The Work of Robert Moses? No, It’s Joe Macken.

A delivery truck driver from Queens created a scale model of New York City. After 10 million views on TikTok, his mini Gotham has moved to Museum Mile.
IEEE

Vision-Language Models for Vision Tasks: A Survey

Abstract: Most visual recognition studies rely heavily on crowd-labelled data in deep neural networks (DNNs) training, and they usually train a DNN for each single visual recognition task, leading to ...
IEEE

PromptKD: Unsupervised Prompt Distillation for Vision-Language Models

Abstract: Prompt learning has emerged as a valuable technique in enhancing vision-language models (VLMs) such as CLIP for downstream tasks in specific domains. Existing work mainly focuses on ...