{"list":"other","total":82,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"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":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"2110.04544","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","created":"2021-10-09","cited_by_count":1026},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"1709.02371","title":"PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume","created":"2017-09-07","cited_by_count":968},{"id":"1612.03716","title":"COCO-Stuff: Thing and Stuff Classes in Context","created":"2016-12-12","cited_by_count":864},{"id":"1801.00868","title":"Panoptic Segmentation","created":"2018-01-03","cited_by_count":802},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797},{"id":"2203.16527","title":"Exploring Plain Vision Transformer Backbones for Object Detection","created":"2022-03-30","cited_by_count":724},{"id":"2201.03546","title":"Language-driven Semantic Segmentation","created":"2022-01-10","cited_by_count":717},{"id":"2112.01071","title":"Extract Free Dense Labels from CLIP","created":"2021-12-02","cited_by_count":583},{"id":"1909.11065","title":"Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation","created":"2019-09-24","cited_by_count":576},{"id":"2106.04803","title":"CoAtNet: Marrying Convolution and Attention for All Data Sizes","created":"2021-06-09","cited_by_count":569},{"id":"2210.04150","title":"Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP","created":"2022-10-09","cited_by_count":565},{"id":"1803.08669","title":"Pyramid Stereo Matching Network","created":"2018-03-23","cited_by_count":489},{"id":"2112.12143","title":"Scaling Open-Vocabulary Image Segmentation with Image-Level Labels","created":"2021-12-22","cited_by_count":473},{"id":"2111.03930","title":"Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling","created":"2021-11-06","cited_by_count":431},{"id":"1703.04309","title":"End-to-End Learning of Geometry and Context for Deep Stereo Regression","created":"2017-03-13","cited_by_count":360},{"id":"2302.12242","title":"Side Adapter Network for Open-Vocabulary Semantic Segmentation","created":"2023-02-23","cited_by_count":300},{"id":"2212.11270","title":"Generalized Decoding for Pixel, Image, and Language","created":"2022-12-21","cited_by_count":294},{"id":"2203.16194","title":"FlowFormer: A Transformer Architecture for Optical Flow","created":"2022-03-30","cited_by_count":275},{"id":"1906.00817","title":"Zero-Shot Semantic Segmentation","created":"2019-06-03","cited_by_count":245},{"id":"1903.04025","title":"Group-wise Correlation Stereo Network","created":"2019-03-10","cited_by_count":235},{"id":"1912.03098","title":"Connecting Vision and Language with Localized Narratives","created":"2019-12-06","cited_by_count":226},{"id":"2112.14757","title":"A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model","created":"2021-12-29","cited_by_count":223},{"id":"2112.07910","title":"Decoupling Zero-Shot Semantic Segmentation","created":"2021-12-15","cited_by_count":199},{"id":"2303.08131","title":"A Simple Framework for Open-Vocabulary Segmentation and Detection","created":"2023-03-14","cited_by_count":198},{"id":"1905.12886","title":"iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images","created":"2019-05-30","cited_by_count":197},{"id":"2012.02951","title":"FloodNet: A High Resolution Aerial Imagery Dataset for Post Flood Scene Understanding","created":"2020-12-05","cited_by_count":181},{"id":"2212.03588","title":"ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentation","created":"2022-12-07","cited_by_count":178},{"id":"2203.15102","title":"Rethinking Semantic Segmentation: A Prototype View","created":"2022-03-28","cited_by_count":140},{"id":"1703.05593","title":"Convolutional neural network architecture for geometric matching","created":"2017-03-16","cited_by_count":138},{"id":"1912.06704","title":"Hierarchical Deep Stereo Matching on High-resolution Images","created":"2019-12-13","cited_by_count":126},{"id":"2004.01547","title":"Context Prior for Scene Segmentation","created":"2020-04-03","cited_by_count":121},{"id":"2207.10866","title":"Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation","created":"2022-07-22","cited_by_count":114},{"id":"2004.01241","title":"Semantic Segmentation of Underwater Imagery: Dataset and Benchmark","created":"2020-04-02","cited_by_count":95},{"id":"2203.09795","title":"Three things everyone should know about Vision Transformers","created":"2022-03-18","cited_by_count":90},{"id":"1909.10980","title":"PST900: RGB-Thermal Calibration, Dataset and Segmentation Network","created":"2019-09-20","cited_by_count":85},{"id":"2106.02520","title":"CATs: Cost Aggregation Transformers for Visual Correspondence","created":"2021-06-04","cited_by_count":77},{"id":"1703.08769","title":"Open Vocabulary Scene Parsing","created":"2017-03-26","cited_by_count":76},{"id":"2011.08065","title":"Kvasir-Instrument: Diagnostic and therapeutic tool segmentation dataset in gastrointestinal endoscopy","created":"2020-10-23","cited_by_count":54},{"id":"2103.13318","title":"Factors of Influence for Transfer Learning across Diverse Appearance Domains and Task Types","created":"2021-03-24","cited_by_count":54},{"id":"2109.04310","title":"Deep Hough Voting for Robust Global Registration","created":"2021-09-09","cited_by_count":53},{"id":"2202.06817","title":"CATs++: Boosting Cost Aggregation with Convolutions and Transformers","created":"2022-02-14","cited_by_count":53},{"id":"2101.00442","title":"CryoNuSeg: A Dataset for Nuclei Instance Segmentation of Cryosectioned H&E-Stained Histological Images","created":"2021-01-02","cited_by_count":51},{"id":"2108.11819","title":"Mining Contextual Information Beyond Image for Semantic Segmentation","created":"2021-08-26","cited_by_count":48},{"id":"2106.02740","title":"ZeroWaste Dataset: Towards Deformable Object Segmentation in Cluttered Scenes","created":"2021-06-04","cited_by_count":47},{"id":"2105.05409","title":"A Large-Scale Benchmark for Food Image Segmentation","created":"2021-05-12","cited_by_count":45},{"id":"2103.16831","title":"Convolutional Hough Matching Networks","created":"2021-03-31","cited_by_count":43},{"id":"2204.00179","title":"GraftNet: Towards Domain Generalized Stereo Matching with a Broad-Spectrum and Task-Oriented Feature","created":"2022-04-01","cited_by_count":43},{"id":"2010.07347","title":"Matching-space Stereo Networks for Cross-domain Generalization","created":"2020-10-14","cited_by_count":32},{"id":"2210.02689","title":"Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondence","created":"2022-10-06","cited_by_count":32},{"id":"2004.04627","title":"AdaStereo: A Simple and Efficient Approach for Adaptive Stereo Matching","created":"2020-04-09","cited_by_count":31},{"id":"2210.03416","title":"Detailed Annotations of Chest X-Rays via CT Projection for Report Understanding","created":"2022-10-07","cited_by_count":26},{"id":"2203.03238","title":"Semantic Segmentation in Art Paintings","created":"2022-03-07","cited_by_count":23},{"id":"2111.11567","title":"ATLANTIS: A Benchmark for Semantic Segmentation of Waterbody Images","created":"2021-11-22","cited_by_count":10}],"next_cursor":null}