Saliency-Guided Attention Network for Image-Sentence Matching

International Conference on Computer Vision, pp. 5754-5763, 2019.

Cited by: 8|Bibtex|Views21|Links
EI

Abstract:

This paper studies the task of matching image and sentence, where learning appropriate representations across the multi-modal data appears to be the main challenge. Unlike previous approaches that predominantly deploy symmetrical architecture to represent both modalities, we propose Saliency-guided Attention Network (SAN) that asymmetrica...More

Code:

Data:

Your rating :
0

 

Tags
Comments