Author

Koichi Ito

h-index 22 View on Semantic Scholar

We have 3 of 237 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Conference Open access Sep 2026

MARS-CLIP: Multi-Resolution and Attention Refined Zero-Shot Image Segmentation

Contrastive Language-Image Pre-training (CLIP) has demonstrated impressive capabilities in zero-shot transfer but often struggles with dense prediction tasks due to low spatial resolution and the loss of structural information. To address these limitations, we propose MARS-CLIP (Multi-resolution and Attention Refined S...

Nagito Saito, Shintaro Ito, Koichi Ito et al. · International Conference on... · 0 citations

Jul 2026

MAGE-Vein: Multi-Instance Age and Gender Estimation from Finger Vein Images

The proposed MAGE-Vein approaches extracts robust structural aging signs by employing a hybrid feature-level fusion of three fingers, effectively suppressing local imaging noise and simultaneous optimization of gender classification conditions the network to effectively eliminate gender-specific vascular variations.

Katsuki Tanaka, Koichi Ito, T. Aoki et al. · arXiv.org · 0 citations

Jul 2026

DINO-VPT: Hierarchical Visual Prompt Tuning for Joint Physical-Digital Face Anti-Spoofing

The results indicate that a properly structured vision-only architecture can achieve state-of-the-art performance in unified FAS without the need for multimodal supervision.

Pierre Gallin-Martel, Mika Feng, Koichi Ito et al. · arXiv.org · 0 citations