Zobrazeno 1 - 10
of 60
pro vyhledávání: '"Yin, Chengxiang"'
Visual Question Answering (VQA) has emerged as one of the most challenging tasks in artificial intelligence due to its multi-modal nature. However, most existing VQA methods are incapable of handling Knowledge-based Visual Question Answering (KB-VQA)
Externí odkaz:
http://arxiv.org/abs/2312.12723
Video Question Answering (VideoQA) is a very attractive and challenging research direction aiming to understand complex semantics of heterogeneous data from two domains, i.e., the spatio-temporal video content and the word sequence in question. Altho
Externí odkaz:
http://arxiv.org/abs/2312.12721
Autor:
Fu, Xiaohui1,2 (AUTHOR) 202017732@mail.sdu.edu.cn, Yin, Chengxiang1 (AUTHOR) 202317788@mail.sdu.edu.cn, Li, Jin1 (AUTHOR) zhang_jiang@sdu.edu.cn, Zhang, Jiang1 (AUTHOR) sychi@mail.sdu.edu.cn, Chi, Siyue1 (AUTHOR) merchenj@sdu.edu.cn, Chen, Jian1 (AUTHOR) libralibo@sdu.edu.cn, Li, Bo1 (AUTHOR)
Publikováno v:
Remote Sensing. Nov2024, Vol. 16 Issue 21, p4078. 14p.
Autor:
Li, Jin1 (AUTHOR) li_jin@mail.sdu.edu.cn, Yin, Chengxiang1 (AUTHOR) yincx@mail.sdu.edu.cn, Chi, Siyue1 (AUTHOR) sychi@mail.sdu.edu.cn, Mao, Wenshuo1 (AUTHOR) fuxh@sdu.edu.cn, Fu, Xiaohui1,2 (AUTHOR) zhang_jiang@sdu.edu.cn, Zhang, Jiang1 (AUTHOR)
Publikováno v:
Remote Sensing. Nov2024, Vol. 16 Issue 21, p3976. 14p.
Humans have a remarkable ability to quickly and effectively learn new concepts in a continuous manner without forgetting old knowledge. Though deep learning has made tremendous successes on various computer vision tasks, it faces challenges for achie
Externí odkaz:
http://arxiv.org/abs/2207.12303
Publikováno v:
ACM Transactions on Intelligent Systems and Technology (2023)
Deep generative models have made great progress in synthesizing images with arbitrary human poses and transferring poses of one person to others. Though many different methods have been proposed to generate images with high visual fidelity, the main
Externí odkaz:
http://arxiv.org/abs/2107.10984
Meta-learning enables a model to learn from very limited data to undertake a new task. In this paper, we study the general meta-learning with adversarial samples. We present a meta-learning algorithm, ADML (ADversarial Meta-Learner), which leverages
Externí odkaz:
http://arxiv.org/abs/1806.03316
Autor:
Fu, Xiaohui, Yin, Chengxiang, Jolliff, Bradley L., Zhang, Jiang, Chen, Jian, Ling, Zongcheng, Zhang, Feng, Liu, Yang, Zou, Yongliao
Publikováno v:
In Icarus December 2022 388
Publikováno v:
In Icarus 15 January 2022 372
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.