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

Publication Type:
Conference Proceeding
Citation:
IJCAI International Joint Conference on Artificial Intelligence, 2015, 2015-January pp. 2234 - 2240
Issue Date:
2015-01-01
Metrics:
Full metadata record
Files in This Item:
Filename Description Size
316.pdfPublished version2.77 MB
Adobe PDF
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.
Please use this identifier to cite or link to this item: