Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Woobin Im"'
Publikováno v:
Pattern Recognition Letters. 141:8-15
We propose a combined center dispersion loss function to reduce the intra-class variations and inter-class similarities of facial expression datasets and achieve high accuracy in facial expression recognition. Because of the lack of data, we strategi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::edc6e8a4712d17e10852d28887d848f4
https://doi.org/10.1016/j.patrec.2020.11.002
https://doi.org/10.1016/j.patrec.2020.11.002
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198328
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0e18344b2f332ae30a345218bdff3e17
https://doi.org/10.1007/978-3-031-19833-5_18
https://doi.org/10.1007/978-3-031-19833-5_18
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585853
ECCV (24)
ECCV (24)
Deep unsupervised learning for optical flow has been proposed, where the loss measures image similarity with the warping function parameterized by estimated flow. The census transform, instead of image pixel values, is often used for the image simila
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::afb99b870cf5f0d9944c352836e4761d
https://doi.org/10.1007/978-3-030-58586-0_11
https://doi.org/10.1007/978-3-030-58586-0_11
Publikováno v:
Neurocomputing. 273:611-621
Dynamic scene recognition is a challenging problem in recognizing a collection of static appearances and dynamic patterns in moving scenes. While existing methods focus on reliable capturing of static patterns, few works have explored frame selection
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::44ad8e4cb82a67486c5c3bf77d1dbd60
https://doi.org/10.1016/j.neucom.2017.08.046
https://doi.org/10.1016/j.neucom.2017.08.046
Publikováno v:
The Criticism and Theory Society of Korea. 22:85-113
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::65e730480f5d11e1477b91971da07fd5
https://doi.org/10.19116/theory.2017.22.2.85
https://doi.org/10.19116/theory.2017.22.2.85
Publikováno v:
Computer Vision – ACCV 2018 ISBN: 9783030208721
ACCV (5)
ACCV (5)
In recent years, considerable efforts based on convolutional neural networks have been devoted to age estimation from face images. Among them, classification-based approaches have shown promising results, but there has been little investigation of ag
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::57f46d598f3eba6d7051772185ae74fe
https://doi.org/10.1007/978-3-030-20873-8_16
https://doi.org/10.1007/978-3-030-20873-8_16
Publikováno v:
ICMR
Up to now, only limited research has been conducted on crossmodal retrieval of suitable music for a specified video or vice versa. Moreover, much of the existing research relies on metadata such as keywords, tags, or description that must be individu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ebd0babe3007a6198ac986a65d137137
https://doi.org/10.1145/3206025.3206046
https://doi.org/10.1145/3206025.3206046
Publikováno v:
ICIP
Real-world face recognition using a single sample per person (SSPP) is a challenging task. The problem is exacerbated if the conditions under which the gallery image and the probe set are captured are completely different. To address these issues fro
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ad50011b7e0b98537bc5bd17a2e5185d
http://arxiv.org/abs/1702.04069
http://arxiv.org/abs/1702.04069