Visual Clues: Bridging Vision and Language Foundations for Image Paragraph Captioning

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.Preprint. Under review.

Vision-Language Pre-training: Basics, Recent Advances, and Future Trends

“…MAGIC (Su et al, 2022) uses a CLIP-induced score to regularize the language generation of GPT-2 so that the zeroshot generated caption is semantically related to the given image. BEST (Xie et al, 2022) uses the cooperation of Florence (Yuan et al, 2021) and GPT-3 for visual storytelling and image paragraph captioning. Wang et al (2022j) propose the cooperation of CLIP, BLIP (Li et al, 2022f), and GPT-3 for few-shot video-language learning.…”