Semantic concept discovery for large-scale zero-shot event detection

Xiaojun Chang, Yi Yang, Alexander G. Hauptmann, Eric P. Xing, Yao Liang Yu

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

67 Citations (Scopus)


We focus on detecting complex events in unconstrained Internet videos. While most existing works rely on the abundance of labeled training data, we consider a more difficult zero-shot setting where no training data is supplied. We first pre-train a number of concept classifiers using data from other sources. Then we evaluate the semantic correlation of each concept w.r.t. the event of interest. After further refinement to take prediction inaccuracy and discriminative power into account, we apply the discovered concept classifiers on all test videos and obtain multiple score vectors. These distinct score vectors are converted into pairwise comparison matrices and the nuclear norm rank aggregation framework is adopted to seek consensus. To address the challenging optimization formulation, we propose an efficient, highly scalable algorithm that is an order of magnitude faster than existing alternatives. Experiments on recent TRECVID datasets verify the superiority of the proposed approach.

Original languageEnglish
Title of host publicationProceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence
EditorsQiang Yang, Michael Wooldridge
Place of PublicationPalo Alto CA USA
PublisherAssociation for the Advancement of Artificial Intelligence (AAAI)
Number of pages7
ISBN (Electronic)9781577357384
Publication statusPublished - 2015
Externally publishedYes
EventInternational Joint Conference on Artificial Intelligence 2015 - Buenos Aires, Argentina
Duration: 25 Jul 20151 Aug 2015
Conference number: 24th


ConferenceInternational Joint Conference on Artificial Intelligence 2015
Abbreviated titleIJCAI 2015
CityBuenos Aires
Internet address

Cite this