Visible-infrared person re-identification (VI Re-ID) aims to match person images between the
visible and infrared modalities. Existing VI Re-ID methods mainly focus on extracting
homogeneous structural relationships in an image, ie the relations between local features,
while ignoring the heterogeneous correlation of local features in different modalities. The
heterogeneous structured relationship is crucial to learn effective identity representations
and perform cross-modality matching. In this paper, we model the homogenous structural …

Visible-infrared person re-identification (VI Re-ID) aims to match person images between the
visible and infrared modalities. Existing VI Re-ID methods mainly focus on extracting
homogeneous structural relationships in an image, ie, the relations between local features,
while ignoring the heterogeneous correlation of local features in different modalities. The
heterogeneous structured relationship is crucial to learn effective identity representations
and perform cross-modality matching. In this paper, we introduce the Homogeneous …