Human Focused Video Description
Authors:
- 1 November 2011
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1480-1487
Abstract
This contribution addresses generation of natural language descriptions for human actions and behaviour observed in video streams. The work starts with implementation of conventional image processing techniques to extract high-level features from video. Because human is often the most important and also interesting feature, description focuses on humans and their activities. Although feature extraction processes are erroneous at various levels, we explore approaches to put them together to produce a coherent description. Evaluation is made by calculating the overlap similarity score between human authored and machine generated descriptions.Keywords
This publication has 18 references indexed in Scilit:
- High-Level Feature Detection from Video in TRECVid: A 5-Year Retrospective of Achievements2008
- SAVE: A framework for semantic annotation of visual events2008
- Human Activity Recognition with Metric Learning2008
- Face detection and recognition of natural human emotion using Markov random fieldsPersonal and Ubiquitous Computing, 2007
- Automatic Learning of Conceptual Knowledge in Image Sequences for Human Behavior Interpretation2007
- Rapid object detection using a boosted cascade of simple features2005
- Recognizing human actions: a local SVM approach2004
- Context-based vision system for place and object recognition2003
- Video query: Research directionsIBM Journal of Research and Development, 1998
- An algorithm for suffix strippingProgram: electronic library and information systems, 1980