HIER: Metric Learning Beyond Class Labels via Hierarchical Regularization

Relational Context Learning for Human-Object Interaction Detection

Improving Cross-Modal Retrieval with Set of Diverse Embeddings

Instant Domain Augmentation for LiDAR Semantic Segmentation

Soft-Landing Strategy for Alleviating the Task Discrepancy Problem in Temporal Action Localization Tasks

Generalizable Implicit Neural Representations with Instance Pattern Composers

Scene-level Point Cloud Colorization with Semantic-and-Geometric-aware Networks

WEDGE: Web-Image Assisted Domain Generalization for Semantic Segmentation

Convolutional Hough Matching Networks for Robust and Efficient Visual Correspondence

SeLCA: Self-Supervised Learning of Canonical Axis