Look Wide and Interpret Twice: Improving Performance on Interactive Instruction-following Tasks

Aug 1, 2021·

Van-Quang Nguyen

,

Masanori Suganuma

,

Takayuki Okatani

· 0 min read

Authors

Van-Quang Nguyen

Postdoc Researcher, RIKEN AIP

---

← GRIT: Faster and Better Image Captioning Transformer Using Dual Visual Features Oct 1, 2022

Efficient Attention Mechanism for Visual Dialog that can Handle All the Interactions between Multiple Inputs Aug 1, 2020 →