Hierarchical semantic compactness and proxy sparsity learning with event inversion for event person re-identification

Wanzhang Chen, Jun Kong, Min Jiang, Xuefeng Tao

Abstract: Event-based person re-identification (Event ReId) is an emerging research field that aims to distinguish individuals in non-overlapping event camera domains. Existing works achieve considerable performance by perceiving single-level semantic similarities. However, these methods often overlook multilevel semantic similarities and differences, leading to semantic non-compactness and proxy non-sparsity within the embedding space. Moreover, the implicit fine-grained information hidden in event representations is not effectively explored. To address these issues, we propose hierarchical semantic compactness and proxy sparsity learning with event inversion for event-based person re-identification. First, the hierarchical semantic compactness learning module is proposed to perceive semantic similarities at multi-level. Specifically, this module explores the semantic relationships between instances and global proxies through the application of proxy-level semantic awareness and instance-level semantic awareness losses. Second, the local proxy sparsity learning module is proposed to ensure the sparsity of local proxies, thereby exploring the semantic differences among local proxies. Third, we incorporate an event inversion model to further exploit fine-grained texture information from events. Finally, the excellent experiment result, with an improvement of 16.8% in mAP and 11.3% in Rank 1 accuracy on the Event-ReId dataset, highlighting the superiority of our model.