Journal
IEEE TRANSACTIONS ON IMAGE PROCESSING
Volume 27, Issue 11, Pages 5514-5524Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIP.2018.2855406
Keywords
Image captioning; attention; linear transformation; CNN; LSTM
Ask authors/readers for more resources
We propose a novel attention framework called attentive linear transformation (ALT) for automatic generation of image captions. Instead of learning the spatial or channel-wise attention in existing models, ALT learns to attend to the high-dimensional transformation matrix from the image feature space to the context vector space. Thus ALT can learn various relevant feature abstractions, including spatial attention, channel-wise attention, and visual dependence. Besides, we propose a soft threshold regression to predict the spatial attention probabilities. It preserves more relevant local regions than popular softmax regression. Extensive experiments on the MS COCO and the Flickr30k data sets all demonstrate the superiority of our model compared with other state-of-the-art models.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available