Zobrazeno 1 - 10
of 549
pro vyhledávání: '"Chen Zijian"'
Publikováno v:
电力工程技术, Vol 43, Iss 2, Pp 163-169 (2024)
Gas gap switch has good application prospects in power systems, due to its quick response and simple structure. However, there is still little research on insulation recovery characteristic. Therefore, the double pulse method is used to study the inf
Externí odkaz:
https://doaj.org/article/433ce0c98d1243758b564d9b80c48498
Publikováno v:
Open Medicine, Vol 19, Iss 1, Pp 7-33 (2024)
Advances in lung cancer research applying machine learning (ML) technology have generated many relevant literature. However, there is absence of bibliometric analysis review that aids a comprehensive understanding of this field and its progress. Pres
Externí odkaz:
https://doaj.org/article/6734fdc49ee8414dbcea66c44c152b23
Autor:
Zhang, Zicheng, Jia, Ziheng, Wu, Haoning, Li, Chunyi, Chen, Zijian, Zhou, Yingjie, Sun, Wei, Liu, Xiaohong, Min, Xiongkuo, Lin, Weisi, Zhai, Guangtao
With the rising interest in research on Large Multi-modal Models (LMMs) for video understanding, many studies have emphasized general video comprehension capabilities, neglecting the systematic exploration into video quality understanding. To address
Externí odkaz:
http://arxiv.org/abs/2409.20063
We propose an image-conditioned diffusion model to estimate high angular resolution diffusion weighted imaging (DWI) from a low angular resolution acquisition. Our model, which we call QID$^2$, takes as input a set of low angular resolution DWI data
Externí odkaz:
http://arxiv.org/abs/2409.02309
Autor:
Chen, Zijian, Varkanitsa, Maria, Ishwar, Prakash, Konrad, Janusz, Betke, Margrit, Kiran, Swathi, Venkataraman, Archana
We propose a lesion-aware graph neural network (LEGNet) to predict language ability from resting-state fMRI (rs-fMRI) connectivity in patients with post-stroke aphasia. Our model integrates three components: an edge-based learning module that encodes
Externí odkaz:
http://arxiv.org/abs/2409.02303
Autor:
Sun, Wei, Zhang, Weixia, Cao, Yuqin, Cao, Linhan, Jia, Jun, Chen, Zijian, Zhang, Zicheng, Min, Xiongkuo, Zhai, Guangtao
UHD images, typically with resolutions equal to or higher than 4K, pose a significant challenge for efficient image quality assessment (IQA) algorithms, as adopting full-resolution images as inputs leads to overwhelming computational complexity and c
Externí odkaz:
http://arxiv.org/abs/2409.00749
Autor:
Cao, Linhan, Sun, Wei, Min, Xiongkuo, Jia, Jun, Zhang, Zicheng, Chen, Zijian, Zhu, Yucheng, Liu, Lizhou, Chen, Qiubo, Chen, Jing, Zhai, Guangtao
Just noticeable distortion (JND), representing the threshold of distortion in an image that is minimally perceptible to the human visual system (HVS), is crucial for image compression algorithms to achieve a trade-off between transmission bit rate an
Externí odkaz:
http://arxiv.org/abs/2408.04273
Autor:
Zhang, Zhichao, Li, Xinyue, Sun, Wei, Jia, Jun, Min, Xiongkuo, Zhang, Zicheng, Li, Chunyi, Chen, Zijian, Wang, Puyi, Ji, Zhongpeng, Sun, Fengyu, Jui, Shangling, Zhai, Guangtao
In recent years, artificial intelligence (AI) driven video generation has garnered significant attention due to advancements in stable diffusion and large language model techniques. Thus, there is a great demand for accurate video quality assessment
Externí odkaz:
http://arxiv.org/abs/2407.21408
Autor:
Chen, Zijian, Sun, Wei, Tian, Yuan, Jia, Jun, Zhang, Zicheng, Wang, Jiarui, Huang, Ru, Min, Xiongkuo, Zhai, Guangtao, Zhang, Wenjun
Assessing action quality is both imperative and challenging due to its significant impact on the quality of AI-generated videos, further complicated by the inherently ambiguous nature of actions within AI-generated video (AIGV). Current action qualit
Externí odkaz:
http://arxiv.org/abs/2406.06087
Autor:
Zhang, Jiyao, Huang, Weiyao, Peng, Bo, Wu, Mingdong, Hu, Fei, Chen, Zijian, Zhao, Bo, Dong, Hao
6D Object Pose Estimation is a crucial yet challenging task in computer vision, suffering from a significant lack of large-scale datasets. This scarcity impedes comprehensive evaluation of model performance, limiting research advancements. Furthermor
Externí odkaz:
http://arxiv.org/abs/2406.04316