Pose-guided Inter- and Intra-part Relational Transformer for Occluded Person Re-Identification
This addresses the problem of identifying partially occluded pedestrians in surveillance, which is an incremental improvement over existing methods.
The paper tackles person re-identification in occlusion scenarios by proposing a pose-guided transformer model that builds part-aware long-term correlations, achieving state-of-the-art results on a public occluded dataset and competitive performance on standard datasets.
Person Re-Identification (Re-Id) in occlusion scenarios is a challenging problem because a pedestrian can be partially occluded. The use of local information for feature extraction and matching is still necessary. Therefore, we propose a Pose-guided inter-and intra-part relational transformer (Pirt) for occluded person Re-Id, which builds part-aware long-term correlations by introducing transformers. In our framework, we firstly develop a pose-guided feature extraction module with regional grouping and mask construction for robust feature representations. The positions of a pedestrian in the image under surveillance scenarios are relatively fixed, hence we propose an intra-part and inter-part relational transformer. The intra-part module creates local relations with mask-guided features, while the inter-part relationship builds correlations with transformers, to develop cross relationships between part nodes. With the collaborative learning inter- and intra-part relationships, experiments reveal that our proposed Pirt model achieves a new state of the art on the public occluded dataset, and further extensions on standard non-occluded person Re-Id datasets also reveal our comparable performances.