{"list":"other","total":64,"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":"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":"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":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"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":"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":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"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":"2105.05537","title":"Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation","created":"2021-05-12","cited_by_count":1222},{"id":"1609.05158","title":"Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network","created":"2016-09-16","cited_by_count":1204},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"1801.00868","title":"Panoptic Segmentation","created":"2018-01-03","cited_by_count":802},{"id":"1906.09756","title":"Cascade R-CNN: High Quality Object Detection and Instance Segmentation","created":"2019-06-24","cited_by_count":429},{"id":"1902.06068","title":"Deep Learning for Image Super-resolution: A Survey","created":"2019-02-16","cited_by_count":369},{"id":"1505.04366","title":"Learning Deconvolution Network for Semantic Segmentation","created":"2015-05-17","cited_by_count":365},{"id":"2211.06220","title":"OneFormer: One Transformer to Rule Universal Image Segmentation","created":"2022-11-10","cited_by_count":328},{"id":"1903.00241","title":"Mask Scoring R-CNN","created":"2019-03-01","cited_by_count":266},{"id":"2209.08575","title":"SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation","created":"2022-09-18","cited_by_count":252},{"id":"2103.16562","title":"Boundary IoU: Improving Object-Centric Image Segmentation Evaluation","created":"2021-03-30","cited_by_count":188},{"id":"1901.03784","title":"UPSNet: A Unified Panoptic Segmentation Network","created":"2019-01-12","cited_by_count":175},{"id":"2003.04092","title":"Searching Central Difference Convolutional Networks for Face Anti-Spoofing","created":"2020-03-09","cited_by_count":173},{"id":"2108.07009","title":"Pixel Difference Networks for Efficient Edge Detection","created":"2021-08-16","cited_by_count":168},{"id":"2012.02310","title":"BoxInst: High-Performance Instance Segmentation with Box Annotations","created":"2020-12-03","cited_by_count":151},{"id":"1905.02188","title":"CARAFE: Content-Aware ReAssembly of FEatures","created":"2019-05-06","cited_by_count":119},{"id":"2203.14211","title":"DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimation","created":"2022-03-27","cited_by_count":118},{"id":"2403.10516","title":"FeatUp: A Model-Agnostic Framework for Features at Any Resolution","created":"2024-03-15","cited_by_count":116},{"id":"2004.02307","title":"EfficientPS: Efficient Panoptic Segmentation","created":"2020-04-05","cited_by_count":111},{"id":"2011.02062","title":"NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofing","created":"2020-11-03","cited_by_count":105},{"id":"1908.00672","title":"Indices Matter: Learning to Index for Deep Image Matting","created":"2019-08-02","cited_by_count":93},{"id":"2007.00047","title":"A Survey on Instance Segmentation: State of the art","created":"2020-06-28","cited_by_count":85},{"id":"2308.15085","title":"Learning to Upsample by Learning to Sample","created":"2023-08-29","cited_by_count":57},{"id":"1504.04531","title":"Hyperspectral pansharpening: a review","created":"2015-04-17","cited_by_count":55},{"id":"2110.10403","title":"AFTer-UNet: Axial Fusion Transformer UNet for Medical Image Segmentation","created":"2021-10-20","cited_by_count":48},{"id":"2105.01290","title":"Dual-Cross Central Difference Network for Face Anti-Spoofing","created":"2021-05-04","cited_by_count":47},{"id":"1608.06049","title":"Local Binary Convolutional Neural Networks","created":"2016-08-22","cited_by_count":38},{"id":"2011.14288","title":"Learning Affinity-Aware Upsampling for Deep Image Matting","created":"2020-11-29","cited_by_count":37},{"id":"2008.09412","title":"Searching Multi-Rate and Multi-Modal Temporal Enhanced Networks for Gesture Recognition","created":"2020-08-21","cited_by_count":36},{"id":"1903.02120","title":"Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregation","created":"2019-03-05","cited_by_count":34},{"id":"2209.12866","title":"SAPA: Similarity-Aware Point Affiliation for Feature Upsampling","created":"2022-09-26","cited_by_count":32},{"id":"2308.09294","title":"Self-Calibrated Cross Attention Network for Few-Shot Segmentation","created":"2023-08-18","cited_by_count":32},{"id":"2302.02057","title":"Semantic Diffusion Network for Semantic Segmentation","created":"2023-02-04","cited_by_count":30},{"id":"2403.14625","title":"LiFT: A Surprisingly Simple Lightweight Feature Transform for Dense ViT Descriptors","created":"2024-03-21","cited_by_count":27},{"id":"2207.10392","title":"FADE: Fusing the Assets of Decoder and Encoder for Task-Agnostic Upsampling","created":"2022-07-21","cited_by_count":25},{"id":"1807.07466","title":"Guided Upsampling Network for Real-Time Semantic Segmentation","created":"2018-07-19","cited_by_count":24},{"id":"1707.05847","title":"The Devil is in the Decoder: Classification, Regression and GANs","created":"2017-07-18","cited_by_count":22},{"id":"2012.04733","title":"CARAFE++: Unified Content-Aware ReAssembly of FEatures","created":"2020-12-07","cited_by_count":20},{"id":"1808.08413","title":"A Brief Survey and an Application of Semantic Image Segmentation for Autonomous Driving","created":"2018-08-25","cited_by_count":19},{"id":"2209.10305","title":"KXNet: A Model-Driven Deep Neural Network for Blind Super-Resolution","created":"2022-09-21","cited_by_count":18},{"id":"2402.00422","title":"Lightweight Pixel Difference Networks for Efficient Visual Representation Learning","created":"2024-02-01","cited_by_count":17},{"id":"2302.14578","title":"Interactive Segmentation as Gaussian Process Classification","created":"2023-02-28","cited_by_count":14},{"id":"1505.00996","title":"Fast Guided Filter","created":"2015-05-05","cited_by_count":12},{"id":"2309.15638","title":"RSF-Conv: Rotation-and-Scale Equivariant Fourier Parameterized Convolution for Retinal Vessel Segmentation","created":"2023-09-27","cited_by_count":5},{"id":"2303.08414","title":"From Local Binary Patterns to Pixel Difference Networks for Efficient Visual Representation Learning","created":"2023-03-15","cited_by_count":1},{"id":"2307.08198","title":"On Point Affiliation in Feature Upsampling","created":"2023-07-17","cited_by_count":1}],"next_cursor":null}