Low-Rank HOCA: Efficient High-Order Cross-Modal Attention for Video Captioning

Add code
Nov 01, 2019
Figure 1 for Low-Rank HOCA: Efficient High-Order Cross-Modal Attention for Video Captioning
Figure 2 for Low-Rank HOCA: Efficient High-Order Cross-Modal Attention for Video Captioning
Figure 3 for Low-Rank HOCA: Efficient High-Order Cross-Modal Attention for Video Captioning
Figure 4 for Low-Rank HOCA: Efficient High-Order Cross-Modal Attention for Video Captioning

Share this with someone who'll enjoy it:

View paper onarxiv icon

Share this with someone who'll enjoy it: