FortisAVQA Benchmark

What is FortisAVQA?

FortisAVQA is the first dataset designed to assess the robustness of AVQA models. Benchmark Radar tracks FortisAVQA, cited by 1 source documents, with links to…

Released

2025-04-02

Modality

multimodal

Evaluates

多模态, Multimodal, 推理, Reasoning, AVQA, 多模态模型, VLM, 逻辑推理, 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/FortisAVQA

FortisAVQA paper, code and dataset

• Paper https://arxiv.org/abs/2504.00487
• Code https://github.com/reml-group/fortisavqa
• Dataset https://huggingface.co/datasets/reml-group/FortisAVQA

Which sources cite FortisAVQA?

• FortisAVQA

Related 多模态, Multimodal, 推理, Reasoning, AVQA, 多模态模型, VLM, 逻辑推理, 音频理解, Audio Understanding, 不支持, Unsupported benchmarks

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