{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"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":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"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":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"id":"1807.10221","title":"Unified Perceptual Parsing for Scene Understanding","created":"2018-07-26","cited_by_count":1271},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"1609.04747","title":"An overview of gradient descent optimization algorithms","created":"2016-09-15","cited_by_count":1033},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"1808.04560","title":"Deep Retinex Decomposition for Low-Light Enhancement","created":"2018-08-14","cited_by_count":723},{"id":"1412.7062","title":"Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs","created":"2014-12-22","cited_by_count":554},{"id":"2001.06826","title":"Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement","created":"2020-01-19","cited_by_count":542},{"id":"2011.12450","title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","created":"2020-11-25","cited_by_count":495},{"id":"1904.01169","title":"Res2Net: A New Multi-scale Backbone Architecture","created":"2019-04-02","cited_by_count":470},{"id":"1906.06972","title":"EnlightenGAN: Deep Light Enhancement without Paired Supervision","created":"2019-06-17","cited_by_count":466},{"id":"1906.09756","title":"Cascade R-CNN: High Quality Object Detection and Instance Segmentation","created":"2019-06-24","cited_by_count":429},{"id":"1905.04161","title":"Kindling the Darkness: A Practical Low-light Image Enhancer","created":"2019-05-04","cited_by_count":355},{"id":"2012.05609","title":"Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement","created":"2020-12-10","cited_by_count":303},{"id":"2006.02334","title":"DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution","created":"2020-06-03","cited_by_count":222},{"id":"2103.00860","title":"Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation","created":"2021-03-01","cited_by_count":192},{"id":"1603.07285","title":"A guide to convolution arithmetic for deep learning","created":"2016-03-23","cited_by_count":185},{"id":"1805.11227","title":"Getting to Know Low-light Images with The Exclusively Dark Dataset","created":"2018-05-29","cited_by_count":157},{"id":"1907.06390","title":"Sequence Level Semantics Aggregation for Video Object Detection","created":"2019-07-15","cited_by_count":87},{"id":"2112.08088","title":"Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions","created":"2021-12-15","cited_by_count":85},{"id":"1904.04474","title":"UG$^{2+}$ Track 2: A Collective Benchmark Effort for Evaluating and Advancing Image Understanding in Poor Visibility Environments","created":"2019-04-09","cited_by_count":84},{"id":"2205.03346","title":"Multitask AET with Orthogonal Tangent Regularity for Dark Object Detection","created":"2022-05-06","cited_by_count":59},{"id":"2109.03495","title":"Temporal RoI Align for Video Object Recognition","created":"2021-09-08","cited_by_count":44},{"id":"2002.11300","title":"Self-supervised Image Enhancement Network: Training with Low Light Images Only","created":"2020-02-26","cited_by_count":29},{"id":"2104.01984","title":"HLA-Face: Joint High-Low Adaptation for Low Light Face Detection","created":"2021-04-05","cited_by_count":28},{"id":"2007.10963","title":"Recurrent Exposure Generation for Low-Light Face Detection","created":"2020-07-21","cited_by_count":27},{"id":"2106.01483","title":"Multiscale Domain Adaptive YOLO for Cross-Domain Object Detection","created":"2021-06-02","cited_by_count":23},{"id":"2106.13939","title":"Domain Adaptive YOLO for One-Stage Cross-Domain Detection","created":"2021-06-26","cited_by_count":23},{"id":"2110.10364","title":"NOD: Taking a Closer Look at Detection under Extreme Low-Light Conditions with Night Object Detection Dataset","created":"2021-10-20","cited_by_count":12},{"id":"2210.02368","title":"Spatio-Temporal Learnable Proposals for End-to-End Video Object Detection","created":"2022-10-05","cited_by_count":8},{"id":"2301.06269","title":"DarkVision: A Benchmark for Low-light Image/Video Perception","created":"2023-01-16","cited_by_count":5},{"id":"2206.06258","title":"Featurized Query R-CNN","created":"2022-06-13","cited_by_count":4},{"id":"2201.08996","title":"Linear Array Network for Low-light Image Enhancement","created":"2022-01-22","cited_by_count":2}],"next_cursor":null}