The influence of temporal information on human action recognition with large number of classes
Date
2014
Authors
Murthy, O. V. Ramana
Goecke, Roland
Journal Title
Journal ISSN
Volume Title
Publisher
IEEE
Abstract
Human action recognition from video input has seen much interest over the last decade. In recent years, the trend is clearly towards action recognition in real-world, unconstrained conditions (i.e. not acted) with an ever growing number of action classes. Much of the work so far has used single frames or sequences of frames where each frame was treated individually. This paper investigates the contribution that temporal information can make to human action recognition in the context of a large number of action classes. The key contributions are: (i) We propose a complementary information channel to the Bag-of- Words framework that models the temporal occurrence of the local information in videos. (ii) We investigate the influence of sensible local information whose temporal occurrence is more vital than any local information. The experimental validation on action recognition datasets with the largest number of classes to date shows the effectiveness of the proposed approach.
Description
Keywords
Gesture recognition, Computational modeling, Hidden Markov models, Histograms, Support vector machines, Training, Trajectory, Vectors, Action recognition, Experimental validations, Human-action recognition, Information channels, Local information, Number of class, Single frames, Temporal information, Motion estimation
Citation
Collections
Source
Reflective Features Detection and Hierarchical Reflections Separation in Image Sequences
Type
Conference paper