Zobrazeno 1 - 10
of 145
pro vyhledávání: '"Anni Cai"'
Publikováno v:
In The Journal of China Universities of Posts and Telecommunications December 2016 23(6):1-7
Publikováno v:
Neurocomputing. 214:618-628
This paper deals with the problem of modeling Internet images and associated texts for cross-modal retrieval such as text-to-image retrieval and image-to-text retrieval. We start with deep canonical correlation analysis (DCCA), a deep approach for ma
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b686876c6488747c04fdaa55dcb4bf20
https://doi.org/10.1016/j.neucom.2016.06.047
https://doi.org/10.1016/j.neucom.2016.06.047
Publikováno v:
IEEE Transactions on Multimedia. 18:1201-1216
With the explosive growth of web data, effective and efficient technologies are in urgent need for retrieving semantically relevant contents of heterogeneous modalities. Previous studies devote efforts to modeling simple cross-modal statistical depen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e36cca4019755f2c54bb2ab00017c033
https://doi.org/10.1109/tmm.2016.2535864
https://doi.org/10.1109/tmm.2016.2535864
Publikováno v:
Neurocomputing. 168:917-929
Visual attention influenced by example images and predefined targets are widely studied in both cognitive and computer vision fields. Nevertheless, semantics, known to be related to high-level human perception, have a great influence on top-down atte
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cd7567413f6169badeb50cf08b46c5be
https://doi.org/10.1016/j.neucom.2015.05.033
https://doi.org/10.1016/j.neucom.2015.05.033
Publikováno v:
International Journal of Advancements in Computing Technology. 5:296-303
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ad2af257622704e77e1c03e3a81360a5
https://doi.org/10.4156/ijact.vol5.issue7.36
https://doi.org/10.4156/ijact.vol5.issue7.36
Publikováno v:
ICASSP
Most instance search systems are based on modeling local features. It remains a challenge to apply deep learning techniques into this task because of the asymmetrical similarity between the query region and dataset images. In this paper, we propose A
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::11819783548acd86f1ea87cad53b02e5
https://doi.org/10.1109/icassp.2016.7472173
https://doi.org/10.1109/icassp.2016.7472173
Publikováno v:
Multimedia Tools and Applications. 68:641-657
Data imbalance problem often exists in our real life dataset, especial for massive video dataset, however, the balanced data distribution and the same misclassification cost are assumed in traditional machine learning algorithms, thus, it will be dif
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3bd0f1517c6d9c4467dffbb57ef7b859
https://doi.org/10.1007/s11042-012-1071-7
https://doi.org/10.1007/s11042-012-1071-7
Publikováno v:
VCIP
With the explosive growth of online multi-media data, methodologies of retrieving documents from heterogeneous modalities are indispensable to facilitate information acquisition in real applications. Most of existing research efforts are focused on b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5ea975293ecf1eaab0f5bd127435edc6
https://doi.org/10.1109/vcip.2015.7457841
https://doi.org/10.1109/vcip.2015.7457841
Publikováno v:
Journal of Electronics (China). 25:415-421
This letter proposes fingerprint-based key binding/recovering with fuzzy vault. Fingerprint minutiae data and the cryptographic key are merged together by a multivariable linear function. First, the minutiae data are bound by a set of random data thr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8984502ce23425ee64220a487f2c4a51
https://doi.org/10.1007/s11767-007-0152-7
https://doi.org/10.1007/s11767-007-0152-7
Publikováno v:
Pattern Recognition. 39:2131-2140
Traditionally, fingerprint matching is minutia-based, which establishes the minutiae correspondences between two fingerprints. In this paper, a novel fingerprint matching algorithm is presented, which establishes both the ridge correspondences and th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::198678004765a6347b2c2655e90fdb01
https://doi.org/10.1016/j.patcog.2006.05.001
https://doi.org/10.1016/j.patcog.2006.05.001