Background estimation, i.e. automatic recovery of the background image from a sequence of images containing moving foreground objects, is an important module in many applications, e.g. surveillance and video segmentation. In this paper, we present a simple, yet effective and robust approach for background estimation based on Loopy Belief Propagation. Robustness of the proposed approach means: (i) minimal assumption on the input frames, and (ii) no need to tune parameters. Basically, the background can be recovered even when the occluding foreground objects stay still for a long time. Furthermore, no motion information needs to be known or estimated for the foreground objects, which implies that background can be recovered from a set of frames which are not consecutive temporally. Analysis and experiments are provided to compare the proposed approach to related methods. Experimental results on typical surveillance videos demonstrate the effectiveness of our approach.

A novel tandem-free solution for multiparty VoIP conferences called PASS (peer-aware silence suppression) is presented. Similar to traditional tandem-free solutions, PASS introduces a limit on the number of concurrent speakers in a conference. But in contrast to traditional solutions, PASS silence suppression and speaker selection are completely distributed, running on each client. No speaker selection is performed at the bridge at all. This configuration leads to better scalability, lower bandwidth occupation and jitter buffer delay, and higher compatibility with a wide variety of network topologies. The key component of PASS, distributed silence suppression and speaker selection, is realized through a robust approach proposed in this paper. Based on a voice activity measure derived using machine learning techniques, this approach is able to reliably suppress silence in complex environments, and perform accurate and transparent speaker selection as well

Person-based indices and timelines can enable fast and non-linear access to recorded meetings. This paper focuses on how to automatically construct those indices and timelines by using face recognition techniques. While there exist extensive research in generic face recognition, recognizing faces in recorded meetings is still an understudied area. Real-world meeting videos impose several interesting and unique challenges including complex lighting, low imaging quality, and large variations in head pose and size. In this paper, a promising approach based on MRC-Boosting is presented to address these challenges, which achieves encouraging performance on real-world meeting videos and shows superior accuracy and robustness compared to two popular existing approaches

In this paper, a novel classification algorithm called MRC-Boosting is proposed. Through aggregating maximal-rejection-classifier features under boosting framework, this algorithm can deal with complicated two-class classification problem, especially for the category called target detection problem where a target class should be discriminated from tile surrounding clutter class. MRC-Boosting is efficient since unlike many other boosting based algorithms, at each iteration the optimal feature is computed in closed-form, with neither exhaustive search nor time-consuming numerical optimization. Furthermore, a variant of MRC-Boosting is derived and applied to face recognition. This variant MRC-Boosting algorithm is able to utilize large amount of training samples efficiently overcoming the difficulty faced by other algorithms like AdaBoost. The effectiveness of the proposed algorithm is validated by face recognition experiments on CMU-PIE database.

Nearest neighbor classification expects the class conditional probabilities to be locally constant. The assumption becomes invalid in high dimension due to the curse-of-dimensionality. Severe bias can be introduced under this condition when using nearest neighbor rule. We propose an adaptive nearest neighbor classification method "indecisive classifier" to minimize bias and variance by avoiding decision making in some hard-decision region. As a result, better classification performance can be expected in some scenario such as video based face recognition.