The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18) 2017

Co-attending Regions and Detections with Multi-modal Multiplicative Embedding for VQA

The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18) 2017 lupantech/dual-mfa-vqa

Existing VQA methods mainly adopt the visual attention mechanism to associate the input question with corresponding image regions for effective question answering.

QUESTION ANSWERING VISUAL QUESTION ANSWERING