Visualization;Semantics;Zero Shot Learning;Videos;Grounding;Vectors;Object Detection;Feature Extraction;Training;Iterative Methods;Food Computing;Zero-Shot Learning;Zero-Shot Detection;Cross-Modal Fusion;Food Detection

SyMFood: Synergistic Multi-Modal Prompting for Fine-Grained Zero-Shot Food Detection
Fine-grained object detection in food computing is severely constrained by the vast diversity of food items and the high cost of data …
PDF 引用 代码 DOI