1. Bottom-up and top-down attention for image captioning and visual question answering;Anderson,2018
2. Microsoft coco: Common objects in context;Lin,2014
3. Face it: Instagram pictures with faces are more popular, https://www.news.gatech.edu/2014/03/20/face-it-instagram-pictures-faces-are-more-popular(2014).
4. A survey and analysis on automatic image annotation;Cheng;Pattern Recognit,2018
5. Learning visual relationship and context-aware attention for image captioning;Wang;Pattern Recognit,2020