1 Hit in 3.2 sec

Mid-level Representation for Visual Recognition [article]

Moin Nabi
2015 arXiv   pre-print
We investigate on discovering and learning a set of mid-level patches to be used for representing the images of an object category.  ...  Visual Recognition is one of the fundamental challenges in AI, where the goal is to understand the semantics of visual data.  ...  Tracklets are formed by selecting regions (or points) of interest via a feature detector and by tracking them over a short period of time.  ... 
arXiv:1512.07314v1 fatcat:knmhkwxqk5aczis7ce6g2sv2wm