no code implementations • 28 Feb 2022 • Koya Tango, Takehiko Ohkawa, Ryosuke Furuta, Yoichi Sato
Detecting the positions of human hands and objects-in-contact (hand-object detection) in each video frame is vital for understanding human activities from videos.
1 code implementation • 26 Aug 2020 • Koya Tango, Marie Katsurai, Hayato Maki, Ryosuke Goto
To solve this problem, our method starts by collecting and preprocessing web images to prepare a cleaned, paired dataset of the anime and real domains.