Retrieval-augmented Pseudo-image Guided Alignment and Text Domain-aware Memory Recall for Continual Zero-shot Captioning

Published in Feb 26, 2025

Recommended citation: Bing Liu, Wenjie Yang, Mingming Liu, Hao Liu, Yong Zhou, and Peng Liu. 2025. Syntactic-Conditional Diffusion Networks for Controllable Image Captioning. ACM Trans. Multimedia Comput. Commun. Appl. 21, 9, Article 259 (September 2025), 25 pages. https://doi.org/10.1145/3748653 https://ieeexplore.ieee.org/document/11359739