A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2016; you can also visit the original URL.
The file type is application/pdf
.
Pyramid Coding for Functional Scene Element Recognition in Video Scenes
2013
2013 IEEE International Conference on Computer Vision
Recognizing functional scene eleme based on the behaviors of moving o with them is an emerging problem of approaches have a limited ability to ch such as cross-walks, intersections, and low activity, are multi-modal, or have Our approach recognizes the low activ elements (crosswalks/intersections) hierarchy of descriptive clusters to f codebooks that is sparse in the numb dense in content. The incorporation o context such as person-enter-building a nearby enables the detection of elemen direct
doi:10.1109/iccv.2013.50
dblp:conf/iccv/SwearsHB13
fatcat:hqwff7t3infxdldbzu3ctu5y54