{"list":"other","total":57,"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"2104.13840","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","created":"2021-04-28","cited_by_count":565},{"id":"1802.10062","title":"CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes","created":"2018-02-27","cited_by_count":267},{"id":"1904.04745","title":"Cross-Modal Self-Attention Network for Referring Image Segmentation","created":"2019-04-09","cited_by_count":263},{"id":"2001.06303","title":"Detection and Tracking Meet Drones Challenge","created":"2020-01-16","cited_by_count":263},{"id":"1808.01050","title":"Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds","created":"2018-08-02","cited_by_count":186},{"id":"1908.03684","title":"Bayesian Loss for Crowd Count Estimation with Point Supervision","created":"2019-08-10","cited_by_count":162},{"id":"1707.05972","title":"Drone-based Object Counting by Spatially Regularized Regional Proposal Network","created":"2017-07-19","cited_by_count":156},{"id":"2001.03360","title":"NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization","created":"2020-01-10","cited_by_count":151},{"id":"1811.10452","title":"Context-Aware Crowd Counting","created":"2018-11-26","cited_by_count":150},{"id":"1903.03303","title":"Learning from Synthetic Data for Crowd Counting in the Wild","created":"2019-03-08","cited_by_count":148},{"id":"2009.13077","title":"Distribution Matching for Crowd Counting","created":"2020-09-28","cited_by_count":143},{"id":"2004.03597","title":"JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method","created":"2020-04-07","cited_by_count":109},{"id":"1708.00199","title":"Switching Convolutional Neural Network for Crowd Counting","created":"2017-08-01","cited_by_count":93},{"id":"2202.13065","title":"An End-to-End Transformer Model for Crowd Localization","created":"2022-02-26","cited_by_count":74},{"id":"2203.02636","title":"Boosting Crowd Counting via Multifaceted Attention","created":"2022-03-05","cited_by_count":73},{"id":"1904.01333","title":"Point in, Box out: Beyond Counting Persons in Crowds","created":"2019-04-02","cited_by_count":62},{"id":"2104.09116","title":"TransCrowd: weakly-supervised crowd counting with transformers","created":"2021-04-19","cited_by_count":61},{"id":"1903.00853","title":"Crowd Counting and Density Estimation by Trellis Encoder-Decoder Network","created":"2019-03-03","cited_by_count":56},{"id":"1909.06966","title":"Perspective-Guided Convolution Networks for Crowd Counting","created":"2019-09-16","cited_by_count":54},{"id":"1608.06197","title":"CrowdNet: A Deep Convolutional Network for Dense Crowd Counting","created":"2016-08-22","cited_by_count":52},{"id":"1902.06285","title":"Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rank","created":"2019-02-17","cited_by_count":52},{"id":"2012.04529","title":"Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting","created":"2020-12-08","cited_by_count":52},{"id":"1712.06679","title":"DecideNet: Counting Varying Density Crowds Through Attention Guided Detection and Density Estimation","created":"2017-12-18","cited_by_count":49},{"id":"1807.01989","title":"Revisiting Perspective Information for Efficient Crowd Counting","created":"2018-07-05","cited_by_count":49},{"id":"2003.12783","title":"CNN-based Density Estimation and Crowd Counting: A Survey","created":"2020-03-28","cited_by_count":43},{"id":"1707.09605","title":"CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Counting","created":"2017-07-30","cited_by_count":41},{"id":"1505.07293","title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Robust Semantic Pixel-Wise Labelling","created":"2015-05-27","cited_by_count":37},{"id":"1905.10085","title":"PCC Net: Perspective Crowd Counting via Spatial Convolutional Network","created":"2019-05-24","cited_by_count":33},{"id":"2003.00164","title":"Towards Using Count-level Weak Supervision for Crowd Counting","created":"2020-02-29","cited_by_count":33},{"id":"2007.08260","title":"Weighing Counts: Sequential Crowd Counting by Reinforcement Learning","created":"2020-07-16","cited_by_count":30},{"id":"2109.14483","title":"CCTrans: Simplifying and Improving Crowd Counting with Transformer","created":"2021-09-29","cited_by_count":30},{"id":"1707.01202","title":"A Survey of Recent Advances in CNN-based Single Image Crowd Counting and Density Estimation","created":"2017-07-05","cited_by_count":29},{"id":"1810.03272","title":"Light-Weight RefineNet for Real-Time Semantic Segmentation","created":"2018-10-08","cited_by_count":27},{"id":"1702.02359","title":"Multi-scale Convolutional Neural Networks for Crowd Counting","created":"2017-02-08","cited_by_count":26},{"id":"1711.04433","title":"Crowd counting via scale-adaptive convolutional neural network","created":"2017-11-13","cited_by_count":23},{"id":"2003.05586","title":"Encoder-Decoder Based Convolutional Neural Networks with Multi-Scale-Aware Modules for Crowd Counting","created":"2020-03-12","cited_by_count":22},{"id":"2202.08517","title":"TAFNet: A Three-Stream Adaptive Fusion Network for RGB-T Crowd Counting","created":"2022-02-17","cited_by_count":15},{"id":"2202.13660","title":"FusionCount: Efficient Crowd Counting via Multiscale Feature Fusion","created":"2022-02-28","cited_by_count":13},{"id":"2112.15509","title":"Scene-Adaptive Attention Network for Crowd Counting","created":"2021-12-31","cited_by_count":12},{"id":"2108.00584","title":"Congested Crowd Instance Localization with Dilated Convolutional Swin Transformer","created":"2021-08-02","cited_by_count":11},{"id":"2002.06515","title":"A Real-Time Deep Network for Crowd Counting","created":"2020-02-16","cited_by_count":7},{"id":"1908.03314","title":"Deep Density-aware Count Regressor","created":"2019-08-09","cited_by_count":6},{"id":"1904.02774","title":"Crowd Transformer Network","created":"2019-04-04","cited_by_count":5},{"id":"2012.15685","title":"A Survey on Deep Learning-based Single Image Crowd Counting: Network Design, Loss Function and Supervisory Signal","created":"2020-12-31","cited_by_count":5},{"id":"2202.03843","title":"A Unified Multi-Task Learning Framework of Real-Time Drone Supervision for Crowd Counting","created":"2022-02-08","cited_by_count":5}],"next_cursor":null}