Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Aozhu Chen"'
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031197802
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8e0c02708555a74def89629c5820976e
https://doi.org/10.1007/978-3-031-19781-9_26
https://doi.org/10.1007/978-3-031-19781-9_26
While deep learning based image retrieval is reported to be vulnerable to adversarial attacks, existing works are mainly on image-to-image retrieval with their attacks performed at the front end via query modification. By contrast, we present in this
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9c6ec84dbaa6c3cd8be177005f267e6e
Publikováno v:
ACM Multimedia
This paper describes our bronze-medal solution for the video captioning task of the ACMMM2021 Pre-Training for Video Understanding Challenge. We depart from the Bottom-Up-Top-Down model, with technical improvements on both video content encoding and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::957a20eed898b370e65025023d81b754
https://doi.org/10.1145/3474085.3479217
https://doi.org/10.1145/3474085.3479217
For quantifying progress in Ad-hoc Video Search (AVS), the annual TRECVID AVS task is an important international evaluation. Solutions submitted by the task participants vary in terms of their choices of cross-modal matching models, visual features a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::11da5a150f69d614829a4e43e0cdabe9
http://arxiv.org/abs/2109.01774
http://arxiv.org/abs/2109.01774
Publikováno v:
Pattern Recognition. 95:114-127
Hashing methods have been intensively studied and widely used in image retrieval. Hashing methods aim to learn a group of hash functions to map original data into compact binary codes and simultaneously preserve some notion of similarity in the Hammi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::dfbefba572740915c809117e4778a96e
https://doi.org/10.1016/j.patcog.2019.06.005
https://doi.org/10.1016/j.patcog.2019.06.005
Publikováno v:
Biomedical Signal Processing and Control. 48:69-79
In this paper, we present a method which can generate color medical images based on multi-feature fusion and hierarchical density peak clustering. First, the proposed method extracts multi-feature to gain abundant feature information. Then, select th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::82806dbdc5f56e3afa1fd6dd04782d16
https://doi.org/10.1016/j.bspc.2018.09.013
https://doi.org/10.1016/j.bspc.2018.09.013
Publikováno v:
Proceedings of the 2nd ACM International Conference on Multimedia in Asia.
Cross-lingual image captioning, with its ability to caption an unlabeled image in a target language other than English, is an emerging topic in the multimedia field. In order to save the precious human resource from re-writing reference sentences per
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ef687214cd5cb8afeda2d96c1500656c
https://doi.org/10.1145/3444685.3446322
https://doi.org/10.1145/3444685.3446322
Autor:
Jun Wang, Zhikang Shuai, Yan Li, Gourab Sabui, An Luo, Zhenyu Miao, Xin Yin, Aozhu Chen, Jiang Mengxuan, Z. John Shen
Publikováno v:
2015 IEEE Applied Power Electronics Conference and Exposition (APEC).
This paper introduces a new self-powered solid state circuit breaker (SSCB) concept using a normally-on SiC JFET as the main static switch and a fast-starting isolated DC/DC converter as the protection driver. The new SSCB detects short circuit fault
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::83e187e27a14f24bc209df8e2fb1437b
https://doi.org/10.1109/apec.2015.7104436
https://doi.org/10.1109/apec.2015.7104436
Publikováno v:
Journal of Computer-Aided Design & Computer Graphics. 30:375
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::30e7d79d3bc841333d0a17b19ab3df67
https://doi.org/10.3724/sp.j.1089.2018.16318
https://doi.org/10.3724/sp.j.1089.2018.16318