{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"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":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"1911.11763","title":"SuperGlue: Learning Feature Matching with Graph Neural Networks","created":"2019-11-26","cited_by_count":1443},{"id":"1712.07629","title":"SuperPoint: Self-Supervised Interest Point Detection and Description","created":"2017-12-20","cited_by_count":1320},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"2104.00680","title":"LoFTR: Detector-Free Local Feature Matching with Transformers","created":"2021-04-01","cited_by_count":984},{"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":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"id":"2106.02034","title":"DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification","created":"2021-06-03","cited_by_count":864},{"id":"1612.01925","title":"FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks","created":"2016-12-06","cited_by_count":784},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764},{"id":"1804.00607","title":"MegaDepth: Learning Single-View Depth Prediction from Internet Photos","created":"2018-04-02","cited_by_count":737},{"id":"1809.06839","title":"Albumentations: fast and flexible image augmentations","created":"2018-09-18","cited_by_count":560},{"id":"1812.03506","title":"From Coarse to Fine: Robust Hierarchical Localization at Large Scale","created":"2018-12-09","cited_by_count":559},{"id":"2102.03902","title":"Nystr\\\"omformer: A Nystr\\\"om-Based Algorithm for Approximating Self-Attention","created":"2021-02-07","cited_by_count":471},{"id":"2106.14881","title":"Early Convolutions Help Transformers See Better","created":"2021-06-28","cited_by_count":396},{"id":"2012.15460","title":"TransTrack: Multiple Object Tracking with Transformer","created":"2020-12-31","cited_by_count":371},{"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":"1905.03561","title":"D2-Net: A Trainable CNN for Joint Detection and Description of Local Features","created":"2019-05-09","cited_by_count":326},{"id":"2006.13566","title":"DISK: Learning local features with policy gradient","created":"2020-06-24","cited_by_count":312},{"id":"2107.00641","title":"Focal Self-attention for Local-Global Interactions in Vision Transformers","created":"2021-07-01","cited_by_count":288},{"id":"1903.07593","title":"Learning Correspondence from the Cycle-Consistency of Time","created":"2019-03-18","cited_by_count":269},{"id":"2006.14613","title":"Space-Time Correspondence as a Contrastive Random Walk","created":"2020-06-25","cited_by_count":239},{"id":"1906.06195","title":"R2D2: Repeatable and Reliable Detector and Descriptor","created":"2019-06-14","cited_by_count":207},{"id":"2104.01538","title":"Hypercorrelation Squeeze for Few-Shot Segmentation","created":"2021-04-04","cited_by_count":193},{"id":"2103.14167","title":"COTR: Correspondence Transformer for Matching Across Images","created":"2021-03-25","cited_by_count":183},{"id":"1810.10510","title":"Neighbourhood Consensus Networks","created":"2018-10-24","cited_by_count":174},{"id":"1907.12347","title":"FSS-1000: A 1000-Class Dataset for Few-Shot Segmentation","created":"2019-07-29","cited_by_count":160},{"id":"1908.10543","title":"SPair-71k: A Large-scale Benchmark for Semantic Correspondence","created":"2019-08-28","cited_by_count":146},{"id":"1912.05524","title":"GLU-Net: Global-Local Universal Network for Dense Flow and Correspondences","created":"2019-12-11","cited_by_count":139},{"id":"1703.05593","title":"Convolutional neural network architecture for geometric matching","created":"2017-03-16","cited_by_count":138},{"id":"1705.01088","title":"Visual Attribute Transfer through Deep Image Analogy","created":"2017-05-02","cited_by_count":123},{"id":"2101.01710","title":"Learning Accurate Dense Correspondences and When to Trust Them","created":"2021-01-05","cited_by_count":113},{"id":"2004.10566","title":"Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions","created":"2020-04-22","cited_by_count":93},{"id":"2006.08844","title":"Dual-Resolution Correspondence Networks","created":"2020-06-16","cited_by_count":90},{"id":"2111.12763","title":"Sparse is Enough in Scaling Transformers","created":"2021-11-24","cited_by_count":86},{"id":"1606.03558","title":"Universal Correspondence Network","created":"2016-06-11","cited_by_count":82},{"id":"2105.13677","title":"ResT: An Efficient Transformer for Visual Recognition","created":"2021-05-28","cited_by_count":79},{"id":"2106.02520","title":"CATs: Cost Aggregation Transformers for Visual Correspondence","created":"2021-06-04","cited_by_count":77},{"id":"2110.03860","title":"Token Pooling in Vision Transformers","created":"2021-10-08","cited_by_count":69},{"id":"1810.08393","title":"DGC-Net: Dense Geometric Correspondence Network","created":"2018-10-19","cited_by_count":67},{"id":"2103.12236","title":"Instance-level Image Retrieval using Reranking Transformers","created":"2021-03-22","cited_by_count":63},{"id":"2112.05143","title":"GAN-Supervised Dense Visual Alignment","created":"2021-12-09","cited_by_count":62},{"id":"2108.09084","title":"Fastformer: Additive Attention Can Be All You Need","created":"2021-08-20","cited_by_count":61},{"id":"1712.06861","title":"End-to-end weakly-supervised semantic alignment","created":"2017-12-19","cited_by_count":60},{"id":"1904.01810","title":"SFNet: Learning Object-aware Semantic Correspondence","created":"2019-04-03","cited_by_count":60},{"id":"1511.05065","title":"Proposal Flow","created":"2015-11-16","cited_by_count":57},{"id":"1908.06537","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","created":"2019-08-18","cited_by_count":56},{"id":"2007.10587","title":"Learning to Compose Hypercolumns for Visual Correspondence","created":"2020-07-21","cited_by_count":53},{"id":"2009.07823","title":"GOCor: Bringing Globally Optimized Correspondence Volumes into Your Neural Network","created":"2020-09-16","cited_by_count":53},{"id":"1705.04043","title":"SCNet: Learning Semantic Correspondence","created":"2017-05-11","cited_by_count":48},{"id":"2004.01526","title":"RANSAC-Flow: generic two-stage image alignment","created":"2020-04-03","cited_by_count":48},{"id":"1703.07144","title":"Proposal Flow: Semantic Correspondences from Object Proposals","created":"2017-03-21","cited_by_count":47},{"id":"1909.03444","title":"Dynamic Context Correspondence Network for Semantic Alignment","created":"2019-09-08","cited_by_count":43},{"id":"2103.16831","title":"Convolutional Hough Matching Networks","created":"2021-03-31","cited_by_count":43},{"id":"1702.00926","title":"FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondence","created":"2017-02-03","cited_by_count":42},{"id":"2003.12059","title":"Correspondence Networks with Adaptive Neighbourhood Consensus","created":"2020-03-26","cited_by_count":42},{"id":"2108.08518","title":"Few-shot Segmentation with Optimal Transport Matching and Message Flow","created":"2021-08-19","cited_by_count":36},{"id":"1810.12155","title":"Recurrent Transformer Networks for Semantic Correspondence","created":"2018-10-29","cited_by_count":32},{"id":"2108.00211","title":"Multi-scale Matching Networks for Semantic Correspondence","created":"2021-07-31","cited_by_count":32},{"id":"1808.02128","title":"Attentive Semantic Alignment with Offset-Aware Correlation Kernels","created":"2018-08-06","cited_by_count":31},{"id":"2106.03090","title":"Deep Matching Prior: Test-Time Optimization for Dense Correspondence","created":"2021-06-06","cited_by_count":30},{"id":"1807.02939","title":"PARN: Pyramidal Affine Regression Networks for Dense Semantic Correspondence","created":"2018-07-09","cited_by_count":26},{"id":"1905.00875","title":"Self-supervised Learning for Video Correspondence Flow","created":"2019-05-02","cited_by_count":21},{"id":"1904.02969","title":"Semantic Attribute Matching Networks","created":"2019-04-05","cited_by_count":20},{"id":"2109.05221","title":"Convolutional Hough Matching Networks for Robust and Efficient Visual Correspondence","created":"2021-09-11","cited_by_count":12},{"id":"1403.0316","title":"Cross-Scale Cost Aggregation for Stereo Matching","created":"2014-03-03","cited_by_count":5}],"next_cursor":null}