Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Bayram Bayramli"'
Publikováno v:
Multimedia Tools and Applications. 82:17827-17852
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0a83c627d1b20e0ef4eb72e2678cd4f4
https://doi.org/10.1007/s11042-022-13897-7
https://doi.org/10.1007/s11042-022-13897-7
Publikováno v:
Image and Vision Computing. 113:104261
Learning depth from a single image is a challenging task in computer vision. Many recent works on monocular depth estimation explore increasingly large convolutional neural networks to learn monocular cues implicitly. Such methods may fail to general
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5b66b2274379a816b882c662686486c3
https://doi.org/10.1016/j.imavis.2021.104261
https://doi.org/10.1016/j.imavis.2021.104261
Publikováno v:
Neural Information Processing ISBN: 9783030367077
ICONIP (1)
ICONIP (1)
There are many factors affecting visual face recognition, such as low resolution images, aging, illumination and pose variance, etc. One of the most important problem is low resolution face images which can result in bad performance on face recogniti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::24da4e4a43a792eaa28968924b59ad89
https://doi.org/10.1007/978-3-030-36708-4_1
https://doi.org/10.1007/978-3-030-36708-4_1
Publikováno v:
Communications in Computer and Information Science ISBN: 9783030368012
ICONIP (5)
ICONIP (5)
Most existing person re-identification (re-id) methods generally require a large amount of, difficult to collect, identity-labeled data to act as discriminative guideline for representation learning. To overcome this problem, we propose an unsupervis
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::368fde64073545a184e69618bcb29091
https://doi.org/10.1007/978-3-030-36802-9_81
https://doi.org/10.1007/978-3-030-36802-9_81