CVPR 2022 We introduce the largest synthetic dataset for autonomous driving to study continuous multi-task domain adaptation.Read more
ECCV 2022 We introduce the HQ-YTVIS dataset as long as Tube-Boundary AP, which provides training, validation and testing support to facilitate future development of VIS methods aiming at higher mask quality.
CVPR 2022 We introduce the largest synthetic dataset for autonomous driving to study continuous multi-task domain adaptation.
CVPR 2020 Oral The largest driving video dataset for heterogeneous multitask learning.
arXiv 2015 We propose to amplify human effort through a partially automated labeling scheme, leveraging deep learning with humans in the loop.
CVPR 2015 Oral We propose to represent a geometric 3D shape as a probability distribution of binary variables on a 3D voxel grid.