Zobrazeno 1 - 10
of 26
pro vyhledávání: '"Zhenzhong Lan"'
Publikováno v:
IEEE Access, Vol 12, Pp 64717-64726 (2024)
Large Language Models (LLMs) excel in interactive chat scenarios due to their advanced conversational abilities. However, their training process invariably exposes them to a diverse range of harmful or toxic content, posing significant challenges in
Externí odkaz:
https://doaj.org/article/895c5b3db9fa4f9b85adf83fef608953
Publikováno v:
IEEE Robotics and Automation Letters. 6:1020-1027
This letter studies the problem of air-to-air visual detection of micro unmanned aerial vehicles (UAVs) by monocular cameras. This problem is important for many applications such as vision-based swarming of UAVs, malicious UAV detection, and see-and-
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9f097f696cfd5f76c38abf0a907a62c4
https://doi.org/10.1109/lra.2021.3056059
https://doi.org/10.1109/lra.2021.3056059
Publikováno v:
SSRN Electronic Journal.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::637b1737e3441b16f249abce509a39f3
https://doi.org/10.2139/ssrn.3987067
https://doi.org/10.2139/ssrn.3987067
Autor:
Yina Patterson, Xinrui Zhang, Yiming Cui, Qipeng Zhao, Yanting Li, He Zhou, Liang Xu, Cong Yu, Hai Hu, Bo Shi, Jun Zeng, Yiwen Zhang, Zuoyu Tian, Lu Li, Cong Yue, Weitang Liu, Qianqian Dong, Zhenzhong Lan, Junyi Li, Chenjie Cao, Zhe Zhao, Yechen Xu, Yin Tian, Kai Sun, Kyle Richardson, Xuanwei Zhang, Zhengliang Yang, Weijian Xie, Yudong Li, Shaoweihua Liu, Dian Yu, Rongzhao Wang
Publikováno v:
COLING
The advent of natural language understanding (NLU) benchmarks for English, such as GLUE and SuperGLUE allows new NLU models to be evaluated across a diverse set of tasks. These comprehensive benchmarks have facilitated a broad range of research and a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6d7ada4afc1e3375c67cb37afa4243ad
Publikováno v:
ACS Applied Energy Materials. 1:4130-4139
Endothermic hydrocarbon fuel has many advantages as a cooling medium in hypersonic aircraft; however substantial application has been greatly hindered due to easy coking, uncontrollable gas product...
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e2f0a8e6defdc7b62eb8226f8ae2f767
https://doi.org/10.1021/acsaem.8b00780
https://doi.org/10.1021/acsaem.8b00780
Publikováno v:
Computer Vision – ACCV 2018 ISBN: 9783030208929
ACCV (3)
ACCV (3)
Analyzing videos of human actions involves understanding the temporal relationships among video frames. State-of-the-art action recognition approaches rely on traditional optical flow estimation methods to pre-compute motion information for CNNs. Suc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d7dfd2847c531007c50190ef61f1a1ce
https://doi.org/10.1007/978-3-030-20893-6_23
https://doi.org/10.1007/978-3-030-20893-6_23
Autor:
Zhongwen Xu, Zhenzhong Lan, Xiaojun Chang, Zexi Mao, Alexander G. Hauptmann, Deyu Meng, Yi Yang, Zhigang Ma, Shoou-I Yu, Ming Lin, Shicheng Xu, Chuang Gan, Lu Jiang, Xuanchong Li, Xingzhong Du, Huan Li
Publikováno v:
ITE Transactions on Media Technology and Applications. 4:227-238
The large number of user-generated videos uploaded on to the Internet everyday has led to many commercial video search engines, which mainly rely on text metadata for search. However, metadata is often lacking for user-generated videos, thus these vi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b5e26d827fbb439f40c9aed109be1c52
https://doi.org/10.3169/mta.4.227
https://doi.org/10.3169/mta.4.227
Publikováno v:
Energy. 192:116540
Endothermic hydrocarbon fuel of active thermal protection has great potential in cooling system. The bottlenecks for the practical application are the unsatisfied heat sink and severe coking issue. Here, NiO nanoparticle/nanosheet hybrid thin layers
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e30acb5d267d507cfb3d7f37e7146a7b
https://doi.org/10.1016/j.energy.2019.116540
https://doi.org/10.1016/j.energy.2019.116540
Publikováno v:
CVPR Workshops
We investigate the problem of representing an entire video using CNN features for human action recognition. End-to-end learning of CNN/RNNs is currently not possible for whole videos due to GPU memory limitations and so a common practice is to use sa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b9955d893ddcce8efcde173276b2320c
https://doi.org/10.1109/cvprw.2017.161
https://doi.org/10.1109/cvprw.2017.161
Autor:
Alexander G. Hauptmann, Wei Tong, Zhigang Ma, Shoou-I Yu, Ehsan Younessian, Zhenzhong Lan, Yi Yang, Lu Jiang, Waito Sze
Publikováno v:
Machine Vision and Applications. 25:5-15
Detecting multimedia events in web videos is an emerging hot research area in the fields of multimedia and computer vision. In this paper, we introduce the core methods and technologies of the framework we developed recently for our Event Labeling th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::808970430e293ef9f7039a2a99bbfe6b
https://doi.org/10.1007/s00138-013-0529-6
https://doi.org/10.1007/s00138-013-0529-6