OTP-NMS: Toward Optimal Threshold Prediction of NMS for Crowded Pedestrian Detection
Author:
Affiliation:
1. College of Electrical and Information Engineering, Hunan University, Changsha, China
2. Oracle, Pleasanton, CA, USA
3. School of Electrical and Information Engineering, The University of Sydney, Sydney, NSW, Australia
Funder
National Natural Science Foundation of China
National Key Research and Development Program of China
Key Research and Development Program of Hunan Province
Hunan Provincial Innovation Foundation for Postgraduates
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Subject
Computer Graphics and Computer-Aided Design,Software
Link
http://xplorestaging.ieee.org/ielx7/83/9991910/10130101.pdf?arnumber=10130101
Reference57 articles.
1. CrowdHuman: A benchmark for detecting human in a crowd;shao;arXiv 1805 00123,2018
2. Deep model reassembly;yang;Proc Adv Neural Inf Process Syst,2022
3. Adaptive NMS: Refining Pedestrian Detection in a Crowd
4. Factorizing Knowledge in Neural Networks
5. Multi-label Learning of Part Detectors for Heavily Occluded Pedestrian Detection
Cited by 10 articles. 订阅此论文施引文献 订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献
1. Robust pedestrian detection via constructing versatile pedestrian knowledge bank;Pattern Recognition;2024-09
2. Differential Feature Fusion, Triplet Global Attention, and Web Semantic for Pedestrian Detection;International Journal on Semantic Web and Information Systems;2024-07-16
3. Key points and visible part fusion attention network for occluded pedestrian detection in traffic environments;Optoelectronics Letters;2024-05-30
4. Recognition of occluded pedestrians from the driver's perspective for extending sight distance and ensuring driving safety at signal-free intersections;Digital Transportation and Safety;2024
5. Ranking-Based Adaptive Query Generation for Detrs in Crowded Pedestrian Detection;2024
1.学者识别学者识别
2.学术分析学术分析
3.人才评估人才评估
"同舟云学术"是以全球学者为主线，采集、加工和组织学术论文而形成的新型学术文献查询和分析系统，可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容，当前同舟云学术共收录了国内外主流学术期刊6万余种，收集的期刊论文及会议论文总量共计约1.5亿篇，并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询！咨询电话：010-8811{复制后删除}0370
www.globalauthorid.com
TOP
Copyright © 2019-2024 北京同舟云网络信息技术有限公司 京公网安备11010802033243号 京ICP备18003416号-3