{"list":"other","total":62,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"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":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"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":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"1707.06484","title":"Deep Layer Aggregation","created":"2017-07-20","cited_by_count":436},{"id":"1802.10062","title":"CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes","created":"2018-02-27","cited_by_count":267},{"id":"2103.11681","title":"Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking","created":"2021-03-22","cited_by_count":220},{"id":"2102.12219","title":"Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges","created":"2021-02-24","cited_by_count":204},{"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":"2001.08248","title":"How Much Position Information Do Convolutional Neural Networks Encode?","created":"2020-01-22","cited_by_count":172},{"id":"1904.09146","title":"Salient Object Detection in the Deep Learning Era: An In-Depth Survey","created":"2019-04-19","cited_by_count":164},{"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":"2107.12746","title":"Rethinking Counting and Localization in Crowds:A Purely Point-Based Framework","created":"2021-07-27","cited_by_count":152},{"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":"2105.14103","title":"An Attention Free Transformer","created":"2021-05-28","cited_by_count":112},{"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":"1609.04453","title":"A Large Contextual Dataset for Classification, Detection and Counting of Cars with Deep Learning","created":"2016-09-14","cited_by_count":86},{"id":"1906.07538","title":"Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detection","created":"2019-06-18","cited_by_count":73},{"id":"2203.02636","title":"Boosting Crowd Counting via Multifaceted Attention","created":"2022-03-05","cited_by_count":73},{"id":"1904.00853","title":"Precise Detection in Densely Packed Scenes","created":"2019-04-01","cited_by_count":63},{"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":"1803.03095","title":"Leveraging Unlabeled Data for Crowd Counting by Learning to Rank","created":"2018-03-08","cited_by_count":57},{"id":"1903.00853","title":"Crowd Counting and Density Estimation by Trellis Encoder-Decoder Network","created":"2019-03-03","cited_by_count":56},{"id":"1807.09856","title":"Where are the Blobs: Counting by Localization with Point Supervision","created":"2018-07-25","cited_by_count":54},{"id":"2206.05253","title":"Rethinking Spatial Invariance of Convolutional Networks for Object Counting","created":"2022-06-10","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":"1712.06679","title":"DecideNet: Counting Varying Density Crowds Through Attention Guided Detection and Density Estimation","created":"2017-12-18","cited_by_count":49},{"id":"1811.11968","title":"ADCrowdNet: An Attention-injective Deformable Convolutional Network for Crowd Understanding","created":"2018-11-29","cited_by_count":45},{"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":"1908.10937","title":"Multi-Level Bottom-Top and Top-Bottom Feature Fusion for Crowd Counting","created":"2019-08-28","cited_by_count":36},{"id":"2007.12831","title":"A Self-Training Approach for Point-Supervised Object Detection and Counting in Crowds","created":"2020-07-25","cited_by_count":36},{"id":"1905.10085","title":"PCC Net: Perspective Crowd Counting via Spatial Convolutional Network","created":"2019-05-24","cited_by_count":33},{"id":"1910.12384","title":"Pushing the Frontiers of Unconstrained Crowd Counting: New Dataset and Benchmark Method","created":"2019-10-28","cited_by_count":32},{"id":"2007.08260","title":"Weighing Counts: Sequential Crowd Counting by Reinforcement Learning","created":"2020-07-16","cited_by_count":30},{"id":"1908.03716","title":"SCAR: Spatial-/Channel-wise Attention Regression Networks for Crowd Counting","created":"2019-08-10","cited_by_count":28},{"id":"2005.05776","title":"Adaptive Mixture Regression Network with Local Counting Map for Crowd Counting","created":"2020-05-12","cited_by_count":28},{"id":"1912.03677","title":"Domain-adaptive Crowd Counting via High-quality Image Translation and Density Reconstruction","created":"2019-12-08","cited_by_count":26},{"id":"2101.12322","title":"Position, Padding and Predictions: A Deeper Look at Position Information in CNNs","created":"2021-01-28","cited_by_count":26},{"id":"2012.04164","title":"Learning Independent Instance Maps for Crowd Localization","created":"2020-12-08","cited_by_count":24},{"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":"2004.02133","title":"Neuron Linear Transformation: Modeling the Domain Shift for Crowd Counting","created":"2020-04-05","cited_by_count":19},{"id":"2002.12256","title":"ZoomCount: A Zooming Mechanism for Crowd Counting in Static Images","created":"2020-02-27","cited_by_count":17},{"id":"2104.12505","title":"Dense Point Prediction: A Simple Baseline for Crowd Counting and Localization","created":"2021-04-26","cited_by_count":10},{"id":"1604.08660","title":"Crowd Counting via Weighted VLAD on Dense Attribute Feature Maps","created":"2016-04-29","cited_by_count":6},{"id":"1901.00039","title":"Mask-aware networks for crowd counting","created":"2018-12-18","cited_by_count":6},{"id":"1507.08445","title":"People Counting in High Density Crowds from Still Images","created":"2015-07-30","cited_by_count":4},{"id":"1612.07019","title":"Robust Learning with Kernel Mean p-Power Error Loss","created":"2016-12-21","cited_by_count":4},{"id":"1903.11249","title":"W-Net: Reinforced U-Net for Density Map Estimation","created":"2019-03-27","cited_by_count":4},{"id":"1905.10115","title":"Multi-Kernel Correntropy for Robust Learning","created":"2019-05-24","cited_by_count":4}],"next_cursor":null}