Visual Clues: Bridging Vision and Language Foundations for Image Paragraph CaptioningDownload PDF

Published: 31 Oct 2022, 18:00, Last Modified: 17 Dec 2022, 04:19NeurIPS 2022 AcceptReaders: Everyone
Keywords: Image paragraph captioning, vision-language models, zero-shot learning
TL;DR: We use textual image description to bridge large pretrained vision foundation models and language models, so that we can generate detailed and coherent image description without any extra training.
Abstract: People say, "A picture is worth a thousand words". Then how can we get the rich information out of the image? We argue that by using visual clues to bridge large pretrained vision foundation models and language models, we can do so without any extra cross-modal training. Thanks to the strong zero-shot capability of foundation models, we start by constructing a rich semantic representation of the image (e.g., image tags, object attributes / locations, captions) as a structured textual prompt, called visual clues, using a vision foundation model. Based on visual clues, we use large language model to produce a series of comprehensive descriptions for the visual content, which is then verified by the vision model again to select the candidate that aligns best with the image. We evaluate the quality of generated descriptions by quantitative and qualitative measurement. The results demonstrate the effectiveness of such a structured semantic representation.
Supplementary Material: zip
20 Replies

Loading