Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2505.19015 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916886143303680 |
|---|---|
| author | Liu, Jingping Liu, Ziyan Cen, Zhedong Zhou, Yan Zou, Yinan Zhang, Weiyan Jiang, Haiyun Ruan, Tong |
| author_facet | Liu, Jingping Liu, Ziyan Cen, Zhedong Zhou, Yan Zou, Yinan Zhang, Weiyan Jiang, Haiyun Ruan, Tong |
| contents | Spatial relation reasoning is a crucial task for multimodal large language models (MLLMs) to understand the objective world. However, current benchmarks have issues like relying on bounding boxes, ignoring perspective substitutions, or allowing questions to be answered using only the model's prior knowledge without image understanding. To address these issues, we introduce SpatialMQA, a human-annotated spatial relation reasoning benchmark based on COCO2017, which enables MLLMs to focus more on understanding images in the objective world. To ensure data quality, we design a well-tailored annotation procedure, resulting in SpatialMQA consisting of 5,392 samples. Based on this benchmark, a series of closed- and open-source MLLMs are implemented and the results indicate that the current state-of-the-art MLLM achieves only 48.14% accuracy, far below the human-level accuracy of 98.40%. Extensive experimental analyses are also conducted, suggesting the future research directions. The benchmark and codes are available at https://github.com/ziyan-xiaoyu/SpatialMQA.git. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_19015 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Can Multimodal Large Language Models Understand Spatial Relations? Liu, Jingping Liu, Ziyan Cen, Zhedong Zhou, Yan Zou, Yinan Zhang, Weiyan Jiang, Haiyun Ruan, Tong Computer Vision and Pattern Recognition Multimedia Spatial relation reasoning is a crucial task for multimodal large language models (MLLMs) to understand the objective world. However, current benchmarks have issues like relying on bounding boxes, ignoring perspective substitutions, or allowing questions to be answered using only the model's prior knowledge without image understanding. To address these issues, we introduce SpatialMQA, a human-annotated spatial relation reasoning benchmark based on COCO2017, which enables MLLMs to focus more on understanding images in the objective world. To ensure data quality, we design a well-tailored annotation procedure, resulting in SpatialMQA consisting of 5,392 samples. Based on this benchmark, a series of closed- and open-source MLLMs are implemented and the results indicate that the current state-of-the-art MLLM achieves only 48.14% accuracy, far below the human-level accuracy of 98.40%. Extensive experimental analyses are also conducted, suggesting the future research directions. The benchmark and codes are available at https://github.com/ziyan-xiaoyu/SpatialMQA.git. |
| title | Can Multimodal Large Language Models Understand Spatial Relations? |
| topic | Computer Vision and Pattern Recognition Multimedia |
| url | https://arxiv.org/abs/2505.19015 |