Figure 3 - ImageRef-VL: Enabling Contextual Image Referencing in Vision-Language Models

Human evaluation score distribution of four methods.

Reference

ImageRef-VL: Enabling Contextual Image Referencing in Vision-Language Models - Scientific Figure on ResearchGate. Available from: https://www.researchgate.net/figure/Human-evaluation-score-distribution-of-four-methods_fig3_388317729 [accessed 24 May 2025]

Caption

Figure 3: Human evaluation score distribution of four methods.

Embed code

<a href="https://www.researchgate.net/figure/Human-evaluation-score-distribution-of-four-methods_fig3_388317729"><img src="https://www.researchgate.net/publication/388317729/figure/fig3/AS:11431281305145834@1737647256678/Human-evaluation-score-distribution-of-four-methods.png" alt="Human evaluation score distribution of four methods."/></a>