News

We have two papers accepted at the 2023 Winter Conference on Applications of Computer Vision (WACV):

• BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video
• Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton Formats

We have one paper accepted at the European Conference on Computer Vision (ECCV) 2022, AVVision Workshop:

• 4D-StOP: Panoptic Segmentation of 4D LiDAR using Spatio-temporal Object Proposal Generation and Aggregation

Furthermore, we will present a live demo:

• Accurate and Efficient Absolute 3D Human Pose Estimation Trained on Dozens of Datasets

We have two papers accepted at the Conference on Computer Vision and Pattern Recognition (CVPR) 2022. Both are selected for oral presentations! Check them out:

• Opening up Open World Tracking
• HODOR: High-level Object Descriptors for Object Re-segmentation in Video Learned from Static Images