Alessandro Conti

zero-shot learning (3) image classification (2) vision language model (2) vision-language model (2) self-supervised learning (1) knowledge distillation (1) source-free domain adaptation (1) test-time adaptation (1) video understanding (1) fine-grained classification (1) semantic space (1) semantic similarity (1) large multimodal model (1) external database (1) large language-vision model (1) zero-shot classification (1) open vocabulary (1) temporal action localization (1) video action recognition (1) open-world classification (1)