Zobrazeno 1 - 10
of 503
pro vyhledávání: '"Song, Peipei"'
Autor:
Zhou, Sheng, Xiao, Junbin, Yang, Xun, Song, Peipei, Guo, Dan, Yao, Angela, Wang, Meng, Chua, Tat-Seng
Existing efforts in text-based video question answering (TextVideoQA) are criticized for their opaque decisionmaking and heavy reliance on scene-text recognition. In this paper, we propose to study Grounded TextVideoQA by forcing models to answer que
Externí odkaz:
http://arxiv.org/abs/2409.14319
Existing eye fixation prediction methods perform the mapping from input images to the corresponding dense fixation maps generated from raw fixation points. However, due to the stochastic nature of human fixation, the generated dense fixation maps may
Externí odkaz:
http://arxiv.org/abs/2403.14821
Autor:
Song, Peipei, Li, Wenyu, Zhong, Peiyan, Zhang, Jing, Konuisz, Piotr, Duan, Feng, Barnes, Nick
Publikováno v:
In Neurocomputing 7 July 2024 589
Publikováno v:
In Digital Signal Processing June 2024 149
Publikováno v:
In Journal of Cleaner Production 20 April 2024 451
Publikováno v:
In Journal of Environmental Chemical Engineering April 2024 12(2)
Publikováno v:
In Journal of Environmental Chemical Engineering April 2024 12(2)
Autor:
Ren, Zixuan, Mu, Linlin, Wang, Lijin, Xia, Lingling, Song, Peipei, Wang, Yan, Li, Junda, Duan, Fan, Li, Haonan, Tang, Huajun, Wang, Wenjuan, Zhu, Lin, Zhang, Lei, Song, Xun, Wang, Yujing, Zhao, Wei, Zhu, Yuqiong, Wang, Ze, Shao, Wenyi, Zhang, Xiaochu, Jiao, Dongliang
Publikováno v:
In Journal of Substance Use and Addiction Treatment January 2024 156
Publikováno v:
Zhongguo linchuang yanjiu, Vol 36, Iss 6, Pp 832-836 (2023)
Osteopontin (OPN) is a secreted phosphosylated protein, which is widely found in various tissues and body fluids. OPN involved in various physiological and pathological processes such as bone growth, wound healing and cell adhesion and migration. The
Externí odkaz:
https://doaj.org/article/080387740e23408098b6fff09b231b8b
Unsupervised image captioning with no annotations is an emerging challenge in computer vision, where the existing arts usually adopt GAN (Generative Adversarial Networks) models. In this paper, we propose a novel memory-based network rather than GAN,
Externí odkaz:
http://arxiv.org/abs/2006.13611