no code implementations • ECCV 2020 • Sho Inayoshi, Keita Otani, Antonio Tejero-de-Pablos, Tatsuya Harada
In this paper, we propose the bounding-box channels, a novel architecture capable of relating the semantic, spatial, and image features strongly.
no code implementations • 4 Apr 2024 • Sho Inayoshi, Aji Resindra Widya, Satoshi Ozaki, Junji Otsuka, Takeshi Ohashi
Model pre-training has become essential in various recognition tasks.
no code implementations • CVPR 2019 • Atsushi Kanehira, Kentaro Takemoto, Sho Inayoshi, Tatsuya Harada
This study addresses generating counterfactual explanations with multimodal information.