DistillCaps: Enhancing Audio-Language Alignment in Captioning via Retrieval-Augmented Knowledge Distillation.
Thinh Pham, Nghiem Tuong Diep, Lizi Liao, Binh T. Nguyen
Browse the full CIKM paper archive.
Thinh Pham, Nghiem Tuong Diep, Lizi Liao, Binh T. Nguyen
Browse the full CIKM paper archive.