Publications

ConfMix: Unsupervised Domain Adaptation for Object Detection via Confidence-based Mixing

Overlap-guided Gaussian Mixture Model for Point Cloud Registration

Graph-based generative face anonymisation with pose preservation

Cluster-level pseudo-labelling for source-free cross-domain facial expression recognition

Data Augmentation-free Unsupervised Learning for 3D Point Cloud Understanding

Low-budget label query through domain alignment enforcement

Hyperbolic Vision Transformers: Combining Improvements in Metric Learning

Novel Class Discovery in Semantic Segmentation

Playable Environments: Video Manipulation in Space and Time

Predict, Prevent, and Evaluate: Disentangled Text-Driven Image Manipulation Empowered by Pre-Trained Vision-Language Model

Self-Supervised Models are Continual Learners