Benchmark

MMS-VPR Benchmark

What is MMS-VPR?

MMS-VPR is a large-scale multimodal dataset for street-level place recognition in pedestrian areas. It contains 78,575 images and 2,512 videos from 207…

Released: 2025-05-18
Modality: multimodal
Evaluates: 多模态, Multimodal, 理解, Understanding, 语言, Language, Visual Place Recognition, Dataset and Benchmark, 多模态模型, VLM, 图像理解, Image Understanding, 语言理解, Comprehension, 不支持, Unsupported
Openness: restricted
Importer: OpenCompass Hub
Reported scores: 0

Source provenance

Original evidence https://hub.opencompass.org.cn/dataset-detail/MMS-VPR

MMS-VPR paper, code and dataset

Paper https://arxiv.org/abs/2505.12254
Code https://github.com/yiasun/MMS-VPRlib
Dataset https://huggingface.co/datasets/Yiwei-Ou/MMS-VPR

No reported scores are on record for this benchmark yet.

Which sources cite MMS-VPR?

MMS-VPR

Related 多模态, Multimodal, 理解, Understanding, 语言, Language, Visual Place Recognition, Dataset and Benchmark, 多模态模型, VLM, 图像理解, Image Understanding, 语言理解, Comprehension, 不支持, Unsupported benchmarks