This is the authors' abstract. We don't add key points for this paper.
In this paper, we propose an efficient image representation strategy for addressing the task of small-scale person re-identification. Taking advantages of being compact and intuitively understandable, we adopt color names descriptor (CND) as our color feature. To solve the inaccuracy by comparing color names with image pixels in Euclidean space, we propose a new approach – soft Gaussian mapping (SGM), which uses a Gaussian model to bridge their semantic gap. We further present a cross-view coupling learning method to build a common subspace where the learned features can contain the transition information among different cameras. Experiments on the challenging small-scale benchmark public datasets demonstrate the effectiveness of our proposed method.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Yang et al. (2019) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: