Summary of An Archaeological Catalog Collection Method Based on Large Vision-language Models, by Honglin Pang et al.
An archaeological Catalog Collection Method Based on Large Vision-Language Models
by Honglin Pang, Yi Chang, Tianjing Duan, Xi Yang
First submitted to arxiv on: 28 Dec 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a novel method for collecting and processing archaeological catalogs using Large Vision-Language Models (VLMs). The current approach faces challenges in accurate image detection and modal matching when dealing with archaeological data. To overcome these issues, the authors develop a three-module system: document localization, block comprehension, and block matching. This system is tested on two pottery catalog datasets, Dabagou and Miaozigou, showing promising results for reliable automated collection. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps make it easier to collect and study ancient artifacts by using computers to organize and understand old catalogs of pottery and other treasures. The problem is that current computer models aren’t good at looking at pictures or understanding how different types of things are related. To fix this, the researchers created a special system with three parts: finding the right documents, understanding what’s inside those documents, and matching similar things together. They tested their system on two ancient pottery catalogs and showed it can be very helpful for people studying these kinds of artifacts. |
