{"list":"other","total":61,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"1710.10196","title":"Progressive Growing of GANs for Improved Quality, Stability, and Variation","created":"2017-10-27","cited_by_count":2988},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"1603.05027","title":"Identity Mappings in Deep Residual Networks","created":"2016-03-16","cited_by_count":1965},{"id":"1903.07291","title":"Semantic Image Synthesis with Spatially-Adaptive Normalization","created":"2019-03-18","cited_by_count":1299},{"id":"1607.08022","title":"Instance Normalization: The Missing Ingredient for Fast Stylization","created":"2016-07-27","cited_by_count":1198},{"id":"1912.01865","title":"StarGAN v2: Diverse Image Synthesis for Multiple Domains","created":"2019-12-04","cited_by_count":1098},{"id":"1711.09020","title":"StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation","created":"2017-11-24","cited_by_count":1039},{"id":"2103.17249","title":"StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery","created":"2021-03-31","cited_by_count":991},{"id":"1804.04732","title":"Multimodal Unsupervised Image-to-Image Translation","created":"2018-04-12","cited_by_count":795},{"id":"1801.04406","title":"Which Training Methods for GANs do actually Converge?","created":"2018-01-13","cited_by_count":679},{"id":"2007.15651","title":"Contrastive Learning for Unpaired Image-to-Image Translation","created":"2020-07-30","cited_by_count":639},{"id":"1703.00848","title":"Unsupervised Image-to-Image Translation Networks","created":"2017-03-02","cited_by_count":603},{"id":"1804.00015","title":"ESPnet: End-to-End Speech Processing Toolkit","created":"2018-03-30","cited_by_count":558},{"id":"1910.11480","title":"Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram","created":"2019-10-25","cited_by_count":340},{"id":"1809.00496","title":"LRS3-TED: a large-scale dataset for visual speech recognition","created":"2018-09-03","cited_by_count":308},{"id":"1711.11586","title":"Toward Multimodal Image-to-Image Translation","created":"2017-11-30","cited_by_count":296},{"id":"1808.00948","title":"Diverse Image-to-Image Translation via Disentangled Representations","created":"2018-08-02","cited_by_count":296},{"id":"2006.16228","title":"Self-Supervised MultiModal Versatile Networks","created":"2020-06-29","cited_by_count":276},{"id":"1609.06773","title":"Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learning","created":"2016-09-21","cited_by_count":257},{"id":"1905.01723","title":"Few-Shot Unsupervised Image-to-Image Translation","created":"2019-05-05","cited_by_count":222},{"id":"2104.09494","title":"NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasets","created":"2021-04-19","cited_by_count":192},{"id":"1912.06203","title":"ManiGAN: Text-Guided Image Manipulation","created":"2019-12-12","cited_by_count":156},{"id":"1903.05628","title":"Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis","created":"2019-03-13","cited_by_count":138},{"id":"1904.07399","title":"Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression","created":"2019-04-16","cited_by_count":128},{"id":"1810.11919","title":"Text-Adaptive Generative Adversarial Networks: Manipulating Images with Natural Language","created":"2018-10-29","cited_by_count":90},{"id":"1707.06873","title":"Semantic Image Synthesis via Adversarial Learning","created":"2017-07-21","cited_by_count":87},{"id":"1904.05742","title":"One-shot Voice Conversion by Separating Speaker and Content Representations with Instance Normalization","created":"2019-04-10","cited_by_count":82},{"id":"1901.09024","title":"Diversity-Sensitive Conditional Generative Adversarial Networks","created":"2019-01-25","cited_by_count":77},{"id":"1802.10151","title":"Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data","created":"2018-02-27","cited_by_count":76},{"id":"2005.08209","title":"Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis","created":"2020-05-17","cited_by_count":74},{"id":"1806.04498","title":"The Unusual Effectiveness of Averaging in GAN Training","created":"2018-06-12","cited_by_count":73},{"id":"2104.00854","title":"The Spatially-Correlative Loss for Various Image Translation Tasks","created":"2021-04-02","cited_by_count":66},{"id":"2107.10394","title":"StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion","created":"2021-07-21","cited_by_count":58},{"id":"1905.09773","title":"Speech2Face: Learning the Face Behind a Voice","created":"2019-05-23","cited_by_count":55},{"id":"1812.09912","title":"Image-to-Image Translation via Group-wise Deep Whitening-and-Coloring Transformation","created":"2018-12-24","cited_by_count":49},{"id":"2112.11641","title":"JoJoGAN: One Shot Face Stylization","created":"2021-12-22","cited_by_count":49},{"id":"2108.04547","title":"Instance-wise Hard Negative Example Generation for Contrastive Learning in Unpaired Image-to-Image Translation","created":"2021-08-10","cited_by_count":45},{"id":"2011.00316","title":"AGAIN-VC: A One-shot Voice Conversion using Activation Guidance and Adaptive Instance Normalization","created":"2020-10-31","cited_by_count":44},{"id":"2203.01532","title":"Exploring Patch-wise Semantic Relation for Contrastive Learning in Image-to-Image Translation Tasks","created":"2022-03-03","cited_by_count":42},{"id":"1805.11145","title":"Exemplar Guided Unsupervised Image-to-Image Translation with Semantic Consistency","created":"2018-05-28","cited_by_count":41},{"id":"1907.12279","title":"StarGAN-VC2: Rethinking Conditional Methods for StarGAN-Based Voice Conversion","created":"2019-07-29","cited_by_count":37},{"id":"2010.14150","title":"FragmentVC: Any-to-Any Voice Conversion by End-to-End Extracting and Fusing Fine-Grained Voice Fragments With Attention","created":"2020-10-27","cited_by_count":37},{"id":"2006.04154","title":"VQVC+: One-Shot Voice Conversion by Vector Quantization and U-Net architecture","created":"2020-06-07","cited_by_count":35},{"id":"2104.11673","title":"Deep Learning Based Assessment of Synthetic Speech Naturalness","created":"2021-04-23","cited_by_count":35},{"id":"2112.00007","title":"Sound-Guided Semantic Image Manipulation","created":"2021-11-30","cited_by_count":35},{"id":"1711.11293","title":"Parallel-Data-Free Voice Conversion Using Cycle-Consistent Adversarial Networks","created":"2017-11-30","cited_by_count":31},{"id":"1804.02812","title":"Multi-target Voice Conversion without Parallel Data by Adversarially Learning Disentangled Audio Representations","created":"2018-04-09","cited_by_count":25},{"id":"2205.05072","title":"Learning Visual Styles from Audio-Visual Associations","created":"2022-05-10","cited_by_count":22},{"id":"1712.02050","title":"Unsupervised Multi-Domain Image Translation with Domain-Specific Encoders/Decoders","created":"2017-12-06","cited_by_count":11},{"id":"2102.04680","title":"Tr\\\"aumerAI: Dreaming Music with StyleGAN","created":"2021-02-09","cited_by_count":11},{"id":"2009.08083","title":"Crossing You in Style: Cross-modal Style Transfer from Music to Visual Arts","created":"2020-09-17","cited_by_count":10},{"id":"2101.06842","title":"Hierarchical disentangled representation learning for singing voice conversion","created":"2021-01-18","cited_by_count":9},{"id":"2203.12707","title":"Maximum Spatial Perturbation Consistency for Unpaired Image-to-Image Translation","created":"2022-03-23","cited_by_count":8},{"id":"1809.10288","title":"WaveCycleGAN: Synthetic-to-natural speech waveform conversion using cycle-consistent adversarial networks","created":"2018-09-25","cited_by_count":6}],"next_cursor":null}