imagesVchitect/ShotBenchvision-languagebenchmarkcinematographyvideoevaluationvlmmultimodalqa

ShotBench: Cinematic Understanding Benchmark for VLMs

Category
Images
Records
3,572 rows
Format
PARQUET
Update Frequency
One-time snapshot
Collection Method
uploaded
PII
None detected
File Size
~0.12 MB
Downloads
0

About this data

3,572 expert-level QA pairs over 3,049 images and 464 video clips from Oscar-nominated cinematography films, for evaluating cinematic understanding in vision-language models.

Schema

NameTypeDescription
indexBIGINTUnique identifier for each question-answer pair (1–3,572).
typeVARCHARMedia format as JSON array; either ["image"] or ["video"].
pathVARCHARFile path(s) to media asset(s) as JSON array; format image/ID.jpg or video/ID.mp4.
questionVARCHARMultiple-choice question about cinematic technique applied to the media.
optionsVARCHARJSON object mapping letter keys (A–D) to answer choice strings.
answerVARCHARCorrect answer label as single letter (A, B, C, or D).
categoryVARCHARCinematic skill dimension: shot size, framing, camera angle, lens, lighting, composition, or movement.

Sample Data

Preview a sample of the data before downloading.

Free

Open dataset

Quality: No ratings
0 downloads
Seller: DataBazaar
Sign up to download

Agent? No sign-up needed →

For AI Agents

Via MCP Server
# 1. Add to your agent's MCP config (claude_desktop_config.json or similar):
{
  "mcpServers": {
    "databazaar": { "command": "npx", "args": ["databazaar-mcp"] }
  }
}

# 2. Your agent can then call:
search_datasets({ query: "ShotBench: Cinematic Understan" })
// Found: b1eb2f57-2782-4ad5-9a05-091512ee81db
get_download_url({ dataset_id: "b1eb2f57-2782-4ad5-9a05-091512ee81db" })  // free — no API key needed
Via REST API
# Free dataset — no API key required:
curl https://api.databazaar.io/datasets/b1eb2f57-2782-4ad5-9a05-091512ee81db/download-url