Zobrazeno 1 - 10
of 28
pro vyhledávání: '"Junsheng Xiao"'
Publikováno v:
Future Internet, Vol 14, Iss 2, p 50 (2022)
The real world is full of noisy labels that lead neural networks to perform poorly because deep neural networks (DNNs) are prone to overfitting label noise. Noise label training is a challenging problem relating to weakly supervised learning. The mos
Externí odkaz:
https://doaj.org/article/8f9b2ba7a0e1423e8c686a12ed2a11e2
Publikováno v:
Sensors, Vol 20, Iss 18, p 5279 (2020)
Language-based person search retrieves images of a target person using natural language description and is a challenging fine-grained cross-modal retrieval task. A novel hybrid attention network is proposed for the task. The network includes the foll
Externí odkaz:
https://doaj.org/article/b4754f0246e442f58fcbf669d982a800
Publikováno v:
Sensors, Vol 20, Iss 3, p 811 (2020)
As a result of its important role in video surveillance, pedestrian attribute recognition has become an attractive facet of computer vision research. Because of the changes in viewpoints, illumination, resolution and occlusion, the task is very chall
Externí odkaz:
https://doaj.org/article/b1c3f90a0750421ca8dfba672af6e47d
Publikováno v:
Journal of Testing & Evaluation; May2024, Vol. 52 Issue 3, p1-15, 15p
Publikováno v:
IEEE Transactions on Computational Social Systems. 9:336-347
Many mobile apps of social Internet of Things (sIOT) systems can help us record and share daily events, such as health and sport events. In fact, healthy diet recognition is an important and challenging problem in dish health assessment. Via the coll
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f7f5b12256ff77d53c3557d3db42d199
https://doi.org/10.1109/tcss.2021.3102591
https://doi.org/10.1109/tcss.2021.3102591
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems. :1-13
Fully supervised semantic segmentation has performed well in many computer vision tasks. However, it is time-consuming because training a model requires a large number of pixel-level annotated samples. Few-shot segmentation has recently become a popu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::82ddae237981aaa250cf19a85578f451
https://doi.org/10.1109/tnnls.2022.3155486
https://doi.org/10.1109/tnnls.2022.3155486
Publikováno v:
Sustainability; Volume 15; Issue 6; Pages: 5588
Due to the limited and difficult access to sensor energy, energy conservation has always been an important issue in wireless body area network (WBAN). How to make full use of the limited energy of heterogeneous sensors in WBAN to achieve lightweight
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4a2444ee71bb5171ef365e02d63c37bb
Autor:
Zhiyuan Cai, Junsheng Xiao
Publikováno v:
2022 IEEE 6th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC ).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::db8a801cce11195e479f39d099a95515
https://doi.org/10.1109/iaeac54830.2022.9929338
https://doi.org/10.1109/iaeac54830.2022.9929338
Publikováno v:
Wireless Networks. 29:1507-1521
The Internet of Medical Things (IoMT), with advances in wireless technologies, has boosted traditional healthcare into smart healthcare. Computer-aided diagnosis technology based on IoMT is thriving with the help of deep learning. However, fully supe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8b0b4c5fa5efcc8b32bf6c0b7b7c0203
https://doi.org/10.1007/s11276-021-02713-z
https://doi.org/10.1007/s11276-021-02713-z
Publikováno v:
Computing. 105:717-739
The incidence of skin cancer, which has high mortality, is growing rapidly worldwide. Early detection of skin lesions is crucial for timely diagnosis and treatment to improve the patient survival rate. Computer vision technology based on deep convolu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5b3157ff9f4d1d7a3719bfe2b9e5c470
https://doi.org/10.1007/s00607-021-00907-z
https://doi.org/10.1007/s00607-021-00907-z