Implementation:Open compass VLMEvalKit Video Holmes

Field	Value
source	VLMEvalKit
domain	Vision, Benchmarking, Video Reasoning

Overview

Benchmark dataset implementation for Video Holmes evaluation in VLMEvalKit.

Description

Video_Holmes inherits from VideoBaseDataset and implements the Video Holmes benchmark for video-based reasoning evaluation. The TYPE field is set to 'Video-MCQ'. It uses a reasoning-focused prompt template with think/answer XML tags and defaults to 32 frames.

Usage

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

Code Reference

Source: vlmeval/dataset/video_holmes.py, Lines: L1-252
Import: from vlmeval.dataset.video_holmes import Video_Holmes

Signature:

class Video_Holmes(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_Holmes')

Related Pages

Page Connections

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

Principle

Implementation

Heuristic

Environment