Picture for Kosuke Shingyouchi

Kosuke Shingyouchi

LatteGAN: Visually Guided Language Attention for Multi-Turn Text-Conditioned Image Manipulation

Add code
Dec 28, 2021
Figure 1 for LatteGAN: Visually Guided Language Attention for Multi-Turn Text-Conditioned Image Manipulation
Figure 2 for LatteGAN: Visually Guided Language Attention for Multi-Turn Text-Conditioned Image Manipulation
Figure 3 for LatteGAN: Visually Guided Language Attention for Multi-Turn Text-Conditioned Image Manipulation
Figure 4 for LatteGAN: Visually Guided Language Attention for Multi-Turn Text-Conditioned Image Manipulation
Viaarxiv icon

Unified Questioner Transformer for Descriptive Question Generation in Goal-Oriented Visual Dialogue

Add code
Jun 29, 2021
Figure 1 for Unified Questioner Transformer for Descriptive Question Generation in Goal-Oriented Visual Dialogue
Figure 2 for Unified Questioner Transformer for Descriptive Question Generation in Goal-Oriented Visual Dialogue
Figure 3 for Unified Questioner Transformer for Descriptive Question Generation in Goal-Oriented Visual Dialogue
Figure 4 for Unified Questioner Transformer for Descriptive Question Generation in Goal-Oriented Visual Dialogue
Viaarxiv icon