Risa Shinoda

vision-language model (2) semantic segmentation (2) zero-shot learning (1) action recognition (1) object detection (1) instance segmentation (1) fine-grained classification (1) synthetic data generation (1) interaction detection (1) foundation model (1) domain-specific evaluation (1) wildlife monitoring (1) species identification (1) limited labeled datum (1) formula-driven supervised learning (1) hierarchical segmentation (1) cattle behavior (1) agricultural task (1) crop disease (1) fine-grained identification (1)