Zobrazeno 1 - 10
of 22
pro vyhledávání: '"Raghuraman Gopalan"'
Publikováno v:
IEEE Signal Processing Magazine. 32:53-69
In pattern recognition and computer vision, one is often faced with scenarios where the training data used to learn a model have different distribution from the data on which the model is applied. Regardless of the cause, any distributional change th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9ab0cc4e1b45d41d078bd57557a34510
https://doi.org/10.1109/msp.2014.2347059
https://doi.org/10.1109/msp.2014.2347059
Publikováno v:
Foundations and Trends® in Computer Graphics and Vision. 8:285-378
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2d899998912dd809f4d7f278390f6770
https://doi.org/10.1561/0600000057
https://doi.org/10.1561/0600000057
Autor:
Raghuraman Gopalan
Publikováno v:
BigMM
We address domain adaptation in the context of clustering where we are given a set of unlabeled data, coming from several domains, and the goal is to group data into different categories regardless of the domain they come from. This is a challenging
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d90a71d101e9b277e9879328e2ca6758
https://doi.org/10.1109/bigmm.2017.16
https://doi.org/10.1109/bigmm.2017.16
Autor:
Raghuraman Gopalan
Publikováno v:
BigMM
Predicting the temporal evolution of images is an interesting problem that has applications in surveillance, content recommendation and behavioral analysis. Given a single image or a stream of images with timestamps, the goal of this work is to predi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3bbb27d0fa9b1115a899c316b32a670a
https://doi.org/10.1109/bigmm.2017.15
https://doi.org/10.1109/bigmm.2017.15
Autor:
Raghuraman Gopalan, Huy Tho Ho
Publikováno v:
International Journal of Computer Vision. 109:110-125
Many classification algorithms see a reduction in performance when tested on data with properties different from that used for training. This problem arises very naturally in face recognition where images corresponding to the source domain (gallery,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e2d184bde790bb1d061da49f75c40913
https://doi.org/10.1007/s11263-014-0720-x
https://doi.org/10.1007/s11263-014-0720-x
Domain adaptation is an active, emerging research area that attempts to address the changes in data distribution across training and testing datasets. With the availability of a multitude of image acquisition sensors, variations due to illumination a
Publikováno v:
IEEE Transactions on Intelligent Transportation Systems. 13:1088-1098
Road scene analysis is a challenging problem that has applications in autonomous navigation of vehicles. An integral component of this system is the robust detection and tracking of lane markings. It is a hard problem primarily due to large appearanc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7761a4e7d854745f235ca5cabba59aa6
https://doi.org/10.1109/tits.2012.2184756
https://doi.org/10.1109/tits.2012.2184756
Autor:
Raghuraman Gopalan, David W. Jacobs
Publikováno v:
Computer Vision and Image Understanding. 114:135-145
Face recognition under changing lighting conditions is a challenging problem in computer vision. In this paper, we analyze the relative strengths of different lighting insensitive representations, and propose efficient classifier combination schemes
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d2dabbec24e12f082339dadc18688add
https://doi.org/10.1016/j.cviu.2009.07.005
https://doi.org/10.1016/j.cviu.2009.07.005
Publikováno v:
IEEE transactions on pattern analysis and machine intelligence. 36(11)
With unconstrained data acquisition scenarios widely prevalent, the ability to handle changes in data distribution across training and testing data sets becomes important. One way to approach this problem is through domain adaptation, and in this pap
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b9efc02a9b0d626c84e585d85d77c9e8
https://pubmed.ncbi.nlm.nih.gov/26353067
https://pubmed.ncbi.nlm.nih.gov/26353067
Autor:
Raghuraman Gopalan
Publikováno v:
CVPR
We address the problem of estimating location information of an image using principles from automated representation learning. We pursue a hierarchical sparse coding approach that learns features useful in discriminating images across locations, by i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9f69c7a56b6ab71b9f24fa8f5cc5504b
https://doi.org/10.1109/cvpr.2015.7298857
https://doi.org/10.1109/cvpr.2015.7298857