News

Our paper DONUT: A Decoder-Only Model for Trajectory Prediction was accepted at the 2025 International Conference on Computer Vision (ICCV)!

Our project: Sa2VA-i: Improving Sa2VA Results with Consistent Training and Inference achieves 3rd Place of LSVOS Workshop, MeViS Track.

Our paper How do Foundation Models Compare to Skeleton-Based Approaches for Gesture Recognition in Human-Robot Interaction? has been accepted!

We have two papers accepted at Conference on Computer Vision and Pattern Recognition (CVPR) 2025!

• Spotting the Unexpected (STU): A 3D LiDAR Dataset for Anomaly Segmentation in Autonomous Driving

• Your ViT is Secretly an Image Segmentation Model

We have four papers at the IEEE International Conference on Robotics and Automation (ICRA). See you all in Atlanta!

• Systematic Evaluation of Different Projection Methods for Monocular 3D Human Pose Estimation on Heavily Distorted Fisheye Images

• Interactive4D: Interactive 4D LiDAR Segmentation

• OCCUQ: Exploring Efficient Uncertainty Quantification for 3D Occupancy Prediction

• OoDIS: Anomaly Instance Segmentation and Detection Benchmark