Recent News

  • [2024.06.16] Two papers got accepted by CVPR 2024!
  • [2024.01.16] Our survey paper about forging VFM for AD is released!
  • [2023.12.09] Two papers got accepted by AAAI 2024!
  • [2023.10.04] Our CVPR2022 oral paper is extended on TPAMI!
  • [2023.07.14] One paper got accepted by ICCV2023 (Oral)!
  • [2023.02.28] One paper got accepted by CVPR2023!
  • [2022.12.22] One paper got accepted by TNNLS (IF14.255)!
  • [2022.11.21] One paper got accepted by AAAI 2023!
  • [2022.09.15] One paper got accepted by NeurIPS 2022 (Spotlight)!
  • [2022.07.03] One paper got accepted by ECCV 2022.
  • [2022.03.02] Two papers got accepted by CVPR 2022 (one is Oral)!
  • [2021.07.24] Two papers got accepted by ICCV 2021!
  • [2021.04.29] One paper PointLIE got accepted by IJCAI 2021!
  • [2021.01.09] One paper got accepted by ISBI 2021!
  • [2020.12.02] One paper got accepted by AAAI 2021.
  • [2020.07.03] One paper CIMR-SR got accepted by ECCV 2020!
  • [2020.02.24] One paper PointASNL got accepted by CVPR 2020!
  • [2020.01.13] One paper got accepted by ISBI 2020!

Challenge & Benchmark

Publications

Survey
The first survey about forging vision foundation model for autonomous driving!

AAAI2024 (* indicates corresponding author)
4th place in the challenge Occ3D@CVPR2023!

AAAI2024 (* indicates corresponding author)

TPAMI (* indicates co-first author)
Impact Factor: 23.6!

ICCV2023
Oral Presentation! (5% in submission)

International Multimedia Conference (MM) 2023

IEEE Transactions on Image Processing (TIP)
Impact Factor: 10.6

CVPR2023
Rank 1st in the leaderboard of KITTI depth completion (2022-11-16)!

International Journal of Computer Vision (IJCV)
Impact factor: 19.5!

TNNLS (* indicates co-first and correspondence author)
Impact Factor: 14.3!

AAAI 2023

arXiv

NeurIPS 2022
Spotlight! (5% in submission)

ECCV 2022
Rank 1st in the leaderboard of SemanticKITTI (2022-03-08)!

TNNLS (* indicates co-first author)
Impact Factor: 14.3! Newly proposed benchmark for 3D visual grounding!

IEEE Transactions on Visualization and Computer Graphics (TVCG)
Newly proposed dataset for VQA-3D!

CVPR 2022
Oral Presentation! (5% in submission)

CVPR 2022 (* indicates co-first author)

ICCV 2021 (* indicates co-first author)

ICCV 2021 (* indicates co-first author)
Rank 1st in the leaderboard of ScanRefer (2021-03-18)!

IJCAI 2021 (* indicates co-first author)
Only 13.9% acceptance rate!

ISBI 2021 (* indicates co-first author)

AAAI 2021
Rank 1st and 3rd in the semantic scene completion and semantic segmentation leaderboards of SemanticKITTI (2020-09-18)!

Journal of Chemical Information and Modeling
(Impact factor: 4.956)

ISBI 2020

Projects

PointNet and PointNet++ implemented by PyTorch (in pure Python).

EverybodyDanceNow reproduced in PyTorch.

The 2nd solution for the challenge Urban3D@ICCV2021.The 3rd solution for the challenge Urban3D@ECCV2022.

Topic: Enhanced Point Cloud Representation through Cross-modal Knowledge Distillation

Contact

  • xuyan1@link.cuhk.edu.cn
  • No.2001 Longxiang Avenue, Longhongge Community, Longcheng Street, Longgang District, Shenzhen, China.


This page is maintained by Xu Yan. Last update: 2024.06.16.