Active Video Summarization: Customized Summaries via On-line Interaction with the User

Active Video Summarization: Customized Summaries via On-line Interaction with the User
Title:
Active Video Summarization: Customized Summaries via On-line Interaction with the User
Other Titles:
Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17)
DOI:
Keywords:
Publication Date:
04 February 2017
Citation:
GARCIA DEL MOLINO, A.; BOIX, X.; LIM, J.; TAN, A.. Active Video Summarization: Customized Summaries via On-line Interaction with the User. AAAI Conference on Artificial Intelligence, North America, feb. 2017. Available at: <http://www.aaai.org/ocs/index.php/AAAI/AAAI17/paper/view/14856>.
Abstract:
To facilitate the browsing of long videos, automatic video summarization provides an excerpt that represents its content. In the case of egocentric and consumer videos, due to their personal nature, adapting the summary to specific user's preferences is desirable. Current approaches to customizable video summarization obtain the user's preferences prior to the summarization process. As a result, the user needs to manually modify the summary to further meet the preferences. In this paper, we introduce Active Video Summarization (AVS), an interactive approach to gather the user's preferences while creating the summary. AVS asks questions about the summary to update it on-line until the user is satisfied. To minimize the interaction, the best segment to inquire next is inferred from the previous feedback. We evaluate AVS in the commonly used UTEgo dataset. We also introduce a new dataset for customized video summarization (CSumm) recorded with a Google Glass. The results show that AVS achieves an excellent compromise between usability and quality. In 41% of the videos, AVS is considered the best over all tested baselines, including summaries manually generated. Also, when looking for specific events in the video, AVS provides an average level of satisfaction higher than those of all other baselines after only six questions to the user.
License type:
PublisherCopyrights
Funding Info:
This material is based upon work supported by the CBMM, funded by NSF STC award CCF-1231216; The MOE AcRF Tier 2 grant R-263-000-B32-112; the Singapore DIRP grant 9014100596; A*STAR JCO REVIVE project grant 1335h00098; the Singapore International Graduate Award (SINGA); and the Obra Social ``La Caixa'' and Casa Asia Fellowship.
Description:
Full paper can be downloaded from the Publisher's URL provided.
ISSN:
2159-5399
Files uploaded:
File Size Format Action
There are no attached files.