TY - GEN
T1 - DUT-MMSR at MediaEval 2017
T2 - MediaEval 2017
AU - Reza Aditya Permadi, Reza
AU - Septian Gilang Permana Putra, Septian
AU - Helmiriawan, Helmi
AU - Liem, Cynthia
PY - 2017
Y1 - 2017
N2 - This paper describes our approach for the submission to the Media-eval 2017 Predicting Media Interestingness Task, which was particularlydeveloped for the Image subtask. An approach using a late fusion strategy is employed, combining classifiers from different features by stacking them using logistic regression (LR). As the task ground truth was based on pairwise evaluation of shots or keyframe images within the same movie, next to using precomputed features as-is, we also include a more contextual feature, considering aver-aged feature values over each movie. Furthermore, we also consider evaluation outcomes for the heuristic algorithm that yielded the highest MAPscore on the 2016 Image subtask. Considering results obtained for the development and test sets, our late fusion method shows consistent performance on the Image subtask, but not on the Video subtask. Furthermore, clear differences can be observed between MAP@10 and MAP scores.
AB - This paper describes our approach for the submission to the Media-eval 2017 Predicting Media Interestingness Task, which was particularlydeveloped for the Image subtask. An approach using a late fusion strategy is employed, combining classifiers from different features by stacking them using logistic regression (LR). As the task ground truth was based on pairwise evaluation of shots or keyframe images within the same movie, next to using precomputed features as-is, we also include a more contextual feature, considering aver-aged feature values over each movie. Furthermore, we also consider evaluation outcomes for the heuristic algorithm that yielded the highest MAPscore on the 2016 Image subtask. Considering results obtained for the development and test sets, our late fusion method shows consistent performance on the Image subtask, but not on the Video subtask. Furthermore, clear differences can be observed between MAP@10 and MAP scores.
UR - http://resolver.tudelft.nl/uuid:52feb4e1-5812-4824-b169-d1dab9b45278
M3 - Conference contribution
T3 - CEUR Workshop Proceedings
SP - 1
EP - 3
BT - Working Notes Proceedings of the MediaEval 2017 Workshop
A2 - Gravier, Guillaume
A2 - Bischke , Benjamin
A2 - Demarty, Claire-Hélène
A2 - Zaharieva, Maia
A2 - Riegler, Michael
A2 - Dellandrea, Emmanuel
A2 - Bogdanov, Dmitry
A2 - Sutcliffe, Richard
A2 - Jones, Gareth J.F.
A2 - Larson, Martha
Y2 - 13 September 2017 through 15 September 2017
ER -