Graduate School and Research Center in Digital Sciences

EURECOM at TRECVID 2011: The light semantic indexing task

Niaz, Usman; Redi, Miriam; Tanase, Claudiu; Merialdo, Bernard; Farinella, Giovanna; Li, Qian

TRECVID 2011, 15th International Workshop on Video Retrieval Evaluation, 2011, National Institute of Standards and Technology, Gaithersburg, USA

This year EURECOM participated in the TRECVID light Semantic Indexing (SIN) Task for the submission of four different runs for 50 concepts. Our submission builds on the runs submitted last year at the 2010 SIN task by adding more effective visual features to the third system built last year, the details of which can be found in [10]. Two of our systems target specific objects based detection. Our basic run adds densely extracted SIFT features to the pool of features of last year's basic run. The dense SIFT proves to be effective for concepts such as \Nighttime" accounting for a very low number of keypoints when extracted using a conventional log or hessian based detector. Then according to the third run from last year we add textual metadata based information that has been provided with the 2011 video database to the visual features. We improve the retrieval task by adding two more global descriptors to visual features with one capturing temporal statistics along a sequence of shots and the other capturing salient details or gist of an image. Further we enhance the visual recognition of some semantic concepts based on the detection of local objects like computer screens or scene text, and human detection like Male or Female persons.  

Document Bibtex

Title:EURECOM at TRECVID 2011: The light semantic indexing task
Type:Conference
Language:English
City:Gaithersburg
Country:UNITED STATES
Date:
Department:Data Science
Eurecom ref:3573
Copyright: © NIST. Personal use of this material is permitted. The definitive version of this paper was published in TRECVID 2011, 15th International Workshop on Video Retrieval Evaluation, 2011, National Institute of Standards and Technology, Gaithersburg, USA and is available at :
Bibtex: @inproceedings{EURECOM+3573, year = {2011}, title = {{EURECOM} at {TRECVID} 2011: {T}he light semantic indexing task}, author = {{N}iaz, {U}sman and {R}edi, {M}iriam and {T}anase, {C}laudiu and {M}erialdo, {B}ernard and {F}arinella, {G}iovanna and {L}i, {Q}ian}, booktitle = {{TRECVID} 2011, 15th {I}nternational {W}orkshop on {V}ideo {R}etrieval {E}valuation, 2011, {N}ational {I}nstitute of {S}tandards and {T}echnology, {G}aithersburg, {USA}}, address = {{G}aithersburg, {UNITED} {STATES}}, month = {11}, url = {http://www.eurecom.fr/publication/3573} }
See also: