14. 计算机视觉应用
10 计算机视觉应用 V3
非常有趣的用到注意力机制的计算机视觉应用:
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention [pdf]
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering [pdf]
Video Paragraph Captioning Using Hierarchical Recurrent Neural Networks [pdf]
Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos [pdf]
Tips and Tricks for Visual Question Answering: Learnings from the 2017 Challenge [pdf]
Visual Question Answering: A Survey of Methods and Datasets [pdf]