2 papers
cs.CV2026
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…
cs.CV2025
MVA 2025 Small Multi-Object Tracking for Spotting Birds Challenge: Dataset, Methods, and Results
Yuki Kondo, Norimichi Ukita, Riku Kanayama +21
Small Multi-Object Tracking (SMOT) is particularly challenging when targets occupy only a few dozen pixels, rendering detection and appearance-based association unreliable. Buildin…