Zobrazeno 1 - 10 of 184 pro vyhledávání: '"JIALIE SHEN"'
1
Akademický článek
Latent label mining for group activity recognition in basketball videos
Autor: Lifang Wu, Zeyu Li, Ye Xiang, Meng Jian, Jialie Shen
Publikováno v: IET Image Processing, Vol 15, Iss 14, Pp 3487-3497 (2021)
Abstract Motion information has been widely exploited for group activity recognition in sports video. However, in order to model and extract the various motion information between the adjacent frames, existing algorithms only use the coarse video‐l
Externí odkaz: https://doaj.org/article/631c0cbd2e244026b895fee7983080bd
Zobrazit plný text záznamu
2
Efficient Query-based Black-box Attack against Cross-modal Hashing Retrieval
Autor: Lei Zhu, Tianshi Wang, Jingjing Li, Zheng Zhang, Jialie Shen, Xinhua Wang
Publikováno v: ACM Transactions on Information Systems. 41:1-25
Deep cross-modal hashing retrieval models inherit the vulnerability of deep neural networks. They are vulnerable to adversarial attacks, especially for the form of subtle perturbations to the inputs. Although many adversarial attack methods have been
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::84f5b5ab5d8b5b4a70075e4e3c84704e
https://doi.org/10.1145/3559758
Zobrazit plný text záznamu
5
Mixture Distribution Graph Network for Few Shot Learning
Autor: Qian Wang, Jie Lei, Yuxuan Shi, Lei Wu, Ping Li, Hefei Ling, Jialie Shen, Baiyan Zhang
Publikováno v: IEEE Transactions on Cognitive and Developmental Systems. 14:892-901
Few-shot learning aims at heuristically resolving new tasks with limited labeled data; most of the existing approaches are affected by knowledge learned from similar experiences. However, inter-class barriers and new samples insufficiency limit the t
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::d057af144309b4b2a8ee567395fb9d0d
https://doi.org/10.1109/tcds.2021.3075280
Zobrazit plný text záznamu
7
Generative Metric Learning for Adversarially Robust Open-world Person Re-Identification
Autor: Deyin Liu, Lin (Yuanbo) Wu, Richang Hong, Zongyuan Ge, Jialie Shen, Farid Boussaid, Mohammed Bennamoun
The vulnerability of re-identification (re-ID) models under adversarial attacks is of significant concern as criminals may use adversarial perturbations to evade surveillance systems. Unlike a closed-world re-ID setting (i.e., a fixed number of train
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2e859bfbd13d11041cf903adbac08f06
https://cronfa.swan.ac.uk/Record/cronfa63558
Zobrazit plný text záznamu
8
Inferring Emotion from Large-scale Internet Voice Data: A Semi-supervised Curriculum Augmentation based Deep Learning Approach
Autor: Suping Zhou, Jia Jia, Zhiyong Wu, Zhihan Yang, Yanfeng Wang, Wei Chen, Fanbo Meng, Shuo Huang, Jialie Shen, Xiaochuan Wang
Publikováno v: Proceedings of the AAAI Conference on Artificial Intelligence. 35:6039-6047
Effective emotion inference from user queries helps to give a more personified response for Voice Dialogue Applications(VDAs). The tremendous amounts of VDA users bring in diverse emotion expressions. How to achieve a high emotion inferring performan
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::0f6683539589a9576ab60ebeb3c3dc33
https://doi.org/10.1609/aaai.v35i7.16753
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje