Cross-modal person re-identification between visible and infrared domains remains a challenging problem due to significant modality gaps. This paper presents a novel approach termed Intermediate Shared Feature Network (ISFNet) that explicitly addresses this issue by exploiting intermediate feature representations withi...
Aobo Fan, Wangmeng Wang, Zhixin Tie et al.· Electronics· 0 citations
This work discovers persona-centric metamorphic relations to infer test samples from annotated data, without additional annotation cost, and evaluates the robustness of personalized dialogue models regarding persona consistency, revealing that prompt learning is more robust than training from scratch and fine-tuning.
Lin Li, Xiaohua Wu, Yanbing Chen et al.· Cognitive Computation· 0 citations
DMFNet (Diverse Mid-feature Network) is presented, a novel deep learning architecture that effectively harnesses intermediate shared features to bridge this cross-modal gap and enhances cross-modal matching capabilities but also provides interpretable feature visualizations, offering valuable insights into the network'...