Abstract | ||
---|---|---|
We propose a novel approach to both learning and detecting local contour-based representations for mid-level features. Our features, called sketch tokens, are learned using supervised mid-level information in the form of hand drawn contours in images. Patches of human generated contours are clustered to form sketch token classes and a random forest classifier is used for efficient detection in novel images. We demonstrate our approach on both top-down and bottom-up tasks. We show state-of-the-art results on the top-down task of contour detection while being over 200x faster than competing methods. We also achieve large improvements in detection accuracy for the bottom-up tasks of pedestrian and object detection as measured on INRIA and PASCAL, respectively. These gains are due to the complementary information provided by sketch tokens to low-level features such as gradient histograms. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/CVPR.2013.406 | CVPR |
Keywords | Field | DocType |
feature extraction,image classification,image representation,learning (artificial intelligence),object detection,pattern clustering,pedestrians,trees (mathematics),INRIA,PASCAL,bottom-up task,contour detection,gradient histograms,hand drawn contours,human generated contour clustering,learned midlevel representation,local contour-based representation,low-level features,midlevel features,object detection,pedestrian detection,random forest classifier,sketch tokens,supervised midlevel information,top-down task | Computer vision,Object detection,Viola–Jones object detection framework,Feature detection (computer vision),Object-class detection,Pattern recognition,Computer science,Feature extraction,Artificial intelligence,Contextual image classification,Random forest,Sketch | Conference |
Volume | Issue | ISSN |
2013 | 1 | 1063-6919 |
Citations | PageRank | References |
157 | 9.29 | 0 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Joseph J. Lim | 1 | 901 | 51.86 |
C. Lawrence Zitnick | 2 | 7321 | 332.72 |
Piotr Dollár | 3 | 7999 | 307.07 |