TY - GEN
T1 - Video summarization with semantic concept preservation
AU - Yuan, Zheng
AU - Lu, Taoran
AU - Wu, Dapeng
AU - Huang, Yu
AU - Yu, Heather
N1 - Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].
PY - 2011
Y1 - 2011
N2 - A compelling video summarization should allow viewers to understand the summary content and recover the original plot correctly. To this end, we materialize the abstract elements that are cognitively informative for viewers as concepts. They implicitly convey the semantic structure and are instantiated by semantically redundant instances. Then we analyze that a good summary should i) keep various concepts complete and balanced so as to give viewers comparable cognitive clues from a complete perspective ii) pursue the most saliency so that the rendered summary is attractive to human perception. We then formulate video summarization as an integer programming problem and give a ranking based solution. We also propose a novel method to discover the latent concepts by spectral clustering of bag-of-words features. Experiment results on human evaluation scores demonstrate that our summarization approach performs well in terms of the informativeness, enjoyability and scalibility. © 2011 ACM.
AB - A compelling video summarization should allow viewers to understand the summary content and recover the original plot correctly. To this end, we materialize the abstract elements that are cognitively informative for viewers as concepts. They implicitly convey the semantic structure and are instantiated by semantically redundant instances. Then we analyze that a good summary should i) keep various concepts complete and balanced so as to give viewers comparable cognitive clues from a complete perspective ii) pursue the most saliency so that the rendered summary is attractive to human perception. We then formulate video summarization as an integer programming problem and give a ranking based solution. We also propose a novel method to discover the latent concepts by spectral clustering of bag-of-words features. Experiment results on human evaluation scores demonstrate that our summarization approach performs well in terms of the informativeness, enjoyability and scalibility. © 2011 ACM.
KW - attention model
KW - integer programming
KW - video summarization
UR - http://www.scopus.com/inward/record.url?scp=84863515580&partnerID=8YFLogxK
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-84863515580&origin=recordpage
U2 - 10.1145/2107596.2107609
DO - 10.1145/2107596.2107609
M3 - RGC 32 - Refereed conference paper (with host publication)
SN - 9781450310963
T3 - Proceedings of the 10th International Conference on Mobile and Ubiquitous Multimedia, MUM'11
SP - 109
EP - 112
BT - Proceedings of the 10th International Conference on Mobile and Ubiquitous Multimedia, MUM'11
T2 - 10th International Conference on Mobile and Ubiquitous Multimedia, MUM'11
Y2 - 7 December 2011 through 9 December 2011
ER -