6653

Retrieving Objects, People and Places from a Video Collection: TRECVID'12 Instance Search Task

Christian Schulze, Sebastian Palacio

Proceedings of the TRECVID 2012 Workshop TRECVID Workshop (Trecvid-2012), November 26-28, Gaithersburg,, Maryland, USA , Online-Proceedings , 2012
We participated in 2012's TRECVID instance search task (INS) and wanted to measure how much we can positively impact the performance of a state-of-the-art video retrieval system based on local features and relying solely on content-based retrieval methods. Our agenda consisted in the implementation of some incremental additions to the system that included filtering of local features, custom codebook generation and tailored ranking metrics for the indexed videos. We got three versions of our system tested which iteratively included algorithms that consistently pushed further the performance of the system. Given the terms under which the system had to be implemented - ground-truth was not available-, we used artificially generated datasets to get an idea of how much progress were we making with each additional component. We showed that improvements requiring small computational and human effort can already have positive impacts on the system's performance.

Show BibTex:

@inproceedings {
       abstract = {We participated in 2012's TRECVID instance search
task (INS) and wanted to measure how much we can positively
impact the performance of a state-of-the-art video retrieval
system based on local features and relying solely on content-based
retrieval methods. Our agenda consisted in the implementation of
some incremental additions to the system that included filtering
of local features, custom codebook generation and tailored
ranking metrics for the indexed videos. We got three versions
of our system tested which iteratively included algorithms that
consistently pushed further the performance of the system. Given
the terms under which the system had to be implemented -
ground-truth was not available-, we used artificially generated
datasets to get an idea of how much progress were we making
with each additional component. We showed that improvements
requiring small computational and human effort can already have
positive impacts on the system's performance.},
       number = {}, 
       month = {11}, 
       year = {2012}, 
       title = {Retrieving Objects, People and Places from a Video Collection: TRECVID'12 Instance Search Task}, 
       journal = {}, 
       volume = {}, 
       pages = {}, 
       publisher = {Online-Proceedings}, 
       author = {Christian Schulze, Sebastian Palacio}, 
       keywords = {video search, video retrieval, trecvid, local features, inverted file},
       url = {http://www-nlpir.nist.gov/projects/tvpubs/tv.pubs.12.org.html}
}