Robust speech recognition using spatial–temporal feature distribution characteristics

Chen, Berlin; Chen, Wei-Hau; Lin, Shing-Jong; Chu, Weidong

doi:10.1016/j.patrec.2011.01.016

Cited by 4 publications

(1 citation statement)

References 40 publications

(55 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Real spatio-temporal processing should exploit the fact that many interesting events in a video sequence are characterized by strong variations of the data in both the spatial and temporal dimensions. Recently, spatio-temporal feature has drawn attention for human action recognition and content-based video analysis [1], [2]. The key idea of spatiotemporal feature is to extend two dimensional features to the temporal dimension.…”

Section: Introductionmentioning

confidence: 99%

A Video Content Classification Algorithm Applying to Human Action Recognition

Sun

Jiang

et al. 2013

ElAEE

View full text Add to dashboard Cite

A new classification algorithm of human action recognition of video content is suggested in our paper. It analyzes the variation of the content of video scenes or human action from video bi-modal features, in order to cognize content efficiently and precisely. This scheme is based on the pattern analysis of spatio-temporal slices and audio signature feature extracted from the video files. The Spatial-temporal Variation Histogram feature is firstly defined in our paper. It is applied to describe spatio-temporal variation analysis of human action or video scenes. The audio signature is also applied to identify the audio content by extracting unique signatures from a part of audio signal. The experiments show excellent performance of classification on the KTH dataset.

show abstract

Section: Introductionmentioning

confidence: 99%