Contextual decomposition of multi-label images

Most research on image decomposition, e.g. image segmentation and image parsing, has predominantly focused on the low-level visual clues within single image and neglected the contextual information across different images. In this paper, we present a new perspective to image decomposition piloted by the multi-labels associated with individual images. Observing that the context information (i.e., local label representations of the same label are similar while those from different labels are dissimilar) exists across different images, we propose to perform image decomposition in a collective way, and then the image decomposition problem is formulated as an optimization which maximizes inter-label difference and at the same time minimizes intralabel difference of the target label representations. Such contextual image decomposition has a wide variety of applications, among which the two exemplary ones are: 1) multi-label image annotation in which the sparse coding of a query image over t...

• Type: Conference
• Year: 2009
• Where: CVPR
• Authors: Teng Li, Tao Mei, Shuicheng Yan, In-So Kweon, Chil-Woo Lee
• Keywords: Computer Vision, CVPR 2009, Image Decomposition, Label Representations, Sparse Coding