Masashi Nishiyama
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Masashi Nishiyama has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
Michiko Inoue
6 shared publicationsYoshio Iwai
Tottori University
6 shared publications- Yoshio Iwai
Tottori University
5 shared publications Fuyuko Iwasaki
Tottori University
3 shared publicationsShota Hioki
3 shared publications- Carlos David Ardon Munoz
Tottori University
2 shared publications
Latest Publications
- 26 June 2026
- Published by Springer Nature
- p. 318-332
Investigating Temporal Changes of Impression Formed by Interviewers from the Applicant’s Behavior
- 26 June 2026
- Published by Springer Nature
- p. 318-332
Investigating Temporal Changes of Impression Formed by Interviewers from the Applicant’s Behavior
- Open Access
- 19 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 146492-146502
Pedestrian Age Recognition Using Contrastive Learning by Automatically Generating Descriptions With High Inter-Class Separability
There is a need to accurately recognize pedestrian age classes from whole-body images with minimal manual effort. Recent studies have improved age recognition accuracy by exploiting vision–language models (VLMs). However, the age-description texts provided to the VLM are not designed to be sufficiently discriminative across age classes. Moreover, preparing these texts entails considerable manual work. We address these issues by automatically generating detailed, class-specific age-description texts that are highly separable among age classes and using them in a contrastive learning framework. Our method expands the vocabulary of physical and adhered-human characteristics that represent each age class, thereby sharpening inter-class separability. Leveraging a VLM-powered visual question answering (VQA) module, our approach produces detailed age-description texts from concise question texts without the need for trial and error. The age-description texts yield strongly discriminative textual features, which also align discriminative visual features by contrastive learning. Experimental results on public datasets (RAPv2.0, PETA, MSP60k, and PA100k) show that our method markedly outperforms existing methods in age recognition accuracy. We also confirmed that our method eliminates the trial and error of manually crafting age-description texts.
- 19 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 146492-146502
Open AccessPedestrian Age Recognition Using Contrastive Learning by Automatically Generating Descriptions With High Inter-Class Separability
There is a need to accurately recognize pedestrian age classes from whole-body images with minimal manual effort. Recent studies have improved age recognition accuracy by exploiting vision–language models (VLMs). However, the age-description texts provided to the VLM are not designed to be sufficiently discriminative across age classes. Moreover, preparing these texts entails considerable manual work. We address these issues by automatically generating detailed, class-specific age-description texts that are highly separable among age classes and using them in a contrastive learning framework. Our method expands the vocabulary of physical and adhered-human characteristics that represent each age class, thereby sharpening inter-class separability. Leveraging a VLM-powered visual question answering (VQA) module, our approach produces detailed age-description texts from concise question texts without the need for trial and error. The age-description texts yield strongly discriminative textual features, which also align discriminative visual features by contrastive learning. Experimental results on public datasets (RAPv2.0, PETA, MSP60k, and PA100k) show that our method markedly outperforms existing methods in age recognition accuracy. We also confirmed that our method eliminates the trial and error of manually crafting age-description texts.
- 25 May 2025
- Published by Springer Nature
- p. 185-199
First Impression Assessment of Digital Human Applicant Images Generated with Posture Prompts and Text Prompts
- 25 May 2025
- Published by Springer Nature
- p. 185-199
First Impression Assessment of Digital Human Applicant Images Generated with Posture Prompts and Text Prompts
- 6 April 2025
- Published by Elsevier in Pattern Recognition Letters
- Vol. 192, 106-112
Robust pixel-wise detection of road obstacles by integrating composite and real images
- 6 April 2025
- Published by Elsevier in Pattern Recognition Letters
- Vol. 192, 106-112
Robust pixel-wise detection of road obstacles by integrating composite and real images
- 2 December 2024
- Published by Springer Nature
- p. 359-374
Conversation Activity Recognition Using Interaction Video Sequences in Pedestrian Groups
- 2 December 2024
- Published by Springer Nature
- p. 359-374
Conversation Activity Recognition Using Interaction Video Sequences in Pedestrian Groups
- Open Access
- 4 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 39484-39494
Canonical Plane Segmentation Without Annotating Pixel-Level Object Regions for Image Registration
Two-dimensional (2D) image registration is a natural choice for simultaneous object pose estimation and object recognition. However, it was not designed to perform object segmentation, which is critical for object-picking applications in warehouse automation scenarios. In this study, we propose a unified 2D image registration framework that simultaneously performs image registration and object segmentation by introducing a deep segmentation network module to the 2D image registration framework. Our method is designed to automatically generate annotations for training the segmentation network module through the process of 2D image registration, that is, no additional manual annotations are required. Specifically, given initial object regions from the 2D image registration results, our method trains the segmentation network module to refine a pseudo-pixel-level object region and remove background pixels based on the pixel-level similarity of an aligned image pair. The experimental results on several picking object datasets demonstrated that the segmentation accuracy of our method was superior to that of existing weakly supervised segmentation methods, and our method simultaneously achieved better performance for object recognition and pose estimation. Furthermore, our segmentation network module smoothly cooperated with many existing 2D image registration techniques.
- 4 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 39484-39494
Open AccessCanonical Plane Segmentation Without Annotating Pixel-Level Object Regions for Image Registration
Two-dimensional (2D) image registration is a natural choice for simultaneous object pose estimation and object recognition. However, it was not designed to perform object segmentation, which is critical for object-picking applications in warehouse automation scenarios. In this study, we propose a unified 2D image registration framework that simultaneously performs image registration and object segmentation by introducing a deep segmentation network module to the 2D image registration framework. Our method is designed to automatically generate annotations for training the segmentation network module through the process of 2D image registration, that is, no additional manual annotations are required. Specifically, given initial object regions from the 2D image registration results, our method trains the segmentation network module to refine a pseudo-pixel-level object region and remove background pixels based on the pixel-level similarity of an aligned image pair. The experimental results on several picking object datasets demonstrated that the segmentation accuracy of our method was superior to that of existing weakly supervised segmentation methods, and our method simultaneously achieved better performance for object recognition and pose estimation. Furthermore, our segmentation network module smoothly cooperated with many existing 2D image registration techniques.