- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
In this paper, the authors study how to increase the information content of image captions by designing a scene graph for the corresponding images. They build a dataset of 704K samples from PixMo-Cap and use GPT-5.4-nano as a tool to automatically generate new structured captions. The results are stored in JSON format and are highly beneficial for downstream tasks. To demonstrate the effectiveness of their scene graph (SG) model, they conduct extensive experiments on different fine-tuning tasks, and the results validate their method. They also discuss and summarize the main findings to further enhance the applications of their model.
Critical strengths
They build a new model with a scene graph to further enhance the information content of the captions with the structure information omitted in the existing data sets. The method is neat and the result of experiments are convincing. The model only relied on the captions and SG pairs without the need of images. Their method need much less tokens than the original QWen-VL model.
Critical weaknesses
- The novelty of the idea is relatively low as the idea of scene graphs have been widely used and studied in the previous works even in the VLMs. Though they designed SG from a different view, the significance is not very substantial.
- Lack of extensive experiments, especially comparing with existing models in VLMs adopting the idea of SGs, e.g., Yu 2021, Park 2025. Especially the DAC paper.
- The main technical issue in the paper is the construction of their data set. The authors didn't discuss it in details in the main part of the paper, but leaving to the appendix.
Questions for authors
- Why the size of data set is 740K, as in Radford2023 paper, the size of 400 millions. What is the your performance limit if the size data set is as large as that of Radford 2023.
- Fig. 1 & 2 didn't provide any help to further improve the readability of the paper because they didn't contain too much details.
- Why the size of model is only 7B? Is is necessary to provide experiments on large models?
- In the paper, the authors emphasize that they only need 1/500 -- 1/300 tokens of the model in QWen-VL. Is it fair to compare them on this metric?