4 papers
Learning Multi-Modal Prototypes for Cross-Domain Few-Shot Object Detection
Wanqi Wang, Jingcai Guo, Yuxiang Cai +1
Cross-Domain Few-Shot Object Detection (CD-FSOD) aims to detect novel classes in unseen target domains given only a few labeled examples. While open-vocabulary detectors built on v…
SRSUPM: Sequential Recommender System Based on User Psychological Motivation
Yicheng Di, Yuan Liu, Zhi Chen +1
Sequential recommender infers users' evolving psychological motivations from historical interactions to recommend the next preferred items. Most existing methods compress recent be…
Fine-Grained Zero-Shot Learning with Attribute-Centric Representations
Zhi Chen, Jingcai Guo, Taotao Cai +1
Recognizing unseen fine-grained categories demands a model that can distinguish subtle visual differences. This is typically achieved by transferring visual-attribute relationships…
On the Discrimination and Consistency for Exemplar-Free Class Incremental Learning
Tianqi Wang, Jingcai Guo, Depeng Li +1
Exemplar-free class incremental learning (EF-CIL) is a nontrivial task that requires continuously enriching model capability with new classes while maintaining previously learned k…