Zobrazeno 1 - 10
of 55
pro vyhledávání: '"Lihuo He"'
Multi-Window Fusion Spatial-Frequency Joint Self-Attention for Remote-Sensing Image Super-Resolution
Publikováno v:
Remote Sensing, Vol 16, Iss 19, p 3695 (2024)
Remote-sensing images typically feature large dimensions and contain repeated texture patterns. To effectively capture finer details and encode comprehensive information, feature-extraction networks with larger receptive fields are essential for remo
Externí odkaz:
https://doaj.org/article/6b3e1572097b4589a34c1521a3ea703d
Publikováno v:
IEEE Access, Vol 7, Pp 176087-176098 (2019)
Blind image quality assessment (BIQA) is a fundamental yet challenging problem in the image processing system. Existing BIQA models have the following problems: 1) Due to the lack of available quality-label images, most of the methods have poor gener
Externí odkaz:
https://doaj.org/article/cd6ffa66f6fc495cb5082c444705c66e
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems. 34:623-634
A largely ignored fact in spectral super-resolution (SSR) is that the subsistent mapping methods neglect the auxiliary prior of camera spectral sensitivity (CSS) and only pay attention to wider or deeper network framework design while ignoring to exc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::12995638b0459279e73483c5ab69be92
https://doi.org/10.1109/tnnls.2021.3098767
https://doi.org/10.1109/tnnls.2021.3098767
Publikováno v:
IEEE Transactions on Multimedia. 25:1217-1229
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::275b1d0da79631e8cc1c28c849396c62
https://doi.org/10.1109/tmm.2022.3140656
https://doi.org/10.1109/tmm.2022.3140656
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 32:8179-8191
Video-based person re-identification (Re-ID) aims at retrieving the person through the video sequences across non-overlapping cameras. Some characteristics of pedestrians are not consecutive across frames due to the variations of viewpoints, postures
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2cfbdc11b0896b6daef804472ee93374
https://doi.org/10.1109/tcsvt.2021.3076097
https://doi.org/10.1109/tcsvt.2021.3076097
Publikováno v:
IEEE Transactions on Multimedia. :1-13
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0f2d0a747be744b2803c467ec7059558
https://doi.org/10.1109/tmm.2022.3183830
https://doi.org/10.1109/tmm.2022.3183830
Publikováno v:
Neurocomputing. 457:242-253
Benefiting with the rapid development of communication networks, effective video quality assessment (VQA) models which provide guidance for video transmission and compression technologies are highly demanded. This paper proposes a general-purpose ful
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::253fc6be949ea7bcd5adcf301e3f7eea
https://doi.org/10.1016/j.neucom.2021.06.026
https://doi.org/10.1016/j.neucom.2021.06.026
Publikováno v:
Neurocomputing. 430:14-23
With the ever-expanding volume of visual images on the Internet, automatic image aesthetic prediction is becoming more and more important in computer vision field. Considering the image aesthetic assessment is a highly subjective and complex task, so
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d07b08074a643d8d6d43c38dfc6a9eea
https://doi.org/10.1016/j.neucom.2020.10.046
https://doi.org/10.1016/j.neucom.2020.10.046