SonicVisionLM:

Playing Sound with Vision Language Models

Paper

Hyperspherical Learning

Hyperspherical learning in multi-label classification

Paper

HybridCR

Weakly-supervised 3d point cloud semantic segmentation via hybrid contrastive regularization

Paper

Class-imbalanced semi-supervised learning

Class-imbalanced semi-supervised learning for large-scale point cloud semantic segmentation via decoupling optimization

Paper

A fine-grained vision and language representation framework

A fine-grained vision and language representation framework with graph-based fashion semantic knowledge

Paper

Paying attention for adjacent areas

Paying attention for adjacent areas: Learning discriminative features for large-scale 3D scene segmentation

Paper