Selected work

Representative Papers

HitoMi-Cam: A Shape-Agnostic Person Detection Method Using the Spectral Characteristics of Clothing

Nov 07, 2025Journal of Imaging

Conventional CNN-based person detection methods suffer significant performance degradation under pose variations or severe occlusion due to their inherent reliance on human shape priors. To address this limitation, we propose HitoMi-Cam—a lightweight, spectral reflectance–driven person detection method leveraging clothing’s intrinsic spectral signature rather than geometric shape. HitoMi-Cam pioneers shape-agnostic detection via spectral features and is the first such approach deployed and validated on real embedded hardware. By tightly integrating spectral imaging with edge-computing architecture, it achieves real-time inference at 23.2 fps on GPU-free, resource-constrained devices, with a mean average precision of 93.5%, outperforming state-of-the-art CNN baselines by up to 53.8 percentage points. Extensive experiments in simulated disaster search-and-rescue scenarios demonstrate its low false-positive rate and exceptional robustness to occlusion and pose variation. HitoMi-Cam thus serves as a complementary, reliable alternative to conventional vision-based detection systems in challenging operational environments.

0 citationsRead paper

Omics-scale polymer computational database transferable to real-world artificial intelligence applications

Nov 07, 2025

Polymer science has long suffered from a scarcity of large-scale, open-access data, hindering AI-driven innovation. Method: We introduce PolyOmics—the largest publicly available polymer molecular dynamics simulation database to date (>100,000 polymers)—generated via a fully automated high-throughput simulation pipeline and leveraged within a pretrain-fine-tune machine learning framework. We propose and empirically validate a “simulation-to-reality” transfer learning paradigm for polymer property prediction. Contribution/Results: Systematic experiments reveal a power-law scaling relationship between database size and model generalization performance, providing empirical support for data-driven scientific discovery. PolyOmics significantly improves prediction accuracy under low-data regimes, enabling robust property estimation with limited experimental samples. This advancement bridges the gap between academic AI research and industrial polymer development, facilitating rapid, data-informed materials design and accelerating translation into real-world applications.

0 citationsRead paper

Recent publications

Latest Papers

HitoMi-Cam: A Shape-Agnostic Person Detection Method Using the Spectral Characteristics of Clothing

Nov 07, 2025Journal of Imaging

Conventional CNN-based person detection methods suffer significant performance degradation under pose variations or severe occlusion due to their inherent reliance on human shape priors. To address this limitation, we propose HitoMi-Cam—a lightweight, spectral reflectance–driven person detection method leveraging clothing’s intrinsic spectral signature rather than geometric shape. HitoMi-Cam pioneers shape-agnostic detection via spectral features and is the first such approach deployed and validated on real embedded hardware. By tightly integrating spectral imaging with edge-computing architecture, it achieves real-time inference at 23.2 fps on GPU-free, resource-constrained devices, with a mean average precision of 93.5%, outperforming state-of-the-art CNN baselines by up to 53.8 percentage points. Extensive experiments in simulated disaster search-and-rescue scenarios demonstrate its low false-positive rate and exceptional robustness to occlusion and pose variation. HitoMi-Cam thus serves as a complementary, reliable alternative to conventional vision-based detection systems in challenging operational environments.

0 citationsRead paper

Omics-scale polymer computational database transferable to real-world artificial intelligence applications

Nov 07, 2025

Polymer science has long suffered from a scarcity of large-scale, open-access data, hindering AI-driven innovation. Method: We introduce PolyOmics—the largest publicly available polymer molecular dynamics simulation database to date (>100,000 polymers)—generated via a fully automated high-throughput simulation pipeline and leveraged within a pretrain-fine-tune machine learning framework. We propose and empirically validate a “simulation-to-reality” transfer learning paradigm for polymer property prediction. Contribution/Results: Systematic experiments reveal a power-law scaling relationship between database size and model generalization performance, providing empirical support for data-driven scientific discovery. PolyOmics significantly improves prediction accuracy under low-data regimes, enabling robust property estimation with limited experimental samples. This advancement bridges the gap between academic AI research and industrial polymer development, facilitating rapid, data-informed materials design and accelerating translation into real-world applications.

0 citationsRead paper