Sciweavers

Share

Publication

Person Re-Identification: What Features are Important?

8 years 8 months ago
Person Re-Identification: What Features are Important?
State-of-the-art person re-identi cation methods seek robust person matching through combining various feature types. Often, these features are implicitly assigned with a single vector of global weights, which are assumed to be universally good for all individuals, independent to their di erent appearances. In this study, we show that certain features play more important role than others under di erent circumstances. Consequently, we propose a novel unsupervised approach for learning a bottom-up feature importance, so features extracted from different individuals are weighted adaptively driven by their unique and inherent appearance attributes. Extensive experiments on two public datasets demonstrate that attribute-sensitive feature importance facilitates more accurate person matching when it is fused together with global weights obtained using existing methods.
Chunxiao Liu, Shaogang Gong, Chen Change Loy, Xing
Added 02 Oct 2012
Updated 02 Oct 2012
Type Conference
Year 2012
Where ECCV, International Workshop on Re-Identification
Authors Chunxiao Liu, Shaogang Gong, Chen Change Loy, Xinggang Lin
Comments (0)
books