English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Large-scale text-to-image diffusion models have shown impressive capabilitiesfor generative tasks by leveraging strong vision-language alignment frompre-training. However, most vision-language discriminative tasks requireextensive fine-tuning on carefully-labeled datasets to acquire such alignment,with great cost in time and computing resources. In this work, we exploredirectly applying a pre-trained generative diffusion model to the challengingdiscriminative task of visual grounding without any fine-tuning and additionaltraining dataset. Specifically, we propose VGDiffZero, a simple yet effectivezero-shot visual grounding framework based on text-to-image diffusion models.We also design a comprehensive region-scoring method considering both globaland local contexts of each isolated proposal. Extensive experiments on RefCOCO,RefCOCO+, and RefCOCOg show that VGDiffZero achieves strong performance onzero-shot visual grounding. Our code is available athttps://github.com/xuyang-liu16/VGDiffZero.

VGDiffZero: Text-to-image Diffusion Models Can Be Zero-shot Visual Grounders