README.md

VASEVQA Dataset

A Visual Question Answering dataset for ancient vase analysis and description.

Dataset Overview

• Total Images: 31,773 vase images
• Format: Conversational QA pairs in LLaVA format
• Domain: Ancient Greek/Roman pottery and vases

Data Structure

Single-view Dataset

• Training: data_train_single_llava_vasevl_v9.json (9,354 samples)
• Testing: data_test_single_llava_vasevl_v9.json (2,339 samples)
• Format: One image per conversation

Multi-view Dataset

• Training: data_train_multi_llava_vasevl_v6_fixed.json (25,544 samples)
• Testing: data_test_multi_llava_vasevl_v6_fixed.json (6,229 samples)
• Format: Multiple images per conversation with proper <image> tokens

Question Types

Each vase is annotated with questions about:

• Fabric (e.g., ATHENIAN)
• Technique (e.g., BLACK-FIGURE, RED-FIGURE)
• Shape name (e.g., LEKYTHOS, MASTOID)
• Provenance/origin
• Dating information
• Attribution details
• Decorative descriptions
• Overall comprehensive information

JSON Format

{
  "id": "sample_id",
  "images": "images/filename.jpg" | ["image1.jpg", "image2.jpg"],
  "conversations": [
    {
      "from": "human",
      "value": "<image>\nWhat is the fabric of the vase?"
    },
    {
      "from": "gpt", 
      "value": "The fabric of the vase is ATHENIAN."
    }
  ]
}

Files

• images/: Directory containing 31,773 vase images
• descriptions.csv: Original metadata source
• fix_multi_data.py: Script for adding image tokens to multi-view data