We present a higher-level visual representation, visual synset, for object categorization. The visual synset improves the traditional bag of words representation with better discr...
Yantao Zheng, Ming Zhao 0003, Shi-Yong Neo, Tat-Se...
We investigate whether dimensionality reduction using a latent generative model is beneficial for the task of weakly supervised scene classification. In detail we are given a set ...
Recently the "bag of words" model becomes popular in the approaches to object recognition. These approaches model an image as a collection of local patches called "...
Many modern visual recognition algorithms incorporate a step of spatial `pooling', where the outputs of several nearby feature detectors are combined into a local or global `...
Sub-image search with high accuracy in natural images still remains a challenging problem. This paper proposes a new feature vector called profile for a keypoint in a bag of visual...