Abin Jose, M.Sc

[team/jose.jpg]

Researcher
Video Analysis and Content Recognition Group

 

Contact Information

email: jose@ient.rwth-aachen.de
phone: +49 (0) 241 80 2 7679
fax: +49 (0) 241 80 22 196

Visiting Times

Wednesday and Thursday, 10:00 to 12:00 and 14:00 to 16:00
Room 33a

Mailing Address

Abin Jose
Institut für Nachrichtentechnik
RWTH Aachen
D-52056 Aachen

Research Topic

Optimized Feature Space Learning for Generating Efficient Binary Codes for Image Retrieval

Image retrieval is a problem in which similar images are fetched from a database based on a similarity measure. A good and efficient image retrieval system have the following requirements. Mainly, the feature space learned must be optimized in a sense, similar images are close together and dissimilar images are farther apart. ..

More ...

Publications

A. Jose, S. Yan, Z. Mi, and J.-R. Ohm, “DEEP SUBCLASS LINEAR DISCRIMINANT ANALYSIS FOR MULTIMODAL FEATURE SPACE LEARNING,” in Proc. of IEEE International Conference on Image Processing ICIP '20, IEEE, Piscataway, Oct. 2020. [ bib ]

A. Jose, R. D. Lopez, I. Heisterklaus, and M. Wien, “Pyramid Pooling of Convolutional Feature Maps for Image Retrieval,” in Proc. of IEEE International Conference on Image Processing ICIP '18, IEEE, Piscataway, Oct. 2018. [ bib ]

A. Jose, T. Horstmann, and J.-R. Ohm, “Optimized Binary Hashing Codes Generated by Siamese Neural Networks for Image Retrieval,” in Proc. of European Signal Processing Conference EUSIPCO '18, IEEE, Piscataway, Sept. 2018. [ bib ]

A. Jose, S. Yan, and I. Heisterklaus, “Binary hashing using siamese neural networks,” in Proc. of IEEE International Conference on Image Processing ICIP '17, IEEE, Piscataway, Sept. 2017. [ bib ]

A. Jose and I. Heisterklaus, “Bag of fisher vectors representation of images by saliency-based spatial partitioning,” in Proc. of IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP '17, IEEE, Piscataway, Mar. 2017. [ bib ]

A. Jose and I. Heisterklaus, “Saliency based spatial partitioning for global image representations,” in Proc. of International Student Conference on Electrical Engineering POSTER '16, May 2016. [ bib ]

NOTICE FOR IEEE PUBLICATIONS: © IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works, must be obtained from the IEEE. Contact: Manager, Copyrights and Permissions / IEEE Service Center / 445 Hoes Lane / P.O. Box 1331 / Piscataway, NJ 08855-1331, USA. Telephone: + Intl. 908-562-3966.