Attend What You Need: Motion-Appearance Synergistic Networks for Video Question Answering ACL IJCNLP

Ahjeong Seo | Gi-Cheon Kang | Joonhan Park | Byoung-Tak Zhang |

Reasoning Visual Dialog with Sparse Graph Learning and Knowledge Transfer EMNLP Findings

Gi-Cheon Kang | Junseok Park | Hwaran Lee | Byoung-Tak Zhang | Jin-Hwa Kim |