3 papers
cs.CV2026
Skeleton-based Zero-Shot Spatio-Temporal Action Localization via Weakly-Supervised Pretraining
Koshiro Nagano, Fumiaki Sato, Ryo Hachiuma +2
We propose a novel pretraining strategy for skeleton-based zero-shot spatio-temporal action localization to estimate unseen actions for person instances while overcoming high annot…
cs.CV2026
Learning from Synthetic Data via Provenance-Based Input Gradient Guidance
Koshiro Nagano, Ryo Fujii, Ryo Hachiuma +3
Learning methods using synthetic data have attracted attention as an effective approach for increasing the diversity of training data while reducing collection costs, thereby impro…
cs.CL2024
Text2Traj2Text: Learning-by-Synthesis Framework for Contextual Captioning of Human Movement Trajectories
Hikaru Asano, Ryo Yonetani, Taiki Sekii +1
This paper presents Text2Traj2Text, a novel learning-by-synthesis framework for captioning possible contexts behind shopper's trajectory data in retail stores. Our work will impact…