Our Publications

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

3D-Aware Semantic-Guided Generative Model for Human Synthesis

Batch-efficient Eigen Decomposition for Small and Medium Matrices

Class-incremental Novel Class Discovery

CoSMix: Compositional Semantic Mix for Domain Adaptation in 3D LiDAR Segmentation

GIPSO: Geometrically Informed Propagation for Online Adaptation in 3D LiDAR Segmentation

Quantum Motion Segmentation

Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation.

Fast Differentiable Matrix Square Root

Multimodal Across Domains Gaze Target Detection

Multimodal Emotion Recognition with Modality-Pairwise Unsupervised Contrastive Loss

Temporal Alignment for History Representation in Reinforcement Learning

Unsupervised Domain Adaptation for Video Transformers in Action Recognition