Jiaxuan-Li/EVCap

[CVPR 2024] Retrieval-Augmented Image Captioning with External Visual-Name Memory for Open-World Comprehension

28
/ 100
Experimental

This helps generate accurate and detailed descriptions for images, even if they contain new or unusual objects. You provide an image, and it outputs a textual caption that intelligently incorporates knowledge of various visual elements. This is useful for content creators, digital archivists, or anyone needing to automatically describe diverse visual content.

No commits in the last 6 months.

Use this if you need to automatically generate precise and current descriptions for a wide variety of images, including those with objects or scenes not commonly found in standard datasets.

Not ideal if you require descriptions for images where the visual content is highly abstract or does not correspond to common real-world objects and concepts.

image-description visual-content-analysis digital-asset-management accessibility-enhancement
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 12 / 25

How are scores calculated?

Stars

62

Forks

7

Language

Python

License

Last pushed

Apr 08, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Jiaxuan-Li/EVCap"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.