Zobrazeno 1 - 10
of 104
pro vyhledávání: '"Yan, Tianyu"'
Salient Object Detection (SOD) aims to identify and segment the most prominent objects in images. Advanced SOD methods often utilize various Convolutional Neural Networks (CNN) or Transformers for deep feature extraction. However, these methods still
Externí odkaz:
http://arxiv.org/abs/2408.04326
Recently, Segment Anything Model (SAM) shows exceptional performance in generating high-quality object masks and achieving zero-shot image segmentation. However, as a versatile vision model, SAM is primarily trained with large-scale natural light ima
Externí odkaz:
http://arxiv.org/abs/2404.15700
As an important pillar of underwater intelligence, Marine Animal Segmentation (MAS) involves segmenting animals within marine environments. Previous methods don't excel in extracting long-range contextual features and overlook the connectivity betwee
Externí odkaz:
http://arxiv.org/abs/2404.04996
In the remote sensing field, Change Detection (CD) aims to identify and localize the changed regions from dual-phase images over the same places. Recently, it has achieved great progress with the advances of deep learning. However, current methods ge
Externí odkaz:
http://arxiv.org/abs/2310.14214
Recently, change detection (CD) of remote sensing images have achieved great progress with the advances of deep learning. However, current methods generally deliver incomplete CD regions and irregular CD boundaries due to the limited representation a
Externí odkaz:
http://arxiv.org/abs/2210.00757
Publikováno v:
In Progress in Nuclear Energy October 2024 175
Publikováno v:
Journal of Isotopes, Vol 37, Iss 3, Pp 17-23 (2024)
To obtain cobalt target activity data after a cycle of irradiation in a pressurized water reactor, the cobalt target dose distribution was measured underwater using alanine dosimeters. The effects of cobalt target structure, water medium, measurement
Externí odkaz:
https://doaj.org/article/f77c8a9f0b70418da7c2762c6a9dd9e8
Unsupervised person re-identification (Re-ID) attracts increasing attention due to its potential to resolve the scalability problem of supervised Re-ID models. Most existing unsupervised methods adopt an iterative clustering mechanism, where the netw
Externí odkaz:
http://arxiv.org/abs/2112.01839
Autor:
Yan, Tianyu1 (AUTHOR) tianyuyan7@163.com, Wang, Yingqian1 (AUTHOR), Wang, Pu1 (AUTHOR) wp421189@nudt.edu.cn
Publikováno v:
Remote Sensing. Aug2024, Vol. 16 Issue 16, p3018. 19p.
Autor:
Liang, Qianwang1 (AUTHOR), Yan, Tianyu1 (AUTHOR), Wang, Nan1 (AUTHOR), Zhu, Zhiying1 (AUTHOR), Ye, Jiongyao1 (AUTHOR) yejy@ecust.edu.cn
Publikováno v:
Symmetry (20738994). Mar2024, Vol. 16 Issue 3, p356. 22p.