What is the Spatial Extent of an Object?

This paper discusses the question: Can we improve the recognition of objects by using their spatial context? We start from Bag-of-Words models and use the Pascal 2007 dataset. We use the rough object bounding boxes that come with this dataset to investigate the fundamental gain con- text can bring. Our main contributions are: (I) The result of Zhang et al. in CVPR07 that context is superfluous de- rived from the Pascal 2005 data set of 4 classes does not generalize to this dataset. For our larger and more realistic dataset context is important indeed. (II) Using the rough bounding box to limit or extend the scope of an object dur- ing both training and testing, we find that the spatial extent of an object is determined by its category: (a) well-defined, rigid objects have the object itself as the preferred spatial extent. (b) Non-rigid objects have an unbounded spatial ex- tent: all spatial extents produce equally good results. © Objects primarily categorised based on their function h...

• Type: Conference
• Year: 2009
• Where: CVPR
• Authors: Arnold W. M. Smeulders, Jasper R. R. Uijlings, Remko J. H. Scha
• Keywords: Bag Of Words, Computer Vision, CVPR 2009, Object Recognition, Spatial Extent