1 code implementation • 1 Dec 2021 • Kai Zhang, Yifan Sun, Rui Wang, Haichang Li, Xiaohui Hu
MFA basically considers three parallel information fusion strategies, i. e., the cross-model fusion, temporal fusion and a novel online-offline pseudo label fusion.
no code implementations • 17 Sep 2021 • Zheng Lian, Yanan Zhang, Haichang Li, Rui Wang, Xiaohui Hu
The conventional encoder-decoder framework for image captioning generally adopts a single-pass decoding process, which predicts the target descriptive sentence word by word in temporal order.