{"list":"other","total":58,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"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":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1505.05770","title":"Variational Inference with Normalizing Flows","created":"2015-05-21","cited_by_count":2170},{"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":"2111.05826","title":"Palette: Image-to-Image Diffusion Models","created":"2021-11-10","cited_by_count":1300},{"id":"1809.00219","title":"ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks","created":"2018-09-01","cited_by_count":1254},{"id":"2106.15282","title":"Cascaded Diffusion Models for High Fidelity Image Generation","created":"2021-05-30","cited_by_count":1163},{"id":"2209.04747","title":"Diffusion Models in Vision: A Survey","created":"2022-09-10","cited_by_count":1015},{"id":"2107.10833","title":"Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data","created":"2021-07-22","cited_by_count":970},{"id":"2111.14818","title":"Blended Diffusion for Text-driven Editing of Natural Images","created":"2021-11-29","cited_by_count":927},{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747},{"id":"2309.17080","title":"GAIA-1: A Generative World Model for Autonomous Driving","created":"2023-09-29","cited_by_count":637},{"id":"2207.08051","title":"SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery","created":"2022-07-17","cited_by_count":408},{"id":"2306.11029","title":"RemoteCLIP: A Vision Language Foundation Model for Remote Sensing","created":"2023-06-19","cited_by_count":363},{"id":"2311.15826","title":"GeoChat: Grounded Large Vision-Language Model for Remote Sensing","created":"2023-11-24","cited_by_count":328},{"id":"2304.08466","title":"Synthetic Data from Diffusion Models Improves ImageNet Classification","created":"2023-04-17","cited_by_count":327},{"id":"2212.14532","title":"Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning","created":"2022-12-30","cited_by_count":308},{"id":"2204.00227","title":"Perception Prioritized Training of Diffusion Models","created":"2022-04-01","cited_by_count":303},{"id":"2205.11495","title":"Flexible Diffusion Modeling of Long Videos","created":"2022-05-23","cited_by_count":294},{"id":"2311.07113","title":"SpectralGPT: Spectral Remote Sensing Foundation Model","created":"2023-11-13","cited_by_count":252},{"id":"2401.16822","title":"EarthGPT: A Universal Multi-modal Large Language Model for Multi-sensor Image Comprehension in Remote Sensing Domain","created":"2024-01-30","cited_by_count":184},{"id":"2207.06635","title":"EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential Equations","created":"2022-07-14","cited_by_count":172},{"id":"2211.15660","title":"SatlasPretrain: A Large-Scale Dataset for Remote Sensing Image Understanding","created":"2022-11-28","cited_by_count":167},{"id":"2208.03987","title":"Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model","created":"2022-08-08","cited_by_count":149},{"id":"2206.07696","title":"Diffusion Models for Video Prediction and Infilling","created":"2022-06-15","cited_by_count":135},{"id":"2312.03606","title":"DiffusionSat: A Generative Foundation Model for Satellite Imagery","created":"2023-12-06","cited_by_count":131},{"id":"2312.12856","title":"SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensing","created":"2023-12-20","cited_by_count":125},{"id":"2308.06160","title":"DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models","created":"2023-08-11","cited_by_count":123},{"id":"2401.09712","title":"SkyEyeGPT: Unifying Remote Sensing Vision-Language Tasks via Instruction Tuning with Large Language Model","created":"2024-01-18","cited_by_count":113},{"id":"2405.03520","title":"Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyond","created":"2024-05-06","cited_by_count":111},{"id":"2302.04476","title":"Towards Geospatial Foundation Models via Continual Pretraining","created":"2023-02-09","cited_by_count":109},{"id":"2205.01491","title":"A Comprehensive Survey of Image Augmentation Techniques for Deep Learning","created":"2022-05-03","cited_by_count":97},{"id":"2403.05419","title":"Rethinking Transformers Pre-training for Multi-Spectral Satellite Imagery","created":"2024-03-08","cited_by_count":83},{"id":"2312.06960","title":"Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment","created":"2023-12-12","cited_by_count":71},{"id":"2112.13592","title":"Multimodal Image Synthesis and Editing: The Generative AI Era","created":"2021-12-27","cited_by_count":52},{"id":"2309.04430","title":"Create Your World: Lifelong Text-to-Image Diffusion","created":"2023-09-08","cited_by_count":46},{"id":"2404.18895","title":"RSCaMa: Remote Sensing Image Change Captioning with State Space Model","created":"2024-04-29","cited_by_count":35},{"id":"2308.16648","title":"Generate Your Own Scotland: Satellite Image Generation Conditioned on Maps","created":"2023-08-31","cited_by_count":30},{"id":"2402.06475","title":"Large Language Models for Captioning and Retrieving Remote Sensing Images","created":"2024-02-09","cited_by_count":30},{"id":"2009.07047","title":"Old Photo Restoration via Deep Latent Space Translation","created":"2020-09-14","cited_by_count":27},{"id":"2002.01048","title":"Multi-Channel Attention Selection GANs for Guided Image-to-Image Translation","created":"2020-02-03","cited_by_count":23},{"id":"2305.06225","title":"DaGAN++: Depth-Aware Generative Adversarial Network for Talking Head Video Generation","created":"2023-05-10","cited_by_count":20},{"id":"2301.04628","title":"Image-to-Image Translation with Disentangled Latent Vectors for Face Editing","created":"2023-01-11","cited_by_count":13},{"id":"2309.16812","title":"SatDM: Synthesizing Realistic Satellite Image with Semantic Layout Conditioning using Diffusion Models","created":"2023-09-28","cited_by_count":11},{"id":"2202.03678","title":"Quality Metric Guided Portrait Line Drawing Generation from Unpaired Training Data","created":"2022-02-08","cited_by_count":5}],"next_cursor":null}