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

This work focuses on training a single visual relationship detectorpredicting over the union of label spaces from multiple datasets. Merginglabels spanning different datasets could be challenging due to inconsistenttaxonomies. The issue is exacerbated in visual relationship detection whensecond-order visual semantics are introduced between pairs of objects. Toaddress this challenge, we propose UniVRD, a novel bottom-up method for UnifiedVisual Relationship Detection by leveraging vision and language models (VLMs).VLMs provide well-aligned image and text embeddings, where similarrelationships are optimized to be close to each other for semantic unification.Our bottom-up design enables the model to enjoy the benefit of training withboth object detection and visual relationship datasets. Empirical results onboth human-object interaction detection and scene-graph generation demonstratethe competitive performance of our model. UniVRD achieves 38.07 mAP onHICO-DET, outperforming the current best bottom-up HOI detector by 14.26 mAP.More importantly, we show that our unified detector performs as well asdataset-specific models in mAP, and achieves further improvements when we scaleup the model. Our code will be made publicly available on GitHub.

Unified Visual Relationship Detection with Vision and Language Models