Picture for Lun Huang

Lun Huang

GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions

Add code
Apr 30, 2021
Figure 1 for GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions
Figure 2 for GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions
Figure 3 for GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions
Figure 4 for GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions
Viaarxiv icon

Adaptively Aligned Image Captioning via Adaptive Attention Time

Add code
Nov 01, 2019
Figure 1 for Adaptively Aligned Image Captioning via Adaptive Attention Time
Figure 2 for Adaptively Aligned Image Captioning via Adaptive Attention Time
Figure 3 for Adaptively Aligned Image Captioning via Adaptive Attention Time
Figure 4 for Adaptively Aligned Image Captioning via Adaptive Attention Time
Viaarxiv icon

Attention on Attention for Image Captioning

Add code
Aug 21, 2019
Figure 1 for Attention on Attention for Image Captioning
Figure 2 for Attention on Attention for Image Captioning
Figure 3 for Attention on Attention for Image Captioning
Figure 4 for Attention on Attention for Image Captioning
Viaarxiv icon

ParNet: Position-aware Aggregated Relation Network for Image-Text matching

Add code
Jun 17, 2019
Figure 1 for ParNet: Position-aware Aggregated Relation Network for Image-Text matching
Figure 2 for ParNet: Position-aware Aggregated Relation Network for Image-Text matching
Figure 3 for ParNet: Position-aware Aggregated Relation Network for Image-Text matching
Figure 4 for ParNet: Position-aware Aggregated Relation Network for Image-Text matching
Viaarxiv icon