Authors
Lingqiao Liu, Lei Wang, Xinwang Liu
Publication date
2011/11/6
Conference
2011 International Conference on Computer Vision
Pages
2486-2493
Publisher
IEEE
Description
In object recognition, soft-assignment coding enjoys computational efficiency and conceptual simplicity. However, its classification performance is inferior to the newly developed sparse or local coding schemes. It would be highly desirable if its classification performance could become comparable to the state-of-the-art, leading to a coding scheme which perfectly combines computational efficiency and classification performance. To achieve this, we revisit soft-assignment coding from two key aspects: classification performance and probabilistic interpretation. For the first aspect, we argue that the inferiority of soft-assignment coding is due to its neglect of the underlying manifold structure of local features. To remedy this, we propose a simple modification to localize the soft-assignment coding, which surprisingly achieves comparable or even better performance than existing sparse or local coding schemes while …
Total citations
Scholar articles
L Liu, L Wang, X Liu - 2011 International Conference on Computer Vision, 2011