Abstract

Automatic face association across unconstrained video frames has many practical applications. Recent advances in the area of ob ject detection have made it possible to replace the traditional tracking- based association approaches with the more robust detection-based ones. However, it is still a very challenging task for real-world unconstrained videos, especially if the sub jects are in a moving platform and at dis- tances exceeding several tens of meters. In this paper, we present a novel solution based on a Conditional Random Field (CRF) framework. The CRF approach not only gives a probabilistic and systematic treatment of the problem, but also elegantly combines global and local features. When ambiguities in labels cannot be solved by using the face appear- ance alone, our method relies on multiple contextual features to provide further evidence for association. Our algorithm works in an on-line mode and is able to reliably handle real-world videos. Results of experiments using challenging video data and comparisons with other methods are provided to demonstrate the effectiveness of our method.