Our Publications

Efficient Generation of Structured Objects with Constrained Adversarial Networks

Latent World Models For Intrinsically Motivated Exploration

Active Hybrid Classification

Learning to Adapt Invariance in Memory for Person Re-identification

Disentangling monocular 3d object detection: from single to multiclass recognition

Detecting and Preventing Confused Labels in Crowdsourced Datasets

Demystifying Pseudo-LiDAR for Monocular 3D Object Detection

Whitening for Self-Supervised Representation Learning