Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
Left-Right Symmetry Breaking in CLIP-style Vision-Language Models Trained on Synthetic Spatial-Relation Data
Takaki Yamamoto, Chihiro Noguchi, Toshihiro Tanizawa
Spatial understanding remains a key challenge in vision-language models. Yet it is still unclear whether such understanding is truly acquired, and if so, through what mechanisms. W…
cs.CV2025
From Binary to Semantic: Utilizing Large-Scale Binary Occupancy Data for 3D Semantic Occupancy Prediction
Chihiro Noguchi, Takaki Yamamoto
Accurate perception of the surrounding environment is essential for safe autonomous driving. 3D occupancy prediction, which estimates detailed 3D structures of roads, buildings, an…
cs.CV2024
Text Image Generation for Low-Resource Languages with Dual Translation Learning
Chihiro Noguchi, Shun Fukuda, Shoichiro Mihara +1
Scene text recognition in low-resource languages frequently faces challenges due to the limited availability of training datasets derived from real-world scenes. This study propose…