Zobrazeno 1 - 10
of 15
pro vyhledávání: '"Xinyu Ou"'
Publikováno v:
Multimedia Tools and Applications. 78:28257-28283
We propose a novel Multi-Task Learning Network (MTNET) with four different subtasks for person re-identification mission. At the same time, the attribute recognition mission can be implemented by the same network. We achieve multi-mission by integrat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::592cb10cc60d32df043e4df355f43a81
https://doi.org/10.1007/s11042-019-07921-6
https://doi.org/10.1007/s11042-019-07921-6
Autor:
Su-Jing Wang, Feng Xu, Xiaolan Fu, Xiaohua Huang, Xinyu Ou, Yong-Jin Liu, Bing-Jun Li, Wen-Jing Yan
Publikováno v:
Neurocomputing. 312:251-262
Micro-expression is one of important clues for detecting lies. Its most outstanding characteristics include short duration and low intensity of movement. Therefore, video clips of high spatial-temporal resolution are much more desired than still imag
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::79205fee1bbf4c210aa23dcebdc336a1
https://doi.org/10.1016/j.neucom.2018.05.107
https://doi.org/10.1016/j.neucom.2018.05.107
Publikováno v:
ACM Transactions on Intelligent Systems and Technology. 8:1-25
Adult image and video recognition is an important and challenging problem in the real world. Low-level feature cues do not produce good enough information, especially when the dataset is very large and has various data distributions. This issue raise
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c6a76dd42325c35e8f57ee550f9885be
https://doi.org/10.1145/3057733
https://doi.org/10.1145/3057733
Publikováno v:
Journal of Computer Science and Technology. 32:683-700
Semantic segmentation has recently witnessed rapid progress, but existing methods only focus on identifying objects or instances. In this work, we aim to address the task of semantic understanding of scenes with deep learning. Different from many exi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::16e1515da19d689bcb0c330ef6b27db5
https://doi.org/10.1007/s11390-017-1751-x
https://doi.org/10.1007/s11390-017-1751-x
Publikováno v:
Multimedia Tools and Applications. 76:21281-21302
Content-Based large-scale image retrieval has recently attracted considerable attention because of the explosive increase of online images. Inspired by recent advances in convolutional neural networks, we propose a hierarchical deep semantic method f
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::763da19abecf6b6116f1c5d4cf523705
https://doi.org/10.1007/s11042-016-4057-z
https://doi.org/10.1007/s11042-016-4057-z
Publikováno v:
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society.
Image retargeting has been applied to display images of any size via devices with various resolutions (e.g., cell phone and TV monitors). To fit an image with the target resolution, certain unimportant regions need to be deleted or distorted, and the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::81845fdb200c011187d7b88d49c40195
https://pubmed.ncbi.nlm.nih.gov/29994768
https://pubmed.ncbi.nlm.nih.gov/29994768
Publikováno v:
NDSS
The automatic detection of software vulnerabilities is an important research problem. However, existing solutions to this problem rely on human experts to define features and often miss many vulnerabilities (i.e., incurring high false negative rate).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d7e45ff4384d99b8d53379efe98a64b1
https://doi.org/10.14722/ndss.2018.23158
https://doi.org/10.14722/ndss.2018.23158
Publikováno v:
ACM Multimedia
In this demo, we present a Beauty eMakeup System to automatically recommend the most suitable makeup for a female and synthesis the makeup on her face. Given a before-makeup face, her most suitable makeup is determined automatically. Then, both the b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5ee7427e95967e7d3723955f149aabc4
https://doi.org/10.1145/2964284.2973812
https://doi.org/10.1145/2964284.2973812
Publikováno v:
ICME Workshops
In this paper, we tackle the FINE-GRAINED VISUAL RECOGNITION problem by proposing a deep multi-context framework. We employ deep Convolutional Neural Networks to model features of objects in images. Global context and local context are both taken int
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5cd2aa06cd4c2a5857b930e44ba9bc18
https://doi.org/10.1109/icmew.2016.7574666
https://doi.org/10.1109/icmew.2016.7574666
Publikováno v:
APSIPA
Large scale image search has recently attracted considerable attention due to the explosive increase of online images. It has been shown that convolutional neural network(ConvNet) provides a high-level feature of the visual content of the image. It h
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3206436759280d3de1d4069bbb948bf0
https://doi.org/10.1109/apsipa.2014.7041557
https://doi.org/10.1109/apsipa.2014.7041557