Lingdong Kong
PhD Student, NUS
I am a first-year Ph.D. student in the Department of Computer Science at the National University of Singapore, under Prof. Wei Tsang Ooi. I am also closely with Dr. Benoit Cottereau from CNRS, Dr. Lai Xing Ng from A*STAR, and Prof. Ziwei Liu from S-Lab, Nanyang Technological University, Singapore.
I work in the fields of deep learning and computer vision, with particular focuses on 3D perception, domain adaptation, and visual representation learning.
My research pursues to build robust and scalable perception models that can be generalized across different domains and scenarios, with minimum or no human annotations needed.
I am fortunate to have research attachments and internships at Shanghai AI Lab, ByteDance AI Lab, MMLab@NTU, Motional, and Advanced Digital Sciences Center.
News
- [03/2023] - LaserMix was selected as a highlight at CVPR 2023.
- [02/2023] - Two papers (LaserMix and CLIP2Scene) accepted to CVPR 2023.
- [01/2023] - One paper (ConDA) accepted to ICRA 2023.
- [11/2022] - We are organizing the RoboDepth Competition at ICRA 2023.
- [06/2022] - We are organizing the 4th SenseHuman Workshop at ECCV 2022.
- [06/2022] - We are organizing the PointCloud-C Challenge at ECCV 2022.
Recent Publication [Full List]
* indicates equal contribution
|
LaserMix for Semi-Supervised LiDAR Semantic Segmentation |
|
CLIP2Scene: Towards Label-Efficient 3D Scene Understanding by CLIP |
|
ConDA: Unsupervised Domain Adaptation for LiDAR Segmentation via Regularized Domain Concatenation |
|
Benchmarking 3D Robustness to Common Corruption and Sensor Failure |
|
Benchmarking Out-of-Distribution Depth Estimation under Corruptions |
Preprint
|
Rethinking Range View Representation for LiDAR Segmentation
arXiv, 2023
|
|
Robo3D: Towards Robust and Reliable 3D Perception against Corruptions
arXiv, 2023
|
|
Towards Label-Free Scene Understanding by Vision Foundation Models
arXiv, 2023
|
|
Unsupervised Video Domain Adaptation for Action Recognition: A Disentanglement Perspective
arXiv, 2022
|
|
Unified 3D and 4D Panoptic Segmentation via Dynamic Shifting Network
arXiv, 2022
|
|
PointCloud-C: Benchmarking and Analyzing Point Cloud Perception Robustness under Corruptions
arXiv, 2022
|
|
Free Lunch for Co-Saliency Detection: Context Adjustment
arXiv, 2021
|
Workshop Organizer
Venue: London, UK
Talk & Presentation
- [Industrial Experience
|
ByteDance AI Lab |
|
Motional |
Academic Service
Conference Reviewer
- IEEE/CVF International Conference on Computer Vision (ICCV)
- Neural Information Processing Systems (NeurIPS)
- International Conference on Learning Representations (ICLR)
- International Conference on Machine Learning (ICML)
- IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Journal Reviewer
- IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI)
- IEEE Transactions on Neural Networks and Learning Systems (T-NNLS)
- IEEE Transactions on Intelligent Vehicles (T-IV)
- IEEE Robotics and Automation Letters (RA-L)