{"list":"other","total":62,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2208.01618","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","created":"2022-08-02","cited_by_count":2245},{"id":"1411.1784","title":"Conditional Generative Adversarial Nets","created":"2014-11-06","cited_by_count":2162},{"id":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"id":"2104.07636","title":"Image Super-Resolution via Iterative Refinement","created":"2021-04-15","cited_by_count":1511},{"id":"2209.04747","title":"Diffusion Models in Vision: A Survey","created":"2022-09-10","cited_by_count":1015},{"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":"1806.02446","title":"Deep Ordinal Regression Network for Monocular Depth Estimation","created":"2018-06-06","cited_by_count":723},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"1907.10786","title":"Interpreting the Latent Space of GANs for Semantic Face Editing","created":"2019-07-25","cited_by_count":695},{"id":"1703.00848","title":"Unsupervised Image-to-Image Translation Networks","created":"2017-03-02","cited_by_count":603},{"id":"2111.15640","title":"Diffusion Autoencoders: Toward a Meaningful and Decodable Representation","created":"2021-11-30","cited_by_count":449},{"id":"1808.06601","title":"Video-to-Video Synthesis","created":"2018-08-20","cited_by_count":390},{"id":"1912.08804","title":"SynSin: End-to-end View Synthesis from a Single Image","created":"2019-12-18","cited_by_count":364},{"id":"2204.02491","title":"Text2LIVE: Text-Driven Layered Image and Video Editing","created":"2022-04-05","cited_by_count":312},{"id":"2210.04628","title":"Novel View Synthesis with Diffusion Models","created":"2022-10-06","cited_by_count":300},{"id":"2204.08583","title":"VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance","created":"2022-04-18","cited_by_count":285},{"id":"2004.11364","title":"Single-View View Synthesis with Multiplane Images","created":"2020-04-23","cited_by_count":263},{"id":"1801.03150","title":"Moments in Time Dataset: one million videos for event understanding","created":"2018-01-09","cited_by_count":215},{"id":"1810.04020","title":"A Comprehensive Survey of Deep Learning for Image Captioning","created":"2018-10-06","cited_by_count":214},{"id":"1705.04058","title":"Neural Style Transfer: A Review","created":"2017-05-11","cited_by_count":199},{"id":"2210.00379","title":"NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)","created":"2022-10-01","cited_by_count":158},{"id":"2104.05358","title":"UNIT-DDPM: UNpaired Image Translation with Denoising Diffusion Probabilistic Models","created":"2021-04-12","cited_by_count":133},{"id":"2208.02797","title":"Vision-Centric BEV Perception: A Survey","created":"2022-08-04","cited_by_count":126},{"id":"2101.08629","title":"Image-to-Image Translation: Methods and Applications","created":"2021-01-21","cited_by_count":116},{"id":"2103.06818","title":"Coming Down to Earth: Satellite-to-Street View Synthesis for Geo-Localization","created":"2021-03-11","cited_by_count":113},{"id":"1904.06807","title":"Multi-Channel Attention Selection GAN with Cascaded Semantic Guidance for Cross-View Image Translation","created":"2019-04-15","cited_by_count":97},{"id":"2104.00946","title":"UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles","created":"2021-04-02","cited_by_count":96},{"id":"1906.06543","title":"Image-based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era","created":"2019-06-15","cited_by_count":87},{"id":"2203.10541","title":"Unsupervised Domain Adaptation for Nighttime Aerial Tracking","created":"2022-03-20","cited_by_count":56},{"id":"2102.01187","title":"Enjoy Your Editing: Controllable GANs for Image Editing via Latent Space Navigation","created":"2021-02-01","cited_by_count":53},{"id":"2103.01623","title":"Geometry-Guided Street-View Panorama Synthesis from Satellite Imagery","created":"2021-03-02","cited_by_count":41},{"id":"2004.13866","title":"Deflating Dataset Bias Using Synthetic Data Augmentation","created":"2020-04-28","cited_by_count":38},{"id":"1905.02231","title":"A Geometric Approach to Obtain a Bird's Eye View from an Image","created":"2019-05-06","cited_by_count":34},{"id":"2011.02250","title":"Video Generative Adversarial Networks: A Review","created":"2020-11-04","cited_by_count":33},{"id":"1805.00251","title":"Conditional Image-to-Image Translation","created":"2018-05-01","cited_by_count":30},{"id":"1808.05469","title":"Cross-view image synthesis using geometry-guided conditional GANs","created":"2018-08-14","cited_by_count":30},{"id":"2008.04200","title":"Describe What to Change: A Text-guided Unsupervised Image-to-Image Translation Approach","created":"2020-08-10","cited_by_count":29},{"id":"2203.11832","title":"Cross-View Panorama Image Synthesis","created":"2022-03-22","cited_by_count":26},{"id":"2012.13736","title":"Image Synthesis with Adversarial Networks: a Comprehensive Survey and Case Studies","created":"2020-12-26","cited_by_count":24},{"id":"2110.10183","title":"Cascaded Cross MLP-Mixer GANs for Cross-View Image Translation","created":"2021-10-19","cited_by_count":21},{"id":"2107.03120","title":"Cross-View Exocentric to Egocentric Video Synthesis","created":"2021-07-07","cited_by_count":20},{"id":"2002.03219","title":"Exocentric to Egocentric Image Generation via Parallel Generative Adversarial Network","created":"2020-02-08","cited_by_count":17},{"id":"2110.05145","title":"Sim2Air - Synthetic aerial dataset for UAV monitoring","created":"2021-10-11","cited_by_count":16},{"id":"2106.07140","title":"SinIR: Efficient General Image Manipulation with Single Image Reconstruction","created":"2021-06-14","cited_by_count":13},{"id":"2002.05235","title":"Image-to-Image Translation with Text Guidance","created":"2020-02-12","cited_by_count":10},{"id":"2203.10694","title":"FAR: Fourier Aerial Video Recognition","created":"2022-03-21","cited_by_count":10},{"id":"2007.09858","title":"Cross-View Image Synthesis with Deformable Convolution and Attention Mechanism","created":"2020-07-20","cited_by_count":6},{"id":"2101.01619","title":"Novel View Synthesis via Depth-guided Skip Connections","created":"2021-01-05","cited_by_count":5},{"id":"2207.04242","title":"PI-Trans: Parallel-ConvMLP and Implicit-Transformation Based GAN for Cross-View Image Translation","created":"2022-07-09","cited_by_count":4},{"id":"2107.06812","title":"Deep Learning based Novel View Synthesis","created":"2021-07-14","cited_by_count":2}],"next_cursor":null}