LI, Yayuan; GUO, Jintao; QI, Lei; LI, Wenbin; SHI, Yinghuan. Text and Image Are Mutually Beneficial: Enhancing Training-Free Few-Shot Classification with CLIP. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 39, n. 5, p. 5039–5047, 2025. DOI: 10.1609/aaai.v39i5.32534. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/32534. Acesso em: 9 may. 2026.