Structural Semantic Adversarial Active Learning for Image Captioning
MM '20: The 28th ACM International Conference on Multimedia Seattle WA USA October, 2020, pp. 1112-1121, 2020.
Most image captioning models achieve superior performances with the help of large-scale surprised training data, but it is prohibitively costly to label the image captions. To solve this problem, we propose a structural semantic adversarial active learning (SSAAL) model that leverages both visual and textual information for deriving the m...More
PPT (Upload PPT)