{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"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":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"2102.04306","title":"TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation","created":"2021-02-08","cited_by_count":1558},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"2012.00364","title":"Pre-Trained Image Processing Transformer","created":"2020-12-01","cited_by_count":893},{"id":"2006.03677","title":"Visual Transformers: Token-based Image Representation and Processing for Computer Vision","created":"2020-06-05","cited_by_count":334},{"id":"2102.10662","title":"Medical Transformer: Gated Axial-Attention for Medical Image Segmentation","created":"2021-02-21","cited_by_count":320},{"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":"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":"2012.09793","title":"SceneFormer: Indoor Scene Generation with Transformers","created":"2020-12-17","cited_by_count":158},{"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":"2011.04233","title":"End-to-end Lane Shape Prediction with Transformers","created":"2020-11-09","cited_by_count":111},{"id":"2004.03597","title":"JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method","created":"2020-04-07","cited_by_count":109},{"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":"2012.12482","title":"Localization in the Crowd with Topological Constraints","created":"2020-12-23","cited_by_count":68},{"id":"1904.01333","title":"Point in, Box out: Beyond Counting Persons in Crowds","created":"2019-04-02","cited_by_count":62},{"id":"1903.00853","title":"Crowd Counting and Density Estimation by Trellis Encoder-Decoder Network","created":"2019-03-03","cited_by_count":56},{"id":"1708.00953","title":"Generating High-Quality Crowd Density Maps using Contextual Pyramid CNNs","created":"2017-08-02","cited_by_count":55},{"id":"1909.06966","title":"Perspective-Guided Convolution Networks for Crowd Counting","created":"2019-09-16","cited_by_count":54},{"id":"1902.06285","title":"Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rank","created":"2019-02-17","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":"1807.09959","title":"Iterative Crowd Counting","created":"2018-07-26","cited_by_count":48},{"id":"1908.06473","title":"From Open Set to Closed Set: Counting Objects by Spatial Divide-and-Conquer","created":"2019-08-15","cited_by_count":48},{"id":"1908.08692","title":"Crowd Counting with Deep Structured Scale Integration Network","created":"2019-08-23","cited_by_count":46},{"id":"1811.11968","title":"ADCrowdNet: An Attention-injective Deformable Convolutional Network for Crowd Understanding","created":"2018-11-29","cited_by_count":45},{"id":"2103.15320","title":"TFPose: Direct Human Pose Estimation with Transformers","created":"2021-03-29","cited_by_count":42},{"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":"2102.07925","title":"Focal Inverse Distance Transform Maps for Crowd Localization","created":"2021-02-16","cited_by_count":36},{"id":"1912.09632","title":"AutoScale: Learning to Scale for Crowd Counting and Localization","created":"2019-12-20","cited_by_count":35},{"id":"1903.12206","title":"Counting with Focus for Free","created":"2019-03-28","cited_by_count":33},{"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":"1907.12428","title":"Learn to Scale: Generating Multipolar Normalized Density Maps for Crowd Counting","created":"2019-07-29","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":"1707.09476","title":"FCN-rLSTM: Deep Spatio-Temporal Neural Networks for Vehicle Counting in City Cameras","created":"2017-07-29","cited_by_count":27},{"id":"1907.02724","title":"C^3 Framework: An Open-source PyTorch Code for Crowd Counting","created":"2019-07-05","cited_by_count":18},{"id":"2012.08149","title":"Dilated-Scale-Aware Attention ConvNet For Multi-Class Object Counting","created":"2020-12-15","cited_by_count":10}],"next_cursor":null}