ProposalContrast: Unsupervised Pre-training for LiDAR-Based 3D Object Detection

doi:10.1007/978-3-031-19842-7_2

Residential College	false
Status	已發表Published
	ProposalContrast: Unsupervised Pre-training for LiDAR-Based 3D Object Detection
	Junbo, Yin 1; Junbo, Yin 2; Liangjun, Zhang 2,3; Jin, Fang 2,3,4; Dingfu, Zhou 3; Cheng-Zhong, Xu 4; Jianbing, Shen 4; Wenguan, Wang 5
	2022-10
Conference Name	17th European Conference on Computer Vision (ECCV)
Source Publication	Computer Vision – ECCV 2022
Conference Date	2022-10-23
Conference Place	Tel Aviv, Isreal
Country	Isreal
Keyword	3d Object Detection Unsupervised Point Cloud Pre-training
DOI	10.1007/978-3-031-19842-7_2
URL	View the original
Funding Project	Research on Key Technologies and Platforms for Collaborative Intelligence Driven Auto-driving Cars
Language	英語English
WOS Subject	Computer Science, Artificial Intelligence, Imaging Science & Photographic Technology
WOS ID	WOS:000904430800002
Scopus ID	2-s2.0-85142672848
Fulltext Access	View Full-Text via DOI View Full-Text via Web of Science
Citation statistics
Document Type	Conference paper
Collection	University of Macau
Corresponding Author	Jianbing, Shen
Affiliation	1.Beijing Institute of Technology, Beijing, China 2.Baidu Research, Beijing, China 3.National Engineering Laboratory of Deep Learning Technology and Application, Beijing, China 4.State Key Laboratory of IOTSC, CIS, University of Macau, Macau, China 5.University of Technology Sydney
Corresponding Author Affilication	University of Macau
Recommended Citation GB/T 7714	Junbo, Yin,Junbo, Yin,Liangjun, Zhang,et al. ProposalContrast: Unsupervised Pre-training for LiDAR-Based 3D Object Detection[C], 2022.
APA	Junbo, Yin., Junbo, Yin., Liangjun, Zhang., Jin, Fang., Dingfu, Zhou., Cheng-Zhong, Xu., Jianbing, Shen., & Wenguan, Wang (2022). ProposalContrast: Unsupervised Pre-training for LiDAR-Based 3D Object Detection. Computer Vision – ECCV 2022.

Files in This Item:
There are no files associated with this item.

If you have any objections to this item, please fill out the form below and the administrator will contact you as soon as possible.
Content:
Email：	*
Affiliation No.
Verification Code:	Refresh

Any comments and suggestions are welcomed.
Title:	*
Content:
Email：	*
Verification Code:	Refresh