A relation network design for visible thermal person re-identification

A Survey on Thermal to Visual Cross Domain Face Recognition

“…Deep learning based methods are proposed in [103], [104] For matching visual and thermal face images, Chen et al [67] developed the high-frequency representation (HFR) framework, which matches images using multiple subspaces generated from patches. In the context of modality discrepancies, Ye et al [58] introduced the MACE learning method, which focuses on learning discriminative middle-level features and addresses the differences between modalities in features and classifiers [29], [58].…”

“…In [103], Introduce an RN-VTReID for visible-thermal person re-identification and employ a combination of Global Average Pooling (GAP) and Global Max Pooling (GMP) to extract pedestrian background and texture features.…”

“…In [103], Introduce an RN-VTReID for visible-thermal person re-identification and employ a combination of Global Average Pooling (GAP) and Global Max Pooling (GMP) to extract pedestrian background and texture features. In Wu et al's work [122], they introduced a Feature Aggregation Module (FAM) to improve the correlation among local features, including spatial and channel dependencies.…”