Character Identification in TV-series via Non-local Cost Aggregation

Ching-Hui Chen and Rama Chellappa

Abstract

We propose a non-local cost aggregation algorithm to recognize the identity of face and person tracks in a TV-series. In our approach, the fundamental element for identification is a track node, which is built on top of face and person tracks. Track nodes with temporal dependency are grouped into a knot. These knots then serve as the basic units in the construction of a k-knot graph for exploring the video structure. We build the minimum-distance spanning tree (MST) from the k-knot graph such that track nodes of similar appearance are adjacent to each other in MST. Non-local cost aggregation is performed on MST, which ensures information from face and person tracks is utilized as a whole to improve the identification performance. The identification task is performed by minimizing the cost of each knot, which takes into account the unique presence of a subject in a venue. Experimental results demonstrate the effectiveness of our method.

Session

Poster 2

Files

Extended Abstract (PDF, 314K)
Paper (PDF, 706K)

DOI

10.5244/C.29.119
https://dx.doi.org/10.5244/C.29.119

Citation

Bibtex

@inproceedings{BMVC2015_119,
	title={Character Identification in TV-series via Non-local Cost Aggregation},
	author={Ching-Hui Chen and Rama Chellappa},
	year={2015},
	month={September},
	pages={119.1-119.11},
	articleno={119},
	numpages={11},
	booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
	publisher={BMVA Press},
	editor={Xianghua Xie, Mark W. Jones, and Gary K. L. Tam},
	doi={10.5244/C.29.119},
	isbn={1-901725-53-7},
	url={https://dx.doi.org/10.5244/C.29.119}
}