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

Visual grounding, a crucial vision-language task involving the understandingof the visual context based on the query expression, necessitates the model tocapture the interactions between objects, as well as various spatial andattribute information. However, the annotation data of visual grounding task islimited due to its time-consuming and labor-intensive annotation process,resulting in the trained models being constrained from generalizing itscapability to a broader domain. To address this challenge, we proposeGroundVLP, a simple yet effective zero-shot method that harnesses visualgrounding ability from the existing models trained from image-text pairs andpure object detection data, both of which are more conveniently obtainable andoffer a broader domain compared to visual grounding annotation data. GroundVLPproposes a fusion mechanism that combines the heatmap from GradCAM and theobject proposals of open-vocabulary detectors. We demonstrate that the proposedmethod significantly outperforms other zero-shot methods on RefCOCO/+/gdatasets, surpassing prior zero-shot state-of-the-art by approximately 28\% onthe test split of RefCOCO and RefCOCO+. Furthermore, GroundVLP performscomparably to or even better than some non-VLP-based supervised models on theFlickr30k entities dataset. Our code is available athttps://github.com/om-ai-lab/GroundVLP.

GroundVLP: Harnessing Zero-shot Visual Grounding from Vision-Language Pre-training and Open-Vocabulary Object Detection