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

In recent years, sketch-based 3D shape retrieval has attracted growingattention. While many previous studies have focused on cross-modal matchingbetween hand-drawn sketches and 3D shapes, the critical issue of how to handlelow-quality and noisy samples in sketch data has been largely neglected. Thispaper presents an uncertainty-aware cross-modal transfer network (UACTN) thataddresses this issue. UACTN decouples the representation learning of sketchesand 3D shapes into two separate tasks: classification-based sketch uncertaintylearning and 3D shape feature transfer. We first introduce an end-to-endclassification-based approach that simultaneously learns sketch features anduncertainty, allowing uncertainty to prevent overfitting noisy sketches byassigning different levels of importance to clean and noisy sketches. Then, 3Dshape features are mapped into the pre-learned sketch embedding space forfeature alignment. Extensive experiments and ablation studies on two benchmarksdemonstrate the superiority of our proposed method compared to state-of-the-artmethods.

Uncertainty-Aware Cross-Modal Transfer Network for Sketch-Based 3D Shape Retrieval