Unsupervised segmentation of action segments in egocentric videos using gaze
- 1 September 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 351-356
Abstract
Unsupervised segmentation of action segments in egocentric videos is a desirable feature in tasks such as activity recognition and content-based video retrieval. Reducing the search space into a finite set of action segments facilitates a faster and less noisy matching. However, there exist a substantial gap in machine's understanding of natural temporal cuts during a continuous human activity. This work reports on a novel gaze-based approach for segmenting action segments in videos captured using an egocentric camera. Gaze is used to locate the region-of-interest inside a frame. By tracking two simple motion-based parameters inside successive regions-of-interest, we discover a finite set of temporal cuts. We present several results using combinations (of the two parameters) on a dataset, i.e., BRISGAZE-ACTIONS. The dataset contains egocentric videos depicting several daily-living activities. The quality of the temporal cuts is further improved by implementing two entropy measures.Keywords
All Related Versions
This publication has 26 references indexed in Scilit:
- Hierarchical Method for Segmentation by Classification of Motion Capture Data2015
- Automatic Human Mocap Data ClassificationIEEE Transactions on Multimedia, 2014
- 3D Facial Expression Classification Using 3D Facial Surface Normals2014
- Automated human motion segmentation via motion regularitiesThe Visual Computer, 2013
- Segmentation and recognition of motion streams by similarity searchACM Transactions on Multimedia Computing, Communications, and Applications, 2007
- Efficient content-based retrieval of motion capture dataACM Transactions on Graphics, 2005
- Eye movements in natural behaviorTrends in Cognitive Sciences, 2005
- Automated extraction and parameterization of motions in large data setsACM Transactions on Graphics, 2004
- Memory Representations in Natural TasksJournal of Cognitive Neuroscience, 1995
- Where we look when we steerNature, 1994