Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Yuan, Hangjie"'
Text-to-video diffusion models have made remarkable advancements. Driven by their ability to generate temporally coherent videos, research on zero-shot video editing using these fundamental models has expanded rapidly. To enhance editing quality, str
Externí odkaz:
http://arxiv.org/abs/2409.20500
In the context of proxy modeling for process systems, traditional data-driven deep learning approaches frequently encounter significant challenges, such as substantial training costs induced by large amounts of data, and limited generalization capabi
Externí odkaz:
http://arxiv.org/abs/2407.05232
Efforts to overcome catastrophic forgetting have primarily centered around developing more effective Continual Learning (CL) methods. In contrast, less attention was devoted to analyzing the role of network architecture design (e.g., network depth, w
Externí odkaz:
http://arxiv.org/abs/2404.14829
Autor:
Bian, Ang, Li, Wei, Yuan, Hangjie, Yu, Chengrong, Zhao, Zixiang, Wang, Mang, Lu, Aojun, Feng, Tao
Model generalization ability upon incrementally acquiring dynamically updating knowledge from sequentially arriving tasks is crucial to tackle the sensitivity-stability dilemma in Continual Learning (CL). Weight loss landscape sharpness minimization
Externí odkaz:
http://arxiv.org/abs/2404.00986
Bandwidth constraints during signal acquisition frequently impede real-time detection applications. Hyperspectral data is a notable example, whose vast volume compromises real-time hyperspectral detection. To tackle this hurdle, we introduce a novel
Externí odkaz:
http://arxiv.org/abs/2403.01412
Autor:
Wang, Xiang, Zhang, Shiwei, Yuan, Hangjie, Qing, Zhiwu, Gong, Biao, Zhang, Yingya, Shen, Yujun, Gao, Changxin, Sang, Nong
Diffusion-based text-to-video generation has witnessed impressive progress in the past year yet still falls behind text-to-image generation. One of the key reasons is the limited scale of publicly available data (e.g., 10M video-text pairs in WebVid1
Externí odkaz:
http://arxiv.org/abs/2312.15770
Autor:
Yuan, Hangjie, Zhang, Shiwei, Wang, Xiang, Wei, Yujie, Feng, Tao, Pan, Yining, Zhang, Yingya, Liu, Ziwei, Albanie, Samuel, Ni, Dong
Diffusion models have emerged as the de facto paradigm for video generation. However, their reliance on web-scale data of varied quality often yields results that are visually unappealing and misaligned with the textual prompts. To tackle this proble
Externí odkaz:
http://arxiv.org/abs/2312.12490
Autor:
Wei, Yujie, Zhang, Shiwei, Qing, Zhiwu, Yuan, Hangjie, Liu, Zhiheng, Liu, Yu, Zhang, Yingya, Zhou, Jingren, Shan, Hongming
Customized generation using diffusion models has made impressive progress in image generation, but remains unsatisfactory in the challenging video generation task, as it requires the controllability of both subjects and motions. To that end, we prese
Externí odkaz:
http://arxiv.org/abs/2312.04433
Autor:
Zhang, Shiwei, Wang, Jiayu, Zhang, Yingya, Zhao, Kang, Yuan, Hangjie, Qin, Zhiwu, Wang, Xiang, Zhao, Deli, Zhou, Jingren
Video synthesis has recently made remarkable strides benefiting from the rapid development of diffusion models. However, it still encounters challenges in terms of semantic accuracy, clarity and spatio-temporal continuity. They primarily arise from t
Externí odkaz:
http://arxiv.org/abs/2311.04145
In medical image segmentation, domain generalization poses a significant challenge due to domain shifts caused by variations in data acquisition devices and other factors. These shifts are particularly pronounced in the most common scenario, which in
Externí odkaz:
http://arxiv.org/abs/2310.20271