4 papers
Improving Image-Based Nutrition Estimation Through Multimodal Food-Item Verification and Recovery
Jingbo Yue, Bruce Coburn, Jinge Ma +2
Single-image nutrition estimation can fail silently when visible foods are missed. Even when a food is correctly identified, its proposed region may not support portion estimation.…
Mitigating Performance Discrepancy in Cross-Domain 3D Class-Incremental Learning
Jinge Ma, Gautham Vinod, Bruce Coburn +3
3D perception plays a crucial role in real-world applications such as autonomous driving, robotics, and AR/VR. In practical scenarios, 3D perception models need to continually adap…
Food Image Segmentation with LLM-Derived Ingredient Labels and Multimodal Fusion
Jui-Feng Chi, Wei-Ta Chu, Sheng-Long Lin
Food image segmentation plays a vital role in health-related applications such as nutrition tracking and personalized health monitoring. However, existing models often underperform…
Fine-Grained Food Image Understanding via Target-Aware Data Alignment
Jui-Feng Chi, Wei-Lun Chu, Bruce Coburn +2
Fine-grained food visual--semantic understanding requires models to capture subtle distinctions across ingredients, cooking methods, doneness, color, texture, and plate composition…