Dynamic concept composition for zero-example event detection

Xiaojun Chang, Yi Yang, Guodong Long, Chengqi Zhang, Alexander G. Hauptmann

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

35 Citations (Scopus)


In this paper, we focus on automatically detecting events in unconstrained videos without the use of any visual training exemplars. In principle, zero-shot learning makes it possible to train an event detection model based on the assumption that events (e.g. birthday party) can be described by multiple mid-level semantic concepts (e.g. "blowing candle", "birthday cake"). Towards this goal, we first pre-Train a bundle of concept classifiers using data from other sources. Then we evaluate the semantic correlation of each concept w.r.t. the event of interest and pick up the relevant concept classifiers, which are applied on all test videos to get multiple prediction score vectors. While most existing systems combine the predictions of the concept classifiers with fixed weights, we propose to learn the optimal weights of the concept classifiers for each testing video by exploring a set of online available videos with freeform text descriptions of their content. To validate the effectiveness of the proposed approach, we have conducted extensive experiments on the latest TRECVID MEDTest 2014, MEDTest 2013 and CCV dataset. The experimental results confirm the superiority of the proposed approach.

Original languageEnglish
Title of host publicationProceedings of the Thirtieth AAAI Conference on Artificial Intelligence
EditorsDale Schuurmans, Michael Wellman
Place of PublicationPalo Alto CA USA
PublisherAssociation for the Advancement of Artificial Intelligence (AAAI)
Number of pages7
ISBN (Electronic)9781577357605
Publication statusPublished - 2016
Externally publishedYes
EventAAAI Conference on Artificial Intelligence 2016 - Phoenix Convention Center, Phoenix, United States of America
Duration: 12 Feb 201617 Feb 2016
Conference number: 30th


ConferenceAAAI Conference on Artificial Intelligence 2016
Abbreviated titleAAAI 2016
Country/TerritoryUnited States of America
Internet address

Cite this