Implementation:Open compass VLMEvalKit VideoMME

Field	Value
source	VLMEvalKit
domain	Vision, Benchmarking, Video Understanding

Overview

Benchmark dataset implementation for Video-MME evaluation in VLMEvalKit.

Description

VideoMME inherits from VideoBaseDataset and implements the Video-MME benchmark for comprehensive video understanding evaluation. The TYPE field is set to 'Video-MCQ'. It supports subtitle-augmented evaluation with dedicated prompt templates for frames with and without subtitles.

Usage

Registered in vlmeval/dataset/__init__.py and invoked through build_dataset() by benchmark name.

Code Reference

Source: vlmeval/dataset/videomme.py, Lines: L1-285
Import: from vlmeval.dataset.videomme import VideoMME

Signature:

class VideoMME(VideoBaseDataset):
    TYPE = 'Video-MCQ'
    DATASET_URL = {...}
    DATASET_MD5 = {...}
    ...

I/O Contract

Direction	Description
Inputs	TSV dataset file with image/video paths and questions
Outputs	Evaluation results DataFrame with scores per category

Usage Examples

from vlmeval.dataset import build_dataset
dataset = build_dataset('Video-MME')

Related Pages

Page Connections

Double-click a node to navigate. Hold to expand connections.

Principle

Implementation

Heuristic

Environment