{"list":"other","total":52,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"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":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"2012.00364","title":"Pre-Trained Image Processing Transformer","created":"2020-12-01","cited_by_count":893},{"id":"2009.06732","title":"Efficient Transformers: A Survey","created":"2020-09-14","cited_by_count":790},{"id":"1609.01775","title":"Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking","created":"2016-09-06","cited_by_count":692},{"id":"2012.12556","title":"A Survey on Visual Transformer","created":"2020-12-23","cited_by_count":654},{"id":"1906.05909","title":"Stand-Alone Self-Attention in Vision Models","created":"2019-06-13","cited_by_count":542},{"id":"1905.05055","title":"Object Detection in 20 Years: A Survey","created":"2019-05-13","cited_by_count":531},{"id":"1605.06409","title":"R-FCN: Object Detection via Region-based Fully Convolutional Networks","created":"2016-05-20","cited_by_count":414},{"id":"1802.10062","title":"CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes","created":"2018-02-27","cited_by_count":267},{"id":"1904.11491","title":"Local Relation Networks for Image Recognition","created":"2019-04-25","cited_by_count":210},{"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":"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":"2009.13077","title":"Distribution Matching for Crowd Counting","created":"2020-09-28","cited_by_count":143},{"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":"1612.04402","title":"Finding Tiny Faces","created":"2016-12-13","cited_by_count":72},{"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":"1909.06966","title":"Perspective-Guided Convolution Networks for Crowd Counting","created":"2019-09-16","cited_by_count":54},{"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":"1908.08692","title":"Crowd Counting with Deep Structured Scale Integration Network","created":"2019-08-23","cited_by_count":46},{"id":"2003.12783","title":"CNN-based Density Estimation and Crowd Counting: A Survey","created":"2020-03-28","cited_by_count":43},{"id":"2011.09763","title":"Attention-Based Transformers for Instance Segmentation of Cells in Microstructures","created":"2020-11-19","cited_by_count":38},{"id":"1907.10255","title":"HA-CCN: Hierarchical Attention-based Crowd Counting Network","created":"2019-07-24","cited_by_count":32},{"id":"1907.07911","title":"Locality-constrained Spatial Transformer Network for Video Crowd Counting","created":"2019-07-18","cited_by_count":30},{"id":"2007.08260","title":"Weighing Counts: Sequential Crowd Counting by Reinforcement Learning","created":"2020-07-16","cited_by_count":30},{"id":"1707.07890","title":"Spatiotemporal Modeling for Crowd Counting in Videos","created":"2017-07-25","cited_by_count":27},{"id":"1807.00601","title":"Crowd Counting using Deep Recurrent Spatial-Aware Network","created":"2018-07-02","cited_by_count":21},{"id":"2002.00092","title":"Hybrid Graph Neural Networks for Crowd Counting","created":"2020-01-31","cited_by_count":21},{"id":"1811.02805","title":"PaDNet: Pan-Density Crowd Counting","created":"2018-11-07","cited_by_count":16},{"id":"1705.10118","title":"Beyond Counting: Comparisons of Density Maps for Crowd Analysis Tasks - Counting, Detection, and Tracking","created":"2017-05-29","cited_by_count":15},{"id":"1911.10782","title":"Estimating People Flows to Better Count Them in Crowded Scenes","created":"2019-11-25","cited_by_count":12},{"id":"2012.00452","title":"Counting People by Estimating People Flows","created":"2020-12-01","cited_by_count":11},{"id":"1811.11662","title":"Robust Face Detection via Learning Small Faces on Hard Images","created":"2018-11-28","cited_by_count":9},{"id":"2007.06146","title":"Fine-Grained Crowd Counting","created":"2020-07-13","cited_by_count":9},{"id":"1811.07170","title":"Optical Flow Dataset and Benchmark for Visual Crowd Analysis","created":"2018-11-17","cited_by_count":8},{"id":"1912.01811","title":"Drone-based Joint Density Map Estimation, Localization and Tracking with Space-Time Multi-Scale Attention Network","created":"2019-12-04","cited_by_count":5}],"next_cursor":null}