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

Vision-language pre-training (VLP) has shown impressive performance on a widerange of cross-modal tasks, where VLP models without reliance on objectdetectors are becoming the mainstream due to their superior computationefficiency and competitive performance. However, the removal of objectdetectors also deprives the capability of VLP models in explicit objectmodeling, which is essential to various position-sensitive vision-language (VL)tasks, such as referring expression comprehension and visual commonsensereasoning. To address the challenge, we introduce PEVL that enhances thepre-training and prompt tuning of VLP models with explicit object positionmodeling. Specifically, PEVL reformulates discretized object positions andlanguage in a unified language modeling framework, which facilitates explicitVL alignment during pre-training, and also enables flexible prompt tuning forvarious downstream tasks. We show that PEVL enables state-of-the-artperformance of detector-free VLP models on position-sensitive tasks such asreferring expression comprehension and phrase grounding, and also improves theperformance on position-insensitive tasks with grounded inputs. We make thedata and code for this paper publicly available athttps://github.com/thunlp/PEVL.

PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models