CCNet: Criss-Cross Attention for Semantic Segmentation (TPAMI 2020 & ICCV 2019).
Code for "DANCE: A Deep Attentive Contour Model for Efficient Instance Segmentation", WACV2021
[CVPR 2023] VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking
[ICCV 2023] Temporal Enhanced Training of Multi-view 3D Object Detector via Historical Object Prediction
[ICCV 2023] SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videos
Object detection, 3D detection, and pose estimation using center point detection: