{"list":"other","total":70,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"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":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"1707.02921","title":"Enhanced Deep Residual Networks for Single Image Super-Resolution","created":"2017-07-10","cited_by_count":1552},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"id":"2201.09865","title":"RePaint: Inpainting using Denoising Diffusion Probabilistic Models","created":"2022-01-24","cited_by_count":1430},{"id":"2009.09761","title":"DiffWave: A Versatile Diffusion Model for Audio Synthesis","created":"2020-09-21","cited_by_count":1354},{"id":"2302.08453","title":"T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models","created":"2023-02-16","cited_by_count":1351},{"id":"1903.07291","title":"Semantic Image Synthesis with Spatially-Adaptive Normalization","created":"2019-03-18","cited_by_count":1299},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"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":"1911.09070","title":"EfficientDet: Scalable and Efficient Object Detection","created":"2019-11-20","cited_by_count":1020},{"id":"2209.04747","title":"Diffusion Models in Vision: A Survey","created":"2022-09-10","cited_by_count":1015},{"id":"1702.03118","title":"Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning","created":"2017-02-10","cited_by_count":950},{"id":"2204.04676","title":"Simple Baselines for Image Restoration","created":"2022-04-10","cited_by_count":708},{"id":"1905.05055","title":"Object Detection in 20 Years: A Survey","created":"2019-05-13","cited_by_count":531},{"id":"2203.02923","title":"GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation","created":"2022-03-06","cited_by_count":516},{"id":"2208.11970","title":"Understanding Diffusion Models: A Unified Perspective","created":"2022-08-25","cited_by_count":340},{"id":"2302.07944","title":"Effective Data Augmentation With Diffusion Models","created":"2023-02-07","cited_by_count":283},{"id":"2212.05034","title":"SmartBrush: Text and Shape Guided Object Inpainting with Diffusion Model","created":"2022-12-09","cited_by_count":278},{"id":"2211.07804","title":"Diffusion Models for Medical Image Analysis: A Comprehensive Survey","created":"2022-11-14","cited_by_count":273},{"id":"1811.11127","title":"Unprocessing Images for Learned Raw Denoising","created":"2018-11-27","cited_by_count":250},{"id":"1312.6229","title":"OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks","created":"2013-12-21","cited_by_count":224},{"id":"2003.07761","title":"CycleISP: Real Image Restoration via Improved Data Synthesis","created":"2020-03-17","cited_by_count":213},{"id":"1710.07480","title":"HDR image reconstruction from a single exposure using deep CNNs","created":"2017-10-20","cited_by_count":167},{"id":"2207.00050","title":"Semantic Image Synthesis via Diffusion Models","created":"2022-06-30","cited_by_count":132},{"id":"1905.05169","title":"Zoom To Learn, Learn To Zoom","created":"2019-05-13","cited_by_count":115},{"id":"2103.15061","title":"Invertible Image Signal Processing","created":"2021-03-28","cited_by_count":94},{"id":"1801.06724","title":"DeepISP: Towards Learning an End-to-End Image Processing Pipeline","created":"2018-01-20","cited_by_count":88},{"id":"2201.03210","title":"Model-Based Image Signal Processors via Learnable Dictionaries","created":"2022-01-10","cited_by_count":43},{"id":"1908.01481","title":"CameraNet: A Two-Stage Framework for Effective Camera ISP Learning","created":"2019-08-05","cited_by_count":38},{"id":"1705.04352","title":"Reconfiguring the Imaging Pipeline for Computer Vision","created":"2017-05-11","cited_by_count":32},{"id":"2203.07669","title":"Progressive End-to-End Object Detection in Crowded Scenes","created":"2022-03-15","cited_by_count":31},{"id":"2006.12709","title":"CIE XYZ Net: Unprocessing Images for Low-Level Computer Vision Tasks","created":"2020-06-23","cited_by_count":29},{"id":"2308.09534","title":"Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning","created":"2023-08-18","cited_by_count":27},{"id":"2201.10728","title":"Training Vision Transformers with Only 2040 Images","created":"2022-01-26","cited_by_count":23},{"id":"2211.01146","title":"DynamicISP: Dynamically Controlled Image Signal Processor for Image Recognition","created":"2022-11-02","cited_by_count":23},{"id":"2205.03688","title":"GenISP: Neural ISP for Low-Light Machine Cognition","created":"2022-05-07","cited_by_count":22},{"id":"2210.16046","title":"Rawgment: Noise-Accounted RAW Augmentation Enables Recognition in a Wide Variety of Environments","created":"2022-10-28","cited_by_count":18},{"id":"2211.02914","title":"Robust Reflection Removal with Flash-only Cues in the Wild","created":"2022-11-05","cited_by_count":14},{"id":"2301.08965","title":"Raw or Cooked? Object Detection on RAW Images","created":"2023-01-21","cited_by_count":14},{"id":"2210.11153","title":"Reversed Image Signal Processing and RAW Reconstruction. AIM 2022 Challenge Report","created":"2022-10-20","cited_by_count":11},{"id":"1311.6887","title":"Modeling Radiometric Uncertainty for Vision with Tone-mapped Color Images","created":"2013-11-27","cited_by_count":10},{"id":"2303.13916","title":"Self-Supervised Reversed Image Signal Processing via Reference-Guided Dynamic Parameter Selection","created":"2023-03-24","cited_by_count":5},{"id":"2202.11616","title":"ChimeraMix: Image Classification on Small Datasets via Masked Feature Mixing","created":"2022-02-23","cited_by_count":4},{"id":"2210.05451","title":"Enabling ISP-less Low-Power Computer Vision","created":"2022-10-11","cited_by_count":1}],"next_cursor":null}