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

3D cross-modal retrieval is gaining attention in the multimedia community.Central to this topic is learning a joint embedding space to represent datafrom different modalities, such as images, 3D point clouds, and polygon meshes,to extract modality-invariant and discriminative features. Hence, theperformance of cross-modal retrieval methods heavily depends on therepresentational capacity of this embedding space. Existing methods treat allinstances equally, applying the same penalty strength to instances with varyingdegrees of difficulty, ignoring the differences between instances. This canresult in ambiguous convergence or local optima, severely compromising theseparability of the feature space. To address this limitation, we propose anInstance-Variant loss to assign different penalty strengths to differentinstances, improving the space separability. Specifically, we assign differentpenalty weights to instances positively related to their intra-class distance.Simultaneously, we reduce the cross-modal discrepancy between features bylearning a shared weight vector for the same class data from differentmodalities. By leveraging the Gaussian RBF kernel to evaluate samplesimilarity, we further propose an Intra-Class loss function that minimizes theintra-class distance among same-class instances. Extensive experiments on three3D cross-modal datasets show that our proposed method surpasses recentstate-of-the-art approaches.

Instance-Variant Loss with Gaussian RBF Kernel for 3D Cross-modal Retriveal