Zobrazeno 1 - 10
of 103
pro vyhledávání: '"XiaoChen Lian"'
Publikováno v:
2021 IEEE 9th International Conference on Information, Communication and Networks (ICICN).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::52f6c7dc15e20b56a28f00467c6d3093
https://doi.org/10.1109/icicn52636.2021.9673984
https://doi.org/10.1109/icicn52636.2021.9673984
Publikováno v:
2021 6th International Conference on Communication, Image and Signal Processing (CCISP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a9588421d2a94a5f10c865744bfb7c27
https://doi.org/10.1109/ccisp52774.2021.9639357
https://doi.org/10.1109/ccisp52774.2021.9639357
Publikováno v:
CVPR
High-resolution representations (HR) are essential for dense prediction tasks such as segmentation, detection, and pose estimation. Learning HR representations is typically ignored in previous Neural Architecture Search (NAS) methods that focus on im
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::257cade1e70996f593121cf67c91044a
Autor:
Xiaochen Lian, Xiaojie Jin, Yuyin Zhou, Song Bai, Jieru Mei, Cihang Xie, Alan L. Yuille, Linjie Yang, Qihang Yu, Yingwei Li
Publikováno v:
CVPR
Non-Local (NL) blocks have been widely studied in various vision tasks. However, it has been rarely explored to embed the NL blocks in mobile neural networks, mainly due to the following challenges: 1) NL blocks generally have heavy computation cost
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f40ba967ff4ef8553fa7ac50977e280f
https://doi.org/10.1109/cvpr42600.2020.01031
https://doi.org/10.1109/cvpr42600.2020.01031
Publikováno v:
WACV
In this paper, we address the task of instance-level semantic boundary detection. To this end, we generate a large database consisting of more than 10k images (which is 20 bigger than existing edge detection databases) along with ground truth boundar
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3346a2c47502c04c891695e1fc64af0c
https://doi.org/10.1109/wacv.2017.16
https://doi.org/10.1109/wacv.2017.16
Publikováno v:
Neurocomputing. 76:18-27
In this paper, we propose a novel gender classification framework, which utilizes not only facial features, but also external information, i.e. hair and clothing. Instead of using the whole face, we consider five facial components: forehead, eyes, no
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7edb5103425aad8ec77210042dd6e619
https://doi.org/10.1016/j.neucom.2011.01.028
https://doi.org/10.1016/j.neucom.2011.01.028
Publikováno v:
Neural Computing and Applications. 21:661-669
In this paper, we propose a multi-view gender classification system with a hierarchical framework using facial images as input. The front end of the framework is a classifier, which will properly divides the input images into several groups. To ease
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::97ff79dbea0f4d959a85c8a56bc4893b
https://doi.org/10.1007/s00521-011-0647-x
https://doi.org/10.1007/s00521-011-0647-x
Publikováno v:
BMVC
This paper addresses the problem of semantic part parsing (segmentation) of cars, i.e.assigning every pixel within the car to one of the parts (e.g.body, window, lights, license plates and wheels). We formulate this as a landmark identification probl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3d50f275077a8851a5f465916e097214
http://arxiv.org/abs/1406.2375
http://arxiv.org/abs/1406.2375
Publikováno v:
CVPR
Spectral clustering is an elegant and powerful approach for clustering. However, the underlying eigen-decomposition takes cubic time and quadratic space w.r.t. the data set size. These can be reduced by the Nystrom method which samples only a subset
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b5585154ec914a845446c38d11946ea2
https://doi.org/10.1109/cvpr.2011.5995425
https://doi.org/10.1109/cvpr.2011.5995425
Publikováno v:
CVPR
Dictionary generation is a core technique of the bag-of-visual-words (BOV) models when applied to image categorization. Most of previous approaches generate dictionaries by unsupervised clustering techniques, e.g. k-means. However, the features obtai
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::109f4fd401d7a4202eabfa272a5bedd0
https://doi.org/10.1109/cvpr.2010.5539915
https://doi.org/10.1109/cvpr.2010.5539915