Zobrazeno 1 - 10
of 147
pro vyhledávání: '"Zheng Ziqiang"'
Publikováno v:
Nantong Daxue xuebao. Ziran kexue ban, Vol 21, Iss 2, Pp 1-17 (2022)
Metal-organic frameworks(MOFs) are a new type of porous coordination polymers, which has gained wide attention in the fabrication of electrochemical sensors due to their excellent properties including large specific surface area, adjustable structure
Externí odkaz:
https://doaj.org/article/2da8075333464eb0a991816ade773b41
Images of coral reefs provide invaluable information, which is essentially critical for surveying and monitoring the coral reef ecosystems. Robust and precise identification of coral reef regions within surveying imagery is paramount for assessing co
Externí odkaz:
http://arxiv.org/abs/2410.20436
Autor:
Zhang, Jipeng, Zhang, Jianshu, Li, Yuanzhe, Pi, Renjie, Pan, Rui, Liu, Runtao, Zheng, Ziqiang, Zhang, Tong
Large Language Models (LLMs) demonstrate strong proficiency in generating code for high-resource programming languages (HRPLs) like Python but struggle significantly with low-resource programming languages (LRPLs) such as Racket or D. This performanc
Externí odkaz:
http://arxiv.org/abs/2410.18957
Learning-based underwater image enhancement (UIE) methods have made great progress. However, the lack of large-scale and high-quality paired training samples has become the main bottleneck hindering the development of UIE. The inter-frame information
Externí odkaz:
http://arxiv.org/abs/2404.14542
Autor:
Zheng, Ziqiang, Chen, Yiwei, Zhang, Jipeng, Vu, Tuan-Anh, Zeng, Huimin, Tim, Yue Him Wong, Yeung, Sai-Kit
Large language models (LLMs) have demonstrated a powerful ability to answer various queries as a general-purpose assistant. The continuous multi-modal large language models (MLLM) empower LLMs with the ability to perceive visual signals. The launch o
Externí odkaz:
http://arxiv.org/abs/2401.02147
Large language models (LLMs), such as ChatGPT/GPT-4, have proven to be powerful tools in promoting the user experience as an AI assistant. The continuous works are proposing multi-modal large language models (MLLM), empowering LLMs with the ability t
Externí odkaz:
http://arxiv.org/abs/2310.13596
Autor:
Zheng, Ziqiang1,2,3 (AUTHOR) 12626@whpu.edu.cn, Wang, Zuoqian3 (AUTHOR), Zhang, Xuerui1 (AUTHOR), Zheng, Chaofan1 (AUTHOR), Xu, Bichao4 (AUTHOR), Zhang, Jushuang1 (AUTHOR), Zhang, Chengjun5 (AUTHOR), Bie, Siwei1 (AUTHOR), Peng, Fang1 (AUTHOR), Wu, Yuzhen1 (AUTHOR), Wang, Hongxun1 (AUTHOR), Zhang, Shu3 (AUTHOR), Lv, Liang3 (AUTHOR)
Publikováno v:
BMC Microbiology. 9/28/2024, p1-13. 13p.
The huge domain gap between sketches and photos and the highly abstract sketch representations pose challenges for sketch-based image retrieval (\underline{SBIR}). The zero-shot sketch-based image retrieval (\underline{ZS-SBIR}) is more generic and p
Externí odkaz:
http://arxiv.org/abs/2111.12757
Publikováno v:
In Heliyon 30 August 2024 10(16)
Autor:
Yang, Fan, Chang, Xin, Dang, Chenyu, Zheng, Ziqiang, Sakti, Sakriani, Nakamura, Satoshi, Wu, Yang
We aim to improve the performance of Multiple Object Tracking and Segmentation (MOTS) by refinement. However, it remains challenging for refining MOTS results, which could be attributed to that appearance features are not adapted to target videos and
Externí odkaz:
http://arxiv.org/abs/2007.03200