Features B4 Van-Quang Nguyen1 , Masanori Suganuma2,1 , and Takayuki Okatani1,2 1Graduate School of Information Sciences, Tohoku University 2RIKEN Center for AIP ECCV2022 Nguyen, V. Q., Suganuma, M., & Okatani, T. (2022, October). Grit: Faster and beCer image capEoning transformer using dual visual features. In ECCV (pp. 167-184).