{"list":"other","total":71,"rows":[{"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"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":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"2111.09881","title":"Restormer: Efficient Transformer for High-Resolution Image Restoration","created":"2021-11-18","cited_by_count":1627},{"id":"1506.04214","title":"Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting","created":"2015-06-13","cited_by_count":1436},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"id":"1607.08022","title":"Instance Normalization: The Missing Ingredient for Fast Stylization","created":"2016-07-27","cited_by_count":1198},{"id":"2107.08430","title":"YOLOX: Exceeding YOLO Series in 2021","created":"2021-07-18","cited_by_count":1071},{"id":"2102.02808","title":"Multi-Stage Progressive Image Restoration","created":"2021-02-04","cited_by_count":816},{"id":"2204.04676","title":"Simple Baselines for Image Restoration","created":"2022-04-10","cited_by_count":708},{"id":"1711.09078","title":"Video Enhancement with Task-Oriented Flow","created":"2017-11-24","cited_by_count":619},{"id":"2205.08534","title":"Vision Transformer Adapter for Dense Predictions","created":"2022-05-17","cited_by_count":565},{"id":"1803.04189","title":"Noise2Noise: Learning Image Restoration without Clean Data","created":"2018-03-12","cited_by_count":533},{"id":"1905.02716","title":"EDVR: Video Restoration with Enhanced Deformable Convolutional Networks","created":"2019-05-07","cited_by_count":494},{"id":"1901.07518","title":"Hybrid Task Cascade for Instance Segmentation","created":"2019-01-22","cited_by_count":481},{"id":"1805.01934","title":"Learning to See in the Dark","created":"2018-05-04","cited_by_count":460},{"id":"1811.10980","title":"Noise2Void - Learning Denoising from Single Noisy Images","created":"2018-11-27","cited_by_count":364},{"id":"2206.02777","title":"Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation","created":"2022-06-06","cited_by_count":344},{"id":"2211.12860","title":"DETRs with Collaborative Hybrid Assignments Training","created":"2022-11-22","cited_by_count":274},{"id":"1811.11127","title":"Unprocessing Images for Learned Raw Denoising","created":"2018-11-27","cited_by_count":250},{"id":"2303.06705","title":"Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement","created":"2023-03-12","cited_by_count":231},{"id":"2103.09213","title":"Back to the Feature: Learning Robust Camera Localization from Pixels to Pose","created":"2021-03-16","cited_by_count":199},{"id":"2212.07784","title":"RTMDet: An Empirical Study of Designing Real-Time Object Detectors","created":"2022-12-14","cited_by_count":195},{"id":"1904.08298","title":"Events-to-Video: Bringing Modern Computer Vision to Event Cameras","created":"2019-04-17","cited_by_count":193},{"id":"2203.11926","title":"Focal Modulation Networks","created":"2022-03-22","cited_by_count":186},{"id":"2301.11699","title":"Image Restoration with Mean-Reverting Stochastic Differential Equations","created":"2023-01-27","cited_by_count":183},{"id":"1804.01306","title":"A Unifying Contrast Maximization Framework for Event Cameras, with Applications to Motion, Depth, and Optical Flow Estimation","created":"2018-04-04","cited_by_count":178},{"id":"2001.06816","title":"Human-Aware Motion Deblurring","created":"2020-01-19","cited_by_count":175},{"id":"2212.11548","title":"Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Method","created":"2022-12-22","cited_by_count":174},{"id":"2206.02146","title":"Recurrent Video Restoration Transformer with Guided Deformable Attention","created":"2022-06-05","cited_by_count":170},{"id":"2105.01928","title":"Instances as Queries","created":"2021-05-05","cited_by_count":158},{"id":"1712.02327","title":"Burst Denoising with Kernel Prediction Networks","created":"2017-12-06","cited_by_count":157},{"id":"2205.01649","title":"Learning Enriched Features for Fast Image Restoration and Enhancement","created":"2022-04-19","cited_by_count":150},{"id":"2003.12751","title":"A Physics-based Noise Formation Model for Extreme Low-light Raw Denoising","created":"2020-03-28","cited_by_count":138},{"id":"1907.01361","title":"FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow Estimation","created":"2019-07-01","cited_by_count":128},{"id":"2308.13164","title":"Diff-Retinex: Rethinking Low-light Image Enhancement with A Generative Diffusion Model","created":"2023-08-25","cited_by_count":118},{"id":"2112.00167","title":"Event-Based Fusion for Motion Deblurring with Cross-modal Attention","created":"2021-11-30","cited_by_count":113},{"id":"1908.08453","title":"Noise Flow: Noise Modeling with Conditional Normalizing Flows","created":"2019-08-22","cited_by_count":108},{"id":"2310.17577","title":"Global Structure-Aware Diffusion Process for Low-Light Image Enhancement","created":"2023-10-26","cited_by_count":92},{"id":"1801.06724","title":"DeepISP: Towards Learning an End-to-End Image Processing Pipeline","created":"2018-01-20","cited_by_count":88},{"id":"2302.11831","title":"Embedding Fourier for Ultra-High-Definition Low-Light Image Enhancement","created":"2023-02-23","cited_by_count":86},{"id":"2109.09052","title":"Object Tracking by Jointly Exploiting Frame and Event Domain","created":"2021-09-19","cited_by_count":84},{"id":"2108.07058","title":"FaPN: Feature-aligned Pyramid Network for Dense Image Prediction","created":"2021-08-16","cited_by_count":81},{"id":"2003.14013","title":"Supervised Raw Video Denoising with a Benchmark Dataset on Dynamic Scenes","created":"2020-03-31","cited_by_count":77},{"id":"2007.08336","title":"Event Enhanced High-Quality Image Recovery","created":"2020-07-16","cited_by_count":68},{"id":"2206.10810","title":"A Simple Baseline for Video Restoration with Grouped Spatial-temporal Shift","created":"2022-06-22","cited_by_count":68},{"id":"2108.02158","title":"Physics-based Noise Modeling for Extreme Low-light Photography","created":"2021-08-04","cited_by_count":67},{"id":"1908.00682","title":"Attention Guided Low-light Image Enhancement with a Large Scale Low-light Simulation Dataset","created":"2019-08-02","cited_by_count":65},{"id":"2304.10244","title":"Omni Aggregation Networks for Lightweight Image Super-Resolution","created":"2023-04-20","cited_by_count":62},{"id":"2105.13084","title":"HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantization","created":"2021-05-27","cited_by_count":58},{"id":"1910.11336","title":"Handheld Mobile Photography in Very Low Light","created":"2019-10-24","cited_by_count":56},{"id":"2304.14298","title":"Instance Segmentation in the Dark","created":"2023-04-27","cited_by_count":46},{"id":"1904.10898","title":"ViDeNN: Deep Blind Video Denoising","created":"2019-04-24","cited_by_count":40},{"id":"2305.03892","title":"DocDiff: Document Enhancement via Residual Diffusion Models","created":"2023-05-06","cited_by_count":37},{"id":"2103.05407","title":"Efficient Multi-Stage Video Denoising with Recurrent Spatio-Temporal Fusion","created":"2021-03-09","cited_by_count":36},{"id":"2309.02020","title":"RawHDR: High Dynamic Range Image Reconstruction from a Single Raw Image","created":"2023-09-05","cited_by_count":32},{"id":"2308.06725","title":"CLE Diffusion: Controllable Light Enhancement Diffusion Model","created":"2023-08-13","cited_by_count":30},{"id":"2404.14248","title":"NTIRE 2024 Challenge on Low Light Image Enhancement: Methods and Results","created":"2024-04-22","cited_by_count":26},{"id":"2402.05809","title":"You Only Need One Color Space: An Efficient Network for Low-light Image Enhancement","created":"2024-02-08","cited_by_count":24},{"id":"1412.4031","title":"High-level numerical simulations of noise in CCD and CMOS photosensors: review and tutorial","created":"2014-12-11","cited_by_count":23},{"id":"2006.02026","title":"Image Classification in the Dark using Quanta Image Sensors","created":"2020-06-03","cited_by_count":15},{"id":"2204.01716","title":"Estimating Fine-Grained Noise Model via Contrastive Learning","created":"2022-04-03","cited_by_count":14},{"id":"2405.06600","title":"Multi-Object Tracking in the Dark","created":"2024-05-10","cited_by_count":14},{"id":"2401.10666","title":"MixNet: Efficient Global Modeling for Ultra-High-Definition Image Restoration","created":"2024-01-19","cited_by_count":8},{"id":"2402.18217","title":"Region-Aware Exposure Consistency Network for Mixed Exposure Correction","created":"2024-02-28","cited_by_count":8}],"next_cursor":null}