CORE
发表于 2025-3-28 16:30:51
Person Re-identification Using Multi-branch Cooperative Networkns and unconstrained poses, we propose a multi-branch cooperative network for person Re-ID. First, attention branch and multi-scale branch are designed respectively. In the attention branch, we design shade module, random erasing module and stepped module, and guide each module to learn discriminati
宽宏大量
发表于 2025-3-28 19:13:39
Cross-Domain Object Detection Through Image-Category Features Joint Alignmenten does not work as well as expected due to the domain shift problem. In this paper, a domain adaptive model based on image and category features is proposed to solve the cross-domain object detection task. The proposed model for domain adaption is based on the one-stage object detection model Retin
高谈阔论
发表于 2025-3-29 01:26:18
http://reply.papertrans.cn/47/4615/461494/461494_43.png
追踪
发表于 2025-3-29 06:04:38
Communications in Computer and Information Sciencehttp://image.papertrans.cn/i/image/461494.jpg
贞洁
发表于 2025-3-29 10:56:33
https://doi.org/10.1007/978-981-19-5096-4artificial intelligence; color image processing; color images; computer networks; computer systems; compu
Pigeon
发表于 2025-3-29 13:12:01
978-981-19-5095-7The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapor
Psychogenic
发表于 2025-3-29 16:00:21
http://reply.papertrans.cn/47/4615/461494/461494_47.png
生来
发表于 2025-3-29 19:53:26
http://reply.papertrans.cn/47/4615/461494/461494_48.png
alleviate
发表于 2025-3-30 02:39:55
http://reply.papertrans.cn/47/4615/461494/461494_49.png
Maximizer
发表于 2025-3-30 06:26:51
Integration of Depth Normal Consistency and Depth Map Refinement for MVS Reconstructionsted and compared to traditional reconstruction approaches and MVS networks based on deep learning. The experimental results show that the proposed MVS reconstruction network was produced the better results in completeness and increased the quality of MVS reconstruction.