{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"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":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"1806.08734","title":"On the Spectral Bias of Neural Networks","created":"2018-06-22","cited_by_count":1341},{"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":"1711.07280","title":"Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments","created":"2017-11-20","cited_by_count":1027},{"id":"1804.04732","title":"Multimodal Unsupervised Image-to-Image Translation","created":"2018-04-12","cited_by_count":795},{"id":"1703.10593","title":"Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks","created":"2017-03-30","cited_by_count":707},{"id":"1801.04406","title":"Which Training Methods for GANs do actually Converge?","created":"2018-01-13","cited_by_count":679},{"id":"1811.11168","title":"Deformable ConvNets v2: More Deformable, Better Results","created":"2018-11-27","cited_by_count":670},{"id":"2007.15651","title":"Contrastive Learning for Unpaired Image-to-Image Translation","created":"2020-07-30","cited_by_count":639},{"id":"1801.10130","title":"Spherical CNNs","created":"2018-01-30","cited_by_count":456},{"id":"1808.00948","title":"Diverse Image-to-Image Translation via Disentangled Representations","created":"2018-08-02","cited_by_count":296},{"id":"1711.06721","title":"Learning SO(3) Equivariant Representations with Spherical CNNs","created":"2017-11-17","cited_by_count":248},{"id":"1905.01270","title":"DRIT++: Diverse Image-to-Image Translation via Disentangled Representations","created":"2019-05-02","cited_by_count":244},{"id":"2007.00653","title":"Swapping Autoencoder for Deep Image Manipulation","created":"2020-07-01","cited_by_count":215},{"id":"1712.00479","title":"Image to Image Translation for Domain Adaptation","created":"2017-12-01","cited_by_count":171},{"id":"2012.09793","title":"SceneFormer: Indoor Scene Generation with Transformers","created":"2020-12-17","cited_by_count":158},{"id":"2112.10762","title":"StyleSwin: Transformer-based GAN for High-resolution Image Generation","created":"2021-12-20","cited_by_count":152},{"id":"1905.01489","title":"WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving","created":"2019-05-04","cited_by_count":144},{"id":"2107.04589","title":"ViTGAN: Training GANs with Vision Transformers","created":"2021-07-09","cited_by_count":110},{"id":"1804.00168","title":"Learning to Navigate in Cities Without a Map","created":"2018-03-31","cited_by_count":104},{"id":"2203.09283","title":"PanoFormer: Panorama Transformer for Indoor 360 Depth Estimation","created":"2022-03-17","cited_by_count":95},{"id":"2102.03550","title":"UniFuse: Unidirectional Fusion for 360$^{\\circ}$ Panorama Depth Estimation","created":"2021-02-06","cited_by_count":92},{"id":"1803.09655","title":"BAGAN: Data Augmentation with Balancing GAN","created":"2018-03-26","cited_by_count":90},{"id":"2203.01452","title":"Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation","created":"2022-03-02","cited_by_count":72},{"id":"1810.09957","title":"NSML: Meet the MLaaS platform with a real-world case study","created":"2018-10-08","cited_by_count":70},{"id":"1811.11977","title":"DuLa-Net: A Dual-Projection Network for Estimating Room Layouts from a Single RGB Panorama","created":"2018-11-29","cited_by_count":68},{"id":"1806.01320","title":"Cube Padding for Weakly-Supervised Saliency Prediction in 360{\\deg} Videos","created":"2018-06-04","cited_by_count":66},{"id":"2104.00854","title":"The Spatially-Correlative Loss for Various Image Translation Tasks","created":"2021-04-02","cited_by_count":66},{"id":"2007.12072","title":"TSIT: A Simple and Versatile Framework for Image-to-Image Translation","created":"2020-07-23","cited_by_count":64},{"id":"2111.15669","title":"360MonoDepth: High-Resolution 360{\\deg} Monocular Depth Estimation","created":"2021-11-30","cited_by_count":60},{"id":"1908.07269","title":"RelGAN: Multi-Domain Image-to-Image Translation via Relative Attributes","created":"2019-08-20","cited_by_count":56},{"id":"2103.05687","title":"Capturing Omni-Range Context for Omnidirectional Segmentation","created":"2021-03-09","cited_by_count":50},{"id":"1905.01744","title":"Towards Instance-level Image-to-Image Translation","created":"2019-05-05","cited_by_count":36},{"id":"2108.06383","title":"DensePASS: Dense Panoramic Semantic Segmentation via Unsupervised Domain Adaptation with Attention-Augmented Context Exchange","created":"2021-08-13","cited_by_count":36},{"id":"1808.06253","title":"Eliminating the Blind Spot: Adapting 3D Object Detection and Monocular Depth Estimation to 360{\\deg} Panoramic Imagery","created":"2018-08-19","cited_by_count":35},{"id":"2106.09016","title":"Smoothing the Disentangled Latent Style Space for Unsupervised Image-to-Image Translation","created":"2021-06-16","cited_by_count":35},{"id":"1909.07721","title":"DS-PASS: Detail-Sensitive Panoramic Annular Semantic Segmentation through SwaftNet for Surrounding Sensing","created":"2019-09-17","cited_by_count":30},{"id":"1805.02838","title":"A Memory Network Approach for Story-based Temporal Summarization of 360{\\deg} Videos","created":"2018-05-08","cited_by_count":29},{"id":"2203.16248","title":"InstaFormer: Instance-Aware Image-to-Image Translation with Transformer","created":"2022-03-30","cited_by_count":28},{"id":"1803.04228","title":"Omnidirectional CNN for Visual Place Recognition and Navigation","created":"2018-03-12","cited_by_count":22},{"id":"2104.05170","title":"Memory-guided Unsupervised Image-to-image Translation","created":"2021-04-12","cited_by_count":21},{"id":"1805.08009","title":"Object Detection in Equirectangular Panorama","created":"2018-05-21","cited_by_count":20},{"id":"2209.08956","title":"Panoramic Vision Transformer for Saliency Detection in 360{\\deg} Videos","created":"2022-09-19","cited_by_count":15},{"id":"2202.04942","title":"Spherical Transformer","created":"2022-02-10","cited_by_count":11}],"next_cursor":null}