Duplicate and near-duplicate digital image matching is beneficial for image search in terms of collection management, digital content protection, and search efficiency. In this ...
Background: Due to the complex and distributed nature of biological research, our current biological knowledge is spread over many redundant annotation databases maintained by man...
Brad T. Sherman, Da Wei Huang, Qina Tan, Yongjian ...
For the first time in 2007, TRECVID considered structured evaluation of automated video summarization, utilizing BBC rushes video. In 2007, we conducted user evaluations with the ...
We propose the use of latent space models applied to local invariant features for object classification. We investigate whether using latent space models enables to learn patterns...
Florent Monay, Pedro Quelhas, Daniel Gatica-Perez,...
We present a generic, efficient and iterative algorithm for interactively clustering classes of images and videos. The approach moves away from the use of large hand labelled tra...