Machine Learning for Vision-Based Motion Analysis by Liang Wang Guoying Zhao Li Cheng & Matti Pietikäinen

Author:Liang Wang, Guoying Zhao, Li Cheng & Matti Pietikäinen
Language: eng
Format: epub
Publisher: Springer London, London

2.1.2 Top–Down Saliency

Unlike bottom–up saliency, top–down saliency is driven by user intent. There has been limited work done in this regard [4, 23, 28]. Existing approaches that model top–down saliency use a specific goal or task, such as object recognition. Figure 6 illustrates such an approach, where two different saliency maps are derived for a single image based on car and person recognition respectively.

Fig. 6Top–down saliency maps derived using recognition based approaches. Illustration taken from [6]

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.