Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Lezi Wang"'
Publikováno v:
Image and Vision Computing. 87:37-46
Face detection and landmark localization have been extensively investigated and are the prerequisite for many face related applications, such as face recognition and 3D face reconstruction. Most existing methods address only one of the two problems.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::46818986c7f97b8366008453cf07470d
https://doi.org/10.1016/j.imavis.2018.09.008
https://doi.org/10.1016/j.imavis.2018.09.008
Autor:
V. S. Subrahmanian, Maksim Bolonkin, Dimitris N. Metaxas, Judee K. Burgoon, Norah E. Dunbar, Chongyang Bai, Lezi Wang
Publikováno v:
Terrorism, Security, and Computation ISBN: 9783030543822
BMVC
BMVC
In this study, we address a cross-domain problem of applying computer vision approaches to reason about human facial behavior when people play The Resistance game. To capture the facial behaviors, we first collect several hours of video where the par
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::507e4c2ba33e1382566362657644aa36
https://doi.org/10.1007/978-3-030-54383-9_7
https://doi.org/10.1007/978-3-030-54383-9_7
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585228
ECCV (18)
ECCV (18)
A movie’s key moments stand out of the screenplay to grab an audience’s attention and make movie browsing efficient. But a lack of annotations makes the existing approaches not applicable to movie key moment detection. To get rid of human annotat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7845b4d76420bfa9d664b12c7fd0b5d9
https://doi.org/10.1007/978-3-030-58523-5_18
https://doi.org/10.1007/978-3-030-58523-5_18
Autor:
Bo Liu, Dimitris N. Metaxas, Ziyan Wu, Kuan-Chuan Peng, Rajat Vikram Singh, Srikrishna Karanam, Lezi Wang
Publikováno v:
ICCV
Recent developments in gradient-based attention modeling have seen attention maps emerge as a powerful tool for interpreting convolutional neural networks. Despite good localization for an individual class of interest, these techniques produce attent
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::56b536fc2d143649d9fdb263b040085c
http://arxiv.org/abs/1811.07484
http://arxiv.org/abs/1811.07484
Autor:
Carlos Manuel Muñiz, Leonid Sigal, Dimitris N. Metaxas, Lezi Wang, Hareesh Ravi, Mubbasir Kapadia
Publikováno v:
CVPR
We propose an end-to-end network for visual illustration of a sequence of sentences forming a story. At the core of our model is the ability to model the inter-related nature of the sentences within a story, as well as the ability to learn coherence
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1bcb1466d20fc3ca9f9efdf6486c09bd
https://doi.org/10.1109/cvpr.2018.00794
https://doi.org/10.1109/cvpr.2018.00794
Publikováno v:
FG
Face detection and landmark localization have been extensively investigated and are the prerequisite for many face applications, such as face recognition and 3D face reconstruction. Most existing methods achieve success on only one of the two problem
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4e76fae43753df871c07f2c5c6c2f205
https://doi.org/10.1109/fg.2017.40
https://doi.org/10.1109/fg.2017.40
Publikováno v:
Telecommunication Systems. 59:401-413
This study addresses an automatic approach to analyze the structure of large scale web videos based on visual and acoustic information. In our approach, video streams are macro-segmented via mining the duplicate sequences. Acoustic and visual informa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3052a9a3cc8b726624c03da87ee7e627
https://doi.org/10.1007/s11235-014-9945-9
https://doi.org/10.1007/s11235-014-9945-9
Publikováno v:
ICME Workshops
This paper introduces our system competing in MSR-Bing Image Retrieval Challenge at ICME 2014. The task of the challenge is to rank images by their relevance to a given topic, by leveraging cues hidden in search engine's click log. With the successfu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4b5cef04e3d9475514c60e9e94a9166b
https://doi.org/10.1109/icmew.2014.6890605
https://doi.org/10.1109/icmew.2014.6890605
Publikováno v:
ICASSP
Image search reranking has become a widely-used approach to significantly boost retrieval performance in the state-of-art content-based image retrieval system. Most of the methods merely rely on matching visual distances between query and initial res
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4138875301f85c564f3289c742e8a748
https://doi.org/10.1109/icassp.2013.6637935
https://doi.org/10.1109/icassp.2013.6637935
Publikováno v:
ICASSP
The state of the art in query expansion is mainly based on the spatial information. These methods achieve high performance, however, suffer from huge computation and memory. The objective of this paper is to perform visual reranking in near-real time
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::110b78623b3332d91a004d4b3cb4bb95
https://doi.org/10.1109/icassp.2013.6637936
https://doi.org/10.1109/icassp.2013.6637936