cited_by_count":18},{"id":"2005.13192","title":"TIME: Text and Image Mutual-Translation Adversarial Networks","created":"2020-05-27","cited_by_count":9},{"id":"1809.02094","title":"Uncovering divergent linguistic information in word embeddings with lessons for intrinsic and extrinsic evaluation","created":"2018-09-06","cited_by_count":8},{"id":"2105.10189","title":"Combining Transformer Generators with Convolutional Discriminators","created":"2021-05-21","cited_by_count":5},{"id":"2110.08143","title":"Multi-Tailed, Multi-Headed, Spatial Dynamic Memory refined Text-to-Image Synthesis","created":"2021-10-15","cited_by_count":2}],"next_cursor":null}