Zobrazeno 1 - 10
of 2 455
pro vyhledávání: '"Zhang Jiaming"'
Publikováno v:
Zhongguo quanke yixue, Vol 28, Iss 03, Pp 330-334 (2025)
Background The 6-minute walk test (6MWT) is extensively used to assess the exercise capacity of obese populations and offers a reference for devising intervention measures. While reference equations for the 6MWT distance for various populations have
Externí odkaz:
https://doaj.org/article/698777fc89544c129b8fd97b5cd669aa
Publikováno v:
Journal of Orthopaedic Surgery and Research, Vol 18, Iss 1, Pp 1-8 (2023)
Abstract Objective This study aimed to evaluate the feasibility of the modified thoracolumbar injury classification and severity score system in guiding clinical treatment. Methods A retrospective study was conducted on a cohort of 120 patients with
Externí odkaz:
https://doaj.org/article/ce99829a76584f3480ee63bf4f9d0ce4
Backdoor attacks covertly implant triggers into deep neural networks (DNNs) by poisoning a small portion of the training data with pre-designed backdoor triggers. This vulnerability is exacerbated in the era of large models, where extensive (pre-)tra
Externí odkaz:
http://arxiv.org/abs/2410.19427
Autor:
Liu, Yihao, Zhang, Jiaming, Ai, Letian, Tian, Jing, Sefati, Shahriar, Liu, Huan, Martin-Gomez, Alejandro, Kheradmand, Amir, Armand, Mehran
Transcranial magnetic stimulation (TMS) is a noninvasive medical procedure that can modulate brain activity, and it is widely used in neuroscience and neurology research. Compared to manual operators, robots may improve the outcome of TMS due to thei
Externí odkaz:
http://arxiv.org/abs/2410.15243
Pre-trained vision-language models (VLMs), such as CLIP, have exhibited remarkable performance across various downstream tasks by aligning text and images in a unified embedding space. However, due to the imbalanced distribution of pre-trained datase
Externí odkaz:
http://arxiv.org/abs/2410.09365
Autor:
Zhang, Jiaming, Ye, Junhong, Ma, Xingjun, Li, Yige, Yang, Yunfan, Sang, Jitao, Yeung, Dit-Yan
Due to their multimodal capabilities, Vision-Language Models (VLMs) have found numerous impactful applications in real-world scenarios. However, recent studies have revealed that VLMs are vulnerable to image-based adversarial attacks, particularly ta
Externí odkaz:
http://arxiv.org/abs/2410.05346
Autor:
Jiang, Xin, Zheng, Junwei, Liu, Ruiping, Li, Jiahang, Zhang, Jiaming, Matthiesen, Sven, Stiefelhagen, Rainer
As Vision-Language Models (VLMs) advance, human-centered Assistive Technologies (ATs) for helping People with Visual Impairments (PVIs) are evolving into generalists, capable of performing multiple tasks simultaneously. However, benchmarking VLMs for
Externí odkaz:
http://arxiv.org/abs/2409.14215
In the field of autonomous driving, Bird's-Eye-View (BEV) perception has attracted increasing attention in the community since it provides more comprehensive information compared with pinhole front-view images and panoramas. Traditional BEV methods,
Externí odkaz:
http://arxiv.org/abs/2409.13912
Autor:
Zhang Jiaming, Ren Zongxiao, Zhang Guiyi, Peng Zhenhua, Chen Minjing, Wang Liang, Lou Erbiao, Meng Xinggang
Publikováno v:
Frontiers in Earth Science, Vol 10 (2022)
Often with abundant of natural fracture, Carbonate reservoirs are characterized with the stress sensitive and dual media. Mostly, its flow model solved by numerical method. In this paper, the semi-analytical solution for this problem is presented: fi
Externí odkaz:
https://doaj.org/article/8809392180834c588073954db9996c83
Autor:
Chen, Chaochao, Zhang, Jiaming, Zhang, Yizhao, Zhang, Li, Lyu, Lingjuan, Li, Yuyuan, Gong, Biao, Yan, Chenggang
With increasing privacy concerns in artificial intelligence, regulations have mandated the right to be forgotten, granting individuals the right to withdraw their data from models. Machine unlearning has emerged as a potential solution to enable sele
Externí odkaz:
http://arxiv.org/abs/2408.14393