Zobrazeno 1 - 10
of 973
pro vyhledávání: '"CHEN Zhibo"'
Publikováno v:
IEEE Access, Vol 11, Pp 31304-31322 (2023)
Carbon storage capacity can be estimated to establish evaluation standards and statistics for carbon neutrality. Existing estimation methods including machine learning system have weakness modeling ability, and they are unable to deal with the comple
Externí odkaz:
https://doaj.org/article/52ec382aa95d47c69bfd49e798a216c2
Publikováno v:
Kongzhi Yu Xinxi Jishu, Iss 1, Pp 19-25 (2022)
Permanent magnet motors restart at high speeds is an essential and important function in applications in many key fields. Due to the unknown initial position of rotor and the observation error in this condition, improper control may cause current inr
Externí odkaz:
https://doaj.org/article/2846919612f6489993aa9f7bd290a37d
Text-driven Image to Video Generation (TI2V) aims to generate controllable video given the first frame and corresponding textual description. The primary challenges of this task lie in two parts: (i) how to identify the target objects and ensure the
Externí odkaz:
http://arxiv.org/abs/2412.10275
Publikováno v:
IEEE Transactions on Broadcasting, vol. 67, no. 4, pp. 837-850, Dec. 2021
In multimedia broadcasting, no-reference image quality assessment (NR-IQA) is used to indicate the user-perceived quality of experience (QoE) and to support intelligent data transmission while optimizing user experience. This paper proposes an improv
Externí odkaz:
http://arxiv.org/abs/2412.07079
Autor:
Gao, Yixin, Li, Xin, Pan, Xiaohan, Feng, Runsen, Guo, Zongyu, Lu, Yiting, Ren, Yulin, Chen, Zhibo
We present UniMIC, a universal multi-modality image compression framework, intending to unify the rate-distortion-perception (RDP) optimization for multiple image codecs simultaneously through excavating cross-modality generative priors. Unlike most
Externí odkaz:
http://arxiv.org/abs/2412.04912
We present the first loss agent, dubbed LossAgent, for low-level image processing tasks, e.g., image super-resolution and restoration, intending to achieve any customized optimization objectives of low-level image processing in different practical ap
Externí odkaz:
http://arxiv.org/abs/2412.04090
Autor:
Chen, Zhennan, Li, Yajie, Wang, Haofan, Chen, Zhibo, Jiang, Zhengkai, Li, Jun, Wang, Qian, Yang, Jian, Tai, Ying
Regional prompting, or compositional generation, which enables fine-grained spatial control, has gained increasing attention for its practicality in real-world applications. However, previous methods either introduce additional trainable modules, thu
Externí odkaz:
http://arxiv.org/abs/2411.06558
Recently, AI-generated content (AIGC) has gained significant traction due to its powerful creation capability. However, the storage and transmission of large amounts of high-quality AIGC images inevitably pose new challenges for recent file formats.
Externí odkaz:
http://arxiv.org/abs/2410.09834
Publikováno v:
NeurIPS 2024
Significant progress has been made in text-to-video generation through the use of powerful generative models and large-scale internet data. However, substantial challenges remain in precisely controlling individual concepts within the generated video
Externí odkaz:
http://arxiv.org/abs/2409.00558
We present MambaCSR, a simple but effective framework based on Mamba for the challenging compressed image super-resolution (CSR) task. Particularly, the scanning strategies of Mamba are crucial for effective contextual knowledge modeling in the resto
Externí odkaz:
http://arxiv.org/abs/2408.11758