) which is piece-wise constant in the domain of interest. This suggests that BB might be useful for retrospective temporal segmentation tasks, too. We illustrate the potential useful-ness of BB for temporal segmentation on two examples. First, we segment neural spike train data, demonstrating that BB

Temporal segmentation of facial gestures in spontaneous facial behavior recorded in real-world settings is an important, unsolved, and relatively unexplored problem in facial image analysis. Several issues contribute to the challenge of this task. These include non-frontal pose, moderate to large

is especially difficult in ego-centric videos when the camera is constantly moving due to natural head movement of the wearer. We propose a robust temporal segmentation of egocentric videos into a hierar-chy of motion classes using a newCumulative Displacement Curves. Unlike instantaneous motion vectors

Image segmentation provides a powerful semantic description of video imagery essential in image understanding and efficient manipulation of image data. In particular, segmentation based on image motion defines regions undergoing similar motion allowing image coding system to more efficiently

temporal components. In this work, our goal is to identify key temporal segments in a video clip that are most relevant to a video event category. This is achieved by discovery of recurring visual concepts across the videos from a given event class. The temporal segments of a video where this key concept

This paper deals with temporal segmentation of acoustic signals and features extraction. Segmentation and features extraction are aimed at being a first step for sound signal representation, coding, transformation, indexation and multimedia. Three interdependent schemes of segmentation are defined

Many algorithms for temporal video partitioning rely on the analysis of uncompressed video features. Since the information relevant to the partitioning process can be extracted directly from the MPEG compressed stream, higher efficiency can be achieved utilising information from the MPEG compressed

Segmenting note objects in a real time context is useful for live performances, audio broadcasting, or object-based coding. This temporal segmentation relies upon the correct detection of onsets and offsets of musical notes, an area of much research over recent years. However the low

Spatio-temporal cues are powerful sources of information for segmentation in videos. In this work we present an efficient and simple technique for spatio-temporal segmenta-tion that is based on a low-rank spectral clustering algorithm. The complexity of graph-based spatio-temporal segmentation

Temporal segmentation of human motion into actions is central to the understanding and building of computational models of human motion and activity recognition. Several issues contribute to the challenge of temporal segmentation and classification of human motion. These include the large