Zobrazeno 1 - 10
of 37
pro vyhledávání: '"Paul A. Viola"'
Autor:
Pei Yin, Cha Zhang, Xinding Sun, N. Pinto, Ross Cutler, Yong Rui, Paul A. Viola, Zhengyou Zhang
Publikováno v:
IEEE Transactions on Multimedia. 10:1541-1552
Identifying the active speaker in a video of a distributed meeting can be very helpful for remote participants to understand the dynamics of the meeting. A straightforward application of such analysis is to stream a high resolution video of the speak
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::950856ef7b9b6e7dea5020fabe024311
https://doi.org/10.1109/tmm.2008.2007344
https://doi.org/10.1109/tmm.2008.2007344
Publikováno v:
Artificial Intelligence. 170:1101-1122
To successfully embed statistical machine learning models in real world applications, two post-deployment capabilities must be provided: (1) the ability to solicit user corrections and (2) the ability to update the model from these corrections. We re
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f88320a8fd0608cb6c2057a792aca523
https://doi.org/10.1016/j.artint.2006.08.001
https://doi.org/10.1016/j.artint.2006.08.001
Publikováno v:
ICCV
This paper describes a pedestrian detection system that integratesimage intensity information with motion information.We use a detection style algorithm that scans a detectorover two consecutive frames of a video sequence. Thedetector is trained (usi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::776268994184b4a68e98fd4426e8e4a3
https://doi.org/10.1007/s11263-005-6644-8
https://doi.org/10.1007/s11263-005-6644-8
Autor:
Paul A. Viola, Kinh Tieu
Publikováno v:
CVPR
We present an approach for image retrieval using a very large number of highly selective features and efficient online learning. Our approach is predicated on the assumption that each image is generated by a sparse set of visual "causes" and that ima
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::60bc3a8e75a100ef82f3b946241bda51
https://doi.org/10.1023/b:visi.0000004830.93820.78
https://doi.org/10.1023/b:visi.0000004830.93820.78
Autor:
Paul A. Viola, William M. Wells
Publikováno v:
International Journal of Computer Vision. 24:137-154
A new information-theoretic approach is presented for finding the pose of an object in an image. The technique does not require information about the surface properties of the object, besides its shape, and is robust with respect to variations of ill
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b2a9fb53378a2dc486c93872d4a50ad0
https://doi.org/10.1023/a:1007958904918
https://doi.org/10.1023/a:1007958904918
Publikováno v:
CVPR
In computer vision, the bag-of-visual words image representation has been shown to yield good results. Recent work has shown that modeling the spatial relationship between visual words further improves performance. Previous work extracts higher-order
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7d4659b209e50239893c5c69705c51ac
https://doi.org/10.1109/cvpr.2008.4587403
https://doi.org/10.1109/cvpr.2008.4587403
Publikováno v:
ICDAR
This paper proposes a machine learning approach to grouping problems in ink parsing. Starting from an initial segmentation, hypotheses are generated by perturbing local configurations and processed in a high-confidence-first fashion, where the confid
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8e5723729155c1d7d3e714c0e69971e8
https://doi.org/10.1109/icdar.2007.4378670
https://doi.org/10.1109/icdar.2007.4378670
Publikováno v:
CVPR
We propose a method for face recognition based on a discriminative linear projection. In this formulation images are treated as tensors, rather than the more conventional vector of pixels. Projections are pursued sequentially and take the form of a r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1e176f71e9c007963130d28cc8e48e31
https://doi.org/10.1109/cvpr.2007.383107
https://doi.org/10.1109/cvpr.2007.383107
Publikováno v:
MMSP
Speaker detection is a very important task in distributed meeting applications. This paper discusses a number of challenges we met while designing a speaker detector for the Microsoft RoundTable distributed meeting device, and proposes a boosting-bas
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c61470abe0d6e13632f2608e1fabfa19
https://doi.org/10.1109/mmsp.2006.285274
https://doi.org/10.1109/mmsp.2006.285274
Publikováno v:
ICML
The Viterbi algorithm is an efficient and optimal method for decoding linear-chain Markov Models. However, the entire input sequence must be observed before the labels for any time step can be generated, and therefore Viterbi cannot be directly appli
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::161df9764ef0a80512b643ef1449c8a1
https://doi.org/10.1145/1143844.1143927
https://doi.org/10.1145/1143844.1143927