DistillCaps: Enhancing Audio-Language Alignment in Captioning via Retrieval-Augmented Knowledge Distillation.

@inproceedings{pham-2025-distillcaps, author = {Thinh Pham and Nghiem Tuong Diep and Lizi Liao and Binh T. Nguyen}, editor = {Meeyoung Cha and Carl Yang and Senjuti Basu Roy and Chanyoung Park and Zhenhui Jessie Li and Noseong Park and Carl Yang and Senjuti Basu Roy and Zhenhui Jessie Li and Jaap Kamps and Kijung Shin and Bryan Hooi and Lifang He}, title = {{DistillCaps: Enhancing Audio-Language Alignment in Captioning via Retrieval-Augmented Knowledge Distillation}}, booktitle = {{Proceedings of the 34th ACM International Conference on Information and Knowledge Management, CIKM 2025, Seoul, Republic of Korea, November 10-14, 2025}}, pages = {2346--2356}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3746252.3761269}, doi = {https://doi.org/10.1145/3746252.3761269} }