Zobrazeno 1 - 10
of 723
pro vyhledávání: '"Wang Chengjie"'
Publikováno v:
E3S Web of Conferences, Vol 561, p 02004 (2024)
In the process of building materials production, the use of cement raw meal grinding aid technology, infrared high-radiation energy-saving coating for glass melting furnaces, and new ceramic integrated powder making technology can effectively reduce
Externí odkaz:
https://doaj.org/article/62bf256ca2994e4f902d01b3f02a2d79
Publikováno v:
E3S Web of Conferences, Vol 561, p 02002 (2024)
In the process of steel production, the use of high temperature and high pressure smelting technology, continuous casting and rolling technology, waste heat recovery technology, can effectively reduce energy consumption and reduce carbon emissions. A
Externí odkaz:
https://doaj.org/article/fb0df10056cd4f53bf64fa6d15bc1137
Publikováno v:
Kongzhi Yu Xinxi Jishu, Iss 1, Pp 59-63 (2022)
CANopen fieldbus is commonly used in wind power field, which current communication cycle is 10 ms and data volume is 96 bytes. Slow running speed and small amount of data transmitted make it cannot meet the growing demand for real-time communication
Externí odkaz:
https://doaj.org/article/149b948be3384be494b088c8b6924d10
Autor:
Wang, Zhiyao, Chen, Xu, Xu, Chengming, Zhu, Junwei, Hu, Xiaobin, Zhang, Jiangning, Wang, Chengjie, Liu, Yuqi, Zhou, Yiyi, Ji, Rongrong
Face Restoration (FR) is a crucial area within image and video processing, focusing on reconstructing high-quality portraits from degraded inputs. Despite advancements in image FR, video FR remains relatively under-explored, primarily due to challeng
Externí odkaz:
http://arxiv.org/abs/2501.01235
Although mainstream unsupervised anomaly detection (AD) (including image-level classification and pixel-level segmentation)algorithms perform well in academic datasets, their performance is limited in practical application due to the ideal experiment
Externí odkaz:
http://arxiv.org/abs/2412.20870
Autor:
Zhang, Jiangning, Hu, Teng, He, Haoyang, Xue, Zhucun, Wang, Yabiao, Wang, Chengjie, Liu, Yong, Li, Xiangtai, Tao, Dacheng
This work focuses on developing parameter-efficient and lightweight models for dense predictions while trading off parameters, FLOPs, and performance. Our goal is to set up the new frontier of the 5M magnitude lightweight model on various downstream
Externí odkaz:
http://arxiv.org/abs/2412.06674
Autor:
He, Qingdong, Peng, Jinlong, Xu, Pengcheng, Jiang, Boyuan, Hu, Xiaobin, Luo, Donghao, Liu, Yong, Wang, Yabiao, Wang, Chengjie, Li, Xiangtai, Zhang, Jiangning
To enhance the controllability of text-to-image diffusion models, current ControlNet-like models have explored various control signals to dictate image attributes. However, existing methods either handle conditions inefficiently or use a fixed number
Externí odkaz:
http://arxiv.org/abs/2412.03255
Face swapping aims to generate results that combine the identity from the source with attributes from the target. Existing methods primarily focus on image-based face swapping. When processing videos, each frame is handled independently, making it di
Externí odkaz:
http://arxiv.org/abs/2411.18293
Autor:
Ji, Xiaozhong, Hu, Xiaobin, Xu, Zhihong, Zhu, Junwei, Lin, Chuming, He, Qingdong, Zhang, Jiangning, Luo, Donghao, Chen, Yi, Lin, Qin, Lu, Qinglin, Wang, Chengjie
The study of talking face generation mainly explores the intricacies of synchronizing facial movements and crafting visually appealing, temporally-coherent animations. However, due to the limited exploration of global audio perception, current approa
Externí odkaz:
http://arxiv.org/abs/2411.16331
Autor:
He, Haoyang, Zhang, Jiangning, Cai, Yuxuan, Chen, Hongxu, Hu, Xiaobin, Gan, Zhenye, Wang, Yabiao, Wang, Chengjie, Wu, Yunsheng, Xie, Lei
Previous research on lightweight models has primarily focused on CNNs and Transformer-based designs. CNNs, with their local receptive fields, struggle to capture long-range dependencies, while Transformers, despite their global modeling capabilities,
Externí odkaz:
http://arxiv.org/abs/2411.15941