How related exemplars help complex event detection in web videos?

Publication Type:
Conference Proceeding
Proceedings of the IEEE International Conference on Computer Vision, 2013, pp. 2104 - 2111
Issue Date:
Filename Description Size
how.pdfPublished version1.79 MB
Adobe PDF
Full metadata record
Compared to visual concepts such as actions, scenes and objects, complex event is a higher level abstraction of longer video sequences. For example, a 'marriage proposal' event is described by multiple objects (e.g., ring, faces), scenes (e.g., in a restaurant, outdoor) and actions (e.g., kneeling down). The positive exemplars which exactly convey the precise semantic of an event are hard to obtain. It would be beneficial to utilize the related exemplars for complex event detection. However, the semantic correlations between related exemplars and the target event vary substantially as relatedness assessment is subjective. Two related exemplars can be about completely different events, e.g., in the TRECVID MED dataset, both bicycle riding and equestrianism are labeled as related to 'attempting a bike trick' event. To tackle the subjectiveness of human assessment, our algorithm automatically evaluates how positive the related exemplars are for the detection of an event and uses them on an exemplar-specific basis. Experiments demonstrate that our algorithm is able to utilize related exemplars adaptively, and the algorithm gains good performance for complex event detection. © 2013 IEEE.
Please use this identifier to cite or link to this item: