A monocular system for automatic face detection and tracking

Multimodal Stereoscopic Movie Summarization Conforming to Narrative Characteristics

“…As in the case of speakers, each face appearance consists simply of a video segment that starts and ends at the temporal boundaries of an uninterrupted face appearance. Such data may have been acquired through the successive application of face detection [52], face tracking [53], face clustering [54] and label propagation [55] algorithms.…”

Movie shot selection preserving narrative properties

“…As in the case of speakers, each face appearance consists simply of a video segment that starts and ends at the temporal boundaries of an uninterrupted face appearance. Such data may have been acquired through the successive application of face detection [12], face tracking [13], face clustering [14] and label propagation [15] algorithms. Despite these algorithmic prerequisites, no extra data modalities (such as the movie script) are required, beyond the film itself.…”

Facial image clustering in stereo videos using local binary patterns and double spectral analysis

“…In the first approach, the face detection [1] is performed every n frames in one channel (video) of the stereoscopic video, followed by a face tracker [22] at the same channel. In the second approach, face detection [1] was applied on both channels, mismatches between the two channels were rejected and a stereo tracking algorithm [3] was applied in both channels. By using the above approaches we end up with a number of facial trajectories, namely series of consecutive facial images.…”

“…This paper deals with facial image clustering applied on 3D feature films, where the goal is to separate facial images derived through face detectors and trackers [1]- [3] into groups, for which within-cluster similarity is high whereas betweencluster similarity is smaller. Ideally, such an algorithm should assign all facial images from a certain subject to the same cluster.…”