no code implementations • 3 Dec 2020 • Jing Su, Qingyun Dai, Frank Guerin, Mian Zhou
Visual storytelling is a creative and challenging task, aiming to automatically generate a story-like description for a sequence of images.
Ranked #21 on Visual Storytelling on VIST (CIDEr metric)
no code implementations • 2 Dec 2020 • Jing Su, Chenghua Lin, Mian Zhou, Qingyun Dai, Haoyu Lv
In this paper, we propose an end-to-end CNN-LSTM model for generating descriptions for sequential images with a local-object attention mechanism.