{"list":"other","total":53,"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"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":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"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":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"id":"2004.10934","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","created":"2020-04-23","cited_by_count":1630},{"id":"2102.04306","title":"TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation","created":"2021-02-08","cited_by_count":1558},{"id":"1511.00561","title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","created":"2015-11-02","cited_by_count":1487},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"id":"2107.08430","title":"YOLOX: Exceeding YOLO Series in 2021","created":"2021-07-18","cited_by_count":1071},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"1808.00897","title":"BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation","created":"2018-08-02","cited_by_count":645},{"id":"1912.05074","title":"UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation","created":"2019-12-11","cited_by_count":586},{"id":"1412.7062","title":"Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs","created":"2014-12-22","cited_by_count":554},{"id":"1712.00559","title":"Progressive Neural Architecture Search","created":"2017-12-02","cited_by_count":487},{"id":"2104.01136","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","created":"2021-04-02","cited_by_count":475},{"id":"2005.09007","title":"U$^2$-Net: Going Deeper with Nested U-Structure for Salient Object Detection","created":"2020-05-18","cited_by_count":412},{"id":"2003.09005","title":"Semi-Supervised Semantic Segmentation with Cross-Consistency Training","created":"2020-03-19","cited_by_count":376},{"id":"2307.04767","title":"Semantic-SAM: Segment and Recognize Anything at Any Granularity","created":"2023-07-10","cited_by_count":185},{"id":"1901.06340","title":"Feature Pyramid and Hierarchical Boosting Network for Pavement Crack Detection","created":"2019-01-18","cited_by_count":80},{"id":"1905.02423","title":"LEDNet: A Lightweight Encoder-Decoder Network for Real-Time Semantic Segmentation","created":"2019-05-07","cited_by_count":50},{"id":"1801.09454","title":"Road Damage Detection Using Deep Neural Networks with Images Captured Through a Smartphone","created":"2018-01-29","cited_by_count":45},{"id":"1908.00894","title":"Pothole Detection Based on Disparity Transformation and Road Surface Modeling","created":"2019-08-02","cited_by_count":38},{"id":"1904.08582","title":"Road Crack Detection Using Deep Convolutional Neural Network and Adaptive Thresholding","created":"2019-04-18","cited_by_count":33},{"id":"2209.08538","title":"RDD2022: A multi-national image dataset for automatic Road Damage Detection","created":"2022-09-18","cited_by_count":32},{"id":"2012.10802","title":"Rethinking Road Surface 3D Reconstruction and Pothole Detection: From Perspective Transformation to Disparity Map Segmentation","created":"2020-12-19","cited_by_count":27},{"id":"1910.04988","title":"Road Damage Detection Based on Unsupervised Disparity Map Segmentation","created":"2019-10-11","cited_by_count":24},{"id":"2301.04648","title":"Head-Free Lightweight Semantic Segmentation with Linear Transformer","created":"2023-01-11","cited_by_count":22},{"id":"2312.17071","title":"SCTNet: Single-Branch CNN with Transformer Semantic Information for Real-Time Segmentation","created":"2023-12-28","cited_by_count":22},{"id":"2302.11728","title":"A Convolutional-Transformer Network for Crack Segmentation with Boundary Awareness","created":"2023-02-23","cited_by_count":12},{"id":"2010.15021","title":"Road Damage Detection and Classification with Detectron2 and Faster R-CNN","created":"2020-10-28","cited_by_count":11},{"id":"2001.11175","title":"Unsupervised Pixel-level Road Defect Detection via Adversarial Image-to-Frequency Transform","created":"2020-01-30","cited_by_count":9},{"id":"2205.01198","title":"NHA12D: A New Pavement Crack Dataset and a Comparison Study Of Crack Detection Algorithms","created":"2022-05-02","cited_by_count":8},{"id":"2005.13298","title":"An Iteratively Optimized Patch Label Inference Network for Automatic Pavement Distress Detection","created":"2020-05-27","cited_by_count":7},{"id":"2109.00456","title":"Weakly-Supervised Surface Crack Segmentation by Generating Pseudo-Labels using Localization with a Classifier and Thresholding","created":"2021-09-01","cited_by_count":6},{"id":"2401.15647","title":"UP-CrackNet: Unsupervised Pixel-Wise Road Crack Detection via Adversarial Image Restoration","created":"2024-01-28","cited_by_count":6},{"id":"2304.08842","title":"UDTIRI: An Online Open-Source Intelligent Road Inspection Benchmark Suite","created":"2023-04-18","cited_by_count":4}],"next_cursor":null}