TY - GEN
T1 - Movie genre classification via scene categorization
AU - Zhou, Howard
AU - Hermans, Tucker
AU - Karandikar, Asmita V.
AU - Rehg, James M.
PY - 2010
Y1 - 2010
N2 - This paper presents a method for movie genre categorization of movie trailers, based on scene categorization. We view our approach as a step forward from using only low-level visual feature cues, towards the eventual goal of high-level seman- tic understanding of feature films. Our approach decom- poses each trailer into a collection of keyframes through shot boundary analysis. From these keyframes, we use state-of- the-art scene detectors and descriptors to extract features, which are then used for shot categorization via unsuper- vised learning. This allows us to represent trailers using a bag-of-visual-words (bovw) model with shot classes as vo- cabularies. We approach the genre classification task by mapping bovw temporally structured trailer features to four high-level movie genres: action, comedy, drama or horror films. We have conducted experiments on 1239 annotated trailers. Our experimental results demonstrate that exploit- ing scene structures improves film genre classification com- pared to using only low-level visual features.
AB - This paper presents a method for movie genre categorization of movie trailers, based on scene categorization. We view our approach as a step forward from using only low-level visual feature cues, towards the eventual goal of high-level seman- tic understanding of feature films. Our approach decom- poses each trailer into a collection of keyframes through shot boundary analysis. From these keyframes, we use state-of- the-art scene detectors and descriptors to extract features, which are then used for shot categorization via unsuper- vised learning. This allows us to represent trailers using a bag-of-visual-words (bovw) model with shot classes as vo- cabularies. We approach the genre classification task by mapping bovw temporally structured trailer features to four high-level movie genres: action, comedy, drama or horror films. We have conducted experiments on 1239 annotated trailers. Our experimental results demonstrate that exploit- ing scene structures improves film genre classification com- pared to using only low-level visual features.
KW - genre classification
KW - scene understanding
KW - video analysis
UR - http://www.scopus.com/inward/record.url?scp=78650978477&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=78650978477&partnerID=8YFLogxK
U2 - 10.1145/1873951.1874068
DO - 10.1145/1873951.1874068
M3 - Conference contribution
AN - SCOPUS:78650978477
SN - 9781605589336
T3 - MM'10 - Proceedings of the ACM Multimedia 2010 International Conference
SP - 747
EP - 750
BT - MM'10 - Proceedings of the ACM Multimedia 2010 International Conference
T2 - 18th ACM International Conference on Multimedia ACM Multimedia 2010, MM'10
Y2 - 25 October 2010 through 29 October 2010
ER -