Zobrazeno 1 - 10
of 1 915
pro vyhledávání: '"Ma Zhiyuan"'
Autor:
Wang Ting, Cui Shenao, Ren Xiaoyu, Zhang Weishen, Yang Xuechao, Gong Shangwei, Yang Deqiang, Li Bangxiang, Zhang Wengang, Su Tian, Mei Xuefeng, Dong Xiaoming, Duan Liancheng, Ma Zhiyuan, Cao Xueyun, Yu Xiyao
Publikováno v:
Reviews on Advanced Materials Science, Vol 63, Iss 1, Pp pp. 1-16 (2024)
Externí odkaz:
https://doaj.org/article/d995906f58be42acbeeb0f4d717e167b
Autor:
Duan Yiwang, Ma Zhiyuan
Publikováno v:
SHS Web of Conferences, Vol 190, p 03013 (2024)
In the network environment, cross-border consumer contracts are mainly carried out under the operation of network service providers, and this paper analyses the connecting points of legal application from the payment architecture of network platforms
Externí odkaz:
https://doaj.org/article/379ee08f9f0e4800b614add9b7996cdb
With the flourishing of social media platforms, vision-language pre-training (VLP) recently has received great attention and many remarkable progresses have been achieved. The success of VLP largely benefits from the information complementation and e
Externí odkaz:
http://arxiv.org/abs/2410.12595
Autor:
Wei, Jiabao, Ma, Zhiyuan
Virtual Try-ON (VTON) aims to synthesis specific person images dressed in given garments, which recently receives numerous attention in online shopping scenarios. Currently, the core challenges of the VTON task mainly lie in the fine-grained semantic
Externí odkaz:
http://arxiv.org/abs/2410.12501
Autor:
Ma, Zhiyuan, Zhang, Yuzhu, Jia, Guoli, Zhao, Liangliang, Ma, Yichao, Ma, Mingjie, Liu, Gaofeng, Zhang, Kaiyan, Li, Jianjun, Zhou, Bowen
As one of the most popular and sought-after generative models in the recent years, diffusion models have sparked the interests of many researchers and steadily shown excellent advantage in various generative tasks such as image synthesis, video gener
Externí odkaz:
http://arxiv.org/abs/2410.11795
Self-Consistency, a widely-used decoding strategy, significantly boosts the reasoning capabilities of Large Language Models (LLMs). However, it depends on the plurality voting rule, which focuses on the most frequent answer while overlooking all othe
Externí odkaz:
http://arxiv.org/abs/2410.10857
Recently, stable diffusion (SD) models have typically flourished in the field of image synthesis and personalized editing, with a range of photorealistic and unprecedented images being successfully generated. As a result, widespread interest has been
Externí odkaz:
http://arxiv.org/abs/2407.13188
Recent vision-language pre-training models have exhibited remarkable generalization ability in zero-shot recognition tasks. Previous open-vocabulary 3D scene understanding methods mostly focus on training 3D models using either image or text supervis
Externí odkaz:
http://arxiv.org/abs/2407.09781
By leveraging the text-to-image diffusion priors, score distillation can synthesize 3D contents without paired text-3D training data. Instead of spending hours of online optimization per text prompt, recent studies have been focused on learning a tex
Externí odkaz:
http://arxiv.org/abs/2407.02040
The most advanced diffusion models have recently adopted increasingly deep stacked networks (e.g., U-Net or Transformer) to promote the generative emergence capabilities of vision generation models similar to large language models (LLMs). However, pr
Externí odkaz:
http://arxiv.org/abs/2406.13215