Our Publications

SF-UDA^3D: Source-Free Unsupervised Domain Adaptation for LiDAR-Based 3D Object Detection

Bi-Directional Generation for Unsupervised Domain Adaptation

Business Entity Matching with Siamese Graph Convolutional Networks

Random Erasing Data Augmentation

Dual In-painting Model for Unsupervised Gaze Correction and Animation in the Wild

Class-Aware Modality Mix and Center-Guided Metric Learning for Visible-Thermal Person Re-Identification

Learning to Cluster under Domain Shift

On the usage of the trifocal tensor in motion segmentation

Online Continual Learning under Extreme Memory Constraints

Towards Generalization Across Depth for Monocular 3D Object Detection