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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Contrastive Language-Image Pre-training (CLIP) has drawn increasing attentionrecently for its transferable visual representation learning. However, due tothe semantic gap within datasets, CLIP's pre-trained image-text alignmentbecomes sub-optimal on downstream tasks, which severely harms its transferringperformance. To better adapt the cross-modality embedding space, we propose toenhance CLIP via Visual-guided Texts, named VT-CLIP. Specifically, we guidetextual features of different categories to adaptively explore informativeregions on the image and aggregate visual features by attention mechanisms. Inthis way, the texts become visual-guided, namely, more semantically correlatedwith downstream images, which greatly benefits the category-wise matchingprocess. In few-shot settings, we evaluate our VT-CLIP on 11 well-knownclassification datasets to demonstrate its effectiveness.

VT-CLIP: Enhancing Vision-Language Models with Visual-guided Texts