Chiori Hori Takaaki Hori Teng-Yok Lee Ziming Zhang Bret Harsham John R. Hershey Tim K. Marks Kazuhiro Sumi Attention-Based Multimodal Fusion for Video Description. 4203-4212 2017 ICCV https://doi.ieeecomputersociety.org/10.1109/ICCV.2017.450 conf/iccv/2017 db/conf/iccv/iccv2017.html#HoriHLZHHMS17