Výsledky vyhledávání

Gender Recognition Using a Gaze-Guided Self-Attention Mechanism Robust Against Background Bias in Training Samples

Autor: Masashi NISHIYAMA, Michiko INOUE, Yoshio IWAI

Publikováno v: Nishiyama Masashi, Inoue Michiko, Iwai Yoshio, et al. Gender Recognition Using a Gaze-Guided Self-Attention Mechanism Robust Against Background Bias in Training Samples. IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS. 2022. E105D(2). 415-426. doi:10.1587/t

We propose an attention mechanism in deep learning networks for gender recognition using the gaze distribution of human observers when they judge the gender of people in pedestrian images. Prevalent attention mechanisms spatially compute the correlat

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::06e3eeb19dda0a1399de046d662863f1
http://repository.lib.tottori-u.ac.jp/13736

Zobrazit plný text záznamu

Joint object recognition and pose estimation using multiple-anchor triplet learning of canonical plane

Autor: Masashi Nishiyama, Go Irie, Yoshio Iwai, Shunsuke Yoneda, Kouki Ueno

Publikováno v: Pattern Recognition Letters. 152:372-381

Accurate object recognition and pose estimation models are essential for practical applications of robot arms, such as picking products on a shelf. Training such a model often requires a large-scale dataset with qualified labels for both object class

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::2e422212be87653b3770f84571fb952a
https://doi.org/10.1016/j.patrec.2021.11.005

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání