Publications

Home » Publications

CrossDTR: Cross-view and Depth-guided Transformers for 3D Object Detection

May 30, 2023 · 0 min · 0 words · Me

« Prev
Coarse-To-Fine Point Cloud Registration with SE(3)-Equivariant Representations Next »
Learning Fine-Grained Visual Understanding for Video Question Answering via Decoupling Spatial-Temporal Modeling

© 2025 Lee Hsin-Ying · Powered by Hugo & PaperMod