{"list":"other","total":59,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"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":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"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":"1912.01865","title":"StarGAN v2: Diverse Image Synthesis for Multiple Domains","created":"2019-12-04","cited_by_count":1098},{"id":"1612.03716","title":"COCO-Stuff: Thing and Stuff Classes in Context","created":"2016-12-12","cited_by_count":864},{"id":"1606.05328","title":"Conditional Image Generation with PixelCNN Decoders","created":"2016-06-16","cited_by_count":862},{"id":"1601.06759","title":"Pixel Recurrent Neural Networks","created":"2016-01-25","cited_by_count":816},{"id":"1804.04732","title":"Multimodal Unsupervised Image-to-Image Translation","created":"2018-04-12","cited_by_count":795},{"id":"2007.15651","title":"Contrastive Learning for Unpaired Image-to-Image Translation","created":"2020-07-30","cited_by_count":639},{"id":"1606.05908","title":"Tutorial on Variational Autoencoders","created":"2016-06-19","cited_by_count":409},{"id":"1711.11586","title":"Toward Multimodal Image-to-Image Translation","created":"2017-11-30","cited_by_count":296},{"id":"1911.12861","title":"SEAN: Image Synthesis with Semantic Region-Adaptive Normalization","created":"2019-11-28","cited_by_count":253},{"id":"1705.09368","title":"Pose Guided Person Image Generation","created":"2017-05-25","cited_by_count":251},{"id":"1905.01270","title":"DRIT++: Diverse Image-to-Image Translation via Disentangled Representations","created":"2019-05-02","cited_by_count":244},{"id":"1711.10433","title":"Parallel WaveNet: Fast High-Fidelity Speech Synthesis","created":"2017-11-28","cited_by_count":215},{"id":"1903.05854","title":"MirrorGAN: Learning Text-to-image Generation by Redescription","created":"2019-03-14","cited_by_count":176},{"id":"1411.0030","title":"A* Sampling","created":"2014-10-31","cited_by_count":151},{"id":"2003.12267","title":"Controllable Person Image Synthesis with Attribute-Decomposed GAN","created":"2020-03-27","cited_by_count":150},{"id":"1901.06003","title":"Gromov-Wasserstein Learning for Graph Matching and Node Embedding","created":"2019-01-17","cited_by_count":126},{"id":"1910.00292","title":"Generalization in Generation: A closer look at Exposure Bias","created":"2019-10-01","cited_by_count":123},{"id":"1911.02469","title":"Don't Blame the ELBO! A Linear VAE Perspective on Posterior Collapse","created":"2019-11-06","cited_by_count":121},{"id":"2004.05571","title":"Cross-domain Correspondence Learning for Exemplar-based Image Translation","created":"2020-04-12","cited_by_count":116},{"id":"1811.11389","title":"Image Generation from Layout","created":"2018-11-28","cited_by_count":105},{"id":"1908.07500","title":"Image Synthesis From Reconfigurable Layout and Style","created":"2019-08-20","cited_by_count":85},{"id":"1905.10124","title":"Sliced Gromov-Wasserstein","created":"2019-05-24","cited_by_count":66},{"id":"1704.08292","title":"Deep Cross-Modal Audio-Visual Generation","created":"2017-04-26","cited_by_count":63},{"id":"1612.08727","title":"Creating A Multi-track Classical Musical Performance Dataset for Multimodal Music Analysis: Challenges, Insights, and Applications","created":"2016-12-27","cited_by_count":61},{"id":"2003.12697","title":"Semantically Multi-modal Image Synthesis","created":"2020-03-28","cited_by_count":58},{"id":"2112.13592","title":"Multimodal Image Synthesis and Editing: The Generative AI Era","created":"2021-12-27","cited_by_count":52},{"id":"1906.07651","title":"Scheduled Sampling for Transformers","created":"2019-06-18","cited_by_count":48},{"id":"2012.11116","title":"EMLight: Lighting Estimation via Spherical Distribution Approximation","created":"2020-12-21","cited_by_count":48},{"id":"1805.11145","title":"Exemplar Guided Unsupervised Image-to-Image Translation with Semantic Consistency","created":"2018-05-28","cited_by_count":41},{"id":"2106.10482","title":"Unbalanced Feature Transport for Exemplar-based Image Translation","created":"2021-06-19","cited_by_count":41},{"id":"1907.09653","title":"GA-DAN: Geometry-Aware Domain Adaptation Network for Scene Text Detection and Recognition","created":"2019-07-23","cited_by_count":37},{"id":"1908.00999","title":"Cycle In Cycle Generative Adversarial Networks for Keypoint-Guided Image Generation","created":"2019-08-02","cited_by_count":34},{"id":"1906.01314","title":"Example-Guided Style Consistent Image Synthesis from Semantic Labeling","created":"2019-06-04","cited_by_count":29},{"id":"2102.10244","title":"GMLight: Lighting Estimation via Geometric Distribution Approximation","created":"2021-02-20","cited_by_count":28},{"id":"2203.09333","title":"Modulated Contrast for Versatile Image Synthesis","created":"2022-03-17","cited_by_count":23},{"id":"2003.11690","title":"BachGAN: High-Resolution Image Synthesis from Salient Object Layout","created":"2020-03-26","cited_by_count":22},{"id":"2002.02913","title":"Learning Autoencoders with Relational Regularization","created":"2020-02-07","cited_by_count":20},{"id":"2107.03021","title":"Bi-level Feature Alignment for Versatile Image Translation and Manipulation","created":"2021-07-07","cited_by_count":20},{"id":"2204.00442","title":"Marginal Contrastive Correspondence for Guided Image Generation","created":"2022-04-01","cited_by_count":19},{"id":"2207.02812","title":"Towards Counterfactual Image Manipulation via CLIP","created":"2022-07-06","cited_by_count":19},{"id":"1801.07745","title":"Optimal Transport on Discrete Domains","created":"2018-01-23","cited_by_count":16},{"id":"1911.11312","title":"Spatial-Aware GAN for Unsupervised Person Re-identification","created":"2019-11-26","cited_by_count":13},{"id":"2002.09928","title":"Predictive Sampling with Forecasting Autoregressive Models","created":"2020-02-23","cited_by_count":10},{"id":"2107.10427","title":"Confidence-Aware Scheduled Sampling for Neural Machine Translation","created":"2021-07-22","cited_by_count":10}],"next_cursor":null}