MAVOS-DD Benchmark

What is MAVOS-DD?

MAVOS-DD is the first large-scale open-set benchmark for multilingual audio-video deepfake detection. Benchmark Radar tracks MAVOS-DD, cited by 1 source…

Released

2025-05-16

Modality

multimodal

Evaluates

多模态, Multimodal, 安全, Safety, VQA, AVQA, 多模态模型, VLM, 安全对齐, Safety Alignment, 音频理解, Audio Understanding, 不支持, Unsupported

Openness

unknown

Importer

OpenCompass Hub

Reported scores

0

Source provenance

• Original evidence https://hub.opencompass.org.cn/dataset-detail/MAVOS-DD

MAVOS-DD paper and dataset

• Paper https://arxiv.org/pdf/2505.11109
• Dataset https://huggingface.co/datasets/unibuc-cs/MAVOS-DD

Which sources cite MAVOS-DD?

• MAVOS-DD

Related 多模态, Multimodal, 安全, Safety, VQA, AVQA, 多模态模型, VLM, 安全对齐, Safety Alignment, 音频理解, Audio Understanding, 不支持, Unsupported benchmarks

• 3DCodeBench
• A-Bench
• A-OKVQA
• AbsPyramid
• ActBench
• ActionAtlas
• ActiveFly-Bench
• Ada-LEval