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

Open-vocabulary learning has emerged as a cutting-edge research area,particularly in light of the widespread adoption of vision-based foundationalmodels. Its primary objective is to comprehend novel concepts that are notencompassed within a predefined vocabulary. One key facet of this endeavor isVisual Grounding, which entails locating a specific region within an imagebased on a corresponding language description. While current foundationalmodels excel at various visual language tasks, there's a noticeable absence ofmodels specifically tailored for open-vocabulary visual grounding. Thisresearch endeavor introduces novel and challenging OV tasks, namelyOpen-Vocabulary Visual Grounding and Open-Vocabulary Phrase Localization. Theoverarching aim is to establish connections between language descriptions andthe localization of novel objects. To facilitate this, we have curated acomprehensive annotated benchmark, encompassing 7,272 OV-VG images and 1,000OV-PL images. In our pursuit of addressing these challenges, we delved intovarious baseline methodologies rooted in existing open-vocabulary objectdetection, VG, and phrase localization frameworks. Surprisingly, we discoveredthat state-of-the-art methods often falter in diverse scenarios. Consequently,we developed a novel framework that integrates two critical components:Text-Image Query Selection and Language-Guided Feature Attention. These modulesare designed to bolster the recognition of novel categories and enhance thealignment between visual and linguistic information. Extensive experimentsdemonstrate the efficacy of our proposed framework, which consistently attainsSOTA performance across the OV-VG task. Additionally, ablation studies providefurther evidence of the effectiveness of our innovative models. Codes anddatasets will be made publicly available at https://github.com/cv516Buaa/OV-VG.

OV-VG: A Benchmark for Open-Vocabulary Visual Grounding