Zobrazeno 1 - 10
of 190
pro vyhledávání: '"Zhao, Shihao"'
While personalized text-to-image generation has enabled the learning of a single concept from multiple images, a more practical yet challenging scenario involves learning multiple concepts within a single image. However, existing works tackling this
Externí odkaz:
http://arxiv.org/abs/2407.07077
Autor:
Zi, Bojia, Zhao, Shihao, Qi, Xianbiao, Wang, Jianan, Shi, Yukai, Chen, Qianyu, Liang, Bin, Wong, Kam-Fai, Zhang, Lei
Recent advancements in video generation have been remarkable, yet many existing methods struggle with issues of consistency and poor text-video alignment. Moreover, the field lacks effective techniques for text-guided video inpainting, a stark contra
Externí odkaz:
http://arxiv.org/abs/2403.12035
Text-to-image generation has made significant advancements with the introduction of text-to-image diffusion models. These models typically consist of a language model that interprets user prompts and a vision model that generates corresponding images
Externí odkaz:
http://arxiv.org/abs/2403.07860
Personalized text-to-image generation using diffusion models has recently emerged and garnered significant interest. This task learns a novel concept (e.g., a unique toy), illustrated in a handful of images, into a generative model that captures fine
Externí odkaz:
http://arxiv.org/abs/2306.00971
Autor:
Zhao, Shihao, Chen, Dongdong, Chen, Yen-Chun, Bao, Jianmin, Hao, Shaozhe, Yuan, Lu, Wong, Kwan-Yee K.
Text-to-Image diffusion models have made tremendous progress over the past two years, enabling the generation of highly realistic images based on open-domain text descriptions. However, despite their success, text descriptions often struggle to adequ
Externí odkaz:
http://arxiv.org/abs/2305.16322
Autor:
Xiang, Shuiying, Shi, Yuechun, Guo, Xingxing, Zhang, Yahui, Wang, Hongji, Zheng, Dianzhuang, Song, Ziwei, Han, Yanan, Gao, Shuang, Zhao, Shihao, Gu, Biling, Wang, Hailing, Zhu, Xiaojun, Hou, Lianping, Chen, Xiangfei, Zheng, Wanhua, Ma, Xiaohua, Hao, Yue
Photonic neuromorphic computing has emerged as a promising avenue toward building a low-latency and energy-efficient non-von-Neuman computing system. Photonic spiking neural network (PSNN) exploits brain-like spatiotemporal processing to realize high
Externí odkaz:
http://arxiv.org/abs/2204.08362
Autor:
Hong, Chen, Xu, Song, Zhao, Shihao, Zhang, Huachuan, Su, Fangxu, Wang, Shuofeng, Ji, Changwei
Publikováno v:
In Fuel 1 November 2024 375
Adversarial training is one effective approach for training robust deep neural networks against adversarial attacks. While being able to bring reliable robustness, adversarial training (AT) methods in general favor high capacity models, i.e., the lar
Externí odkaz:
http://arxiv.org/abs/2108.07969
Publikováno v:
In Energy 15 May 2024 295
Publikováno v:
In Waste Management 15 February 2024 174:263-272