A Weakly Supervised Learning Framework Utilizing Enhanced Class Activation Map for Object Detection in Construction Sites-Reference-Cited by-同舟云学术

登录注册会员服务联系我们

A Weakly Supervised Learning Framework Utilizing Enhanced Class Activation Map for Object Detection in Construction Sites

Published:2024 Issue: Volume:12 Page:99989-100004
ISSN:2169-3536
Container-title:IEEE Access
language:
Short-container-title:IEEE Access

Author:

Yang Jaehun¹^ORCID,Lee Eunju²^ORCID,Kwon Junehyoung³,Lee Dongmin¹^ORCID,Kim Youngbin²^ORCID,Park Chansik¹^ORCID,Lee Doyeop¹^ORCID

Affiliation:

1. Department of Architectural Engineering, ConTILab, Chung-Ang University, Seoul, South Korea

2. Department of Image Science and Arts, Chung-Ang University, Seoul, South Korea

3. Department of Artificial Intelligence, Chung-Ang University, Seoul, South Korea

Funder

National Research and Development Project for Smart Construction Technology

Korea Agency for Infrastructure Technology Advancement through the Ministry of Land, Infrastructure, and Transport Managed by Korea Expressway Corporation

National Research Foundation of Korea

Korea Government, Ministry of Science and ICT

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Link

http://xplorestaging.ieee.org/ielx8/6287639/10380310/10584490.pdf?arnumber=10584490

Reference59 articles.

1. Computer vision applications in construction safety assurance

2. Computer vision techniques for construction safety and health monitoring

3. SODA: A large-scale open site object detection dataset for deep learning in construction

4. Computer vision applications in construction: Current state, opportunities & challenges

5. Towards automatic visual inspection: A weakly supervised learning method for industrial applicable object detection

同舟云学术

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