Hai Wu's Homepage (XMU)

Hai Wu 吴海

Ph.D. Student

School of informatics, Xiamen University

wuhai@stu.xmu.edu.cn

I am currently pursuing the Ph.D. degree with the School of Informatics, Xiamen University, Xiamen, China. My research interests focus on computer vision and machine learning, particularly in exploring machine learning for autonomous systems. This includes 3D scene understanding, object detection, and other topics related to autonomous driving.

Google Scholar Profile, GitHub Profile

News

[2024/03] Two papers accepted by CVPR 2024.
[2023/10] One paper accepted by AAAI 2024.
[2023/10] One paper accepted by ICCV 2023.
[2023/05] One paper accepted by CVPR 2023.
[2023/06] We release the VirConv codebase, which can achieve SoTA results on KITTI detection dataset.
[2023/05] Our approach VirConv-S ranks 1st on KITTI 3D/BEV/2D object detection benchmark. Please refer to our paper VirConv for more details.
[2022/09] Our approach VirConvTrack ranks 1st on KITTI object tracking benchmark.
[2022/09] One paper accepted by AAAI 2023.
[2022/08] One paper accepted by IEEE TGRS.

Publications

		Commonsense Prototype for Outdoor Unsupervised 3D Object Detection Hai Wu, Shijia Zhao, Xun Huang, Chenglu Wen, Xin Li, and Cheng Wang CVPR. 2024 paper code
		Sunshine to Rainstorm: Cross-Weather Knowledge Distillation for Robust 3D Object Detection Xun Huang, Hai Wu, Xin Li, Xiaoliang Fan, Chenglu Wen, and Cheng Wang AAAI. 2024 paper code
		Virtual Sparse Convolution for Multimodal 3D Object Detection Hai Wu, Chenglu Wen, Shaoshuai Shi, Xin Li, Chenglu Wen, and Cheng Wang CVPR. 2023 paper code
		CoIn: Contrastive Instance Feature Mining for Outdoor 3D Object Detection with Very Limited Annotations Qiming Xia, Jinhao Deng, Chenglu Wen, Hai Wu, Shaoshuai Shi, Xin Li, and Cheng Wang ICCV. 2023 paper code
		Transformation-equivariant 3D object detection for autonomous driving Hai Wu, Chenglu Wen, Wei Li, Xin Li, Ruigang Yang, Cheng Wang AAAI. 2023 paper code
		CasA: A cascade attention network for 3-D object detection from LiDAR point clouds Hai Wu, Jinhao Deng, Chenglu Wen, Xin Li, Cheng Wang, and Jonathan Li IEEE TGRS. 2022 paper code
		SemanticFlow: Semantic Segmentation of Sequential LiDAR Point Clouds From Sparse Frame Annotations Junhao Zhao, Weijie Huang, Hai Wu, Chenglu Wen,Yulan Guo, and Cheng Wang IEEE TGRS. 2023 paper
		BLNet: Bidirectional learning network for point clouds Wenkai Han, Hai Wu, Chenglu Wen, Cheng Wang, Xin Li Computational Visual Media. 2022 paper
		Tracklet Proposal Network for Multi-Object Tracking on Point Clouds Hai Wu, Qing Li, Chenglu Wen, Xin Li, Xiaoliang Fan, Cheng Wang IJCAI. 2021 paper
		3D multi-object tracking in point clouds based on prediction confidence-guided data association Hai Wu, Wenkai Han, Chenglu Wen, Xin Li, Cheng Wang IEEE TITS. 2021 paper
		Indoor 3D human trajectory reconstruction using surveillance camera videos and point clouds Yudi Dai, Chenglu Wen, Hai Wu, Yulan Guo, Longbiao Chen, Cheng Wang IEEE Transactions on Circuits and Systems for Video Technology. 2021 paper
		Recovery of urban 3D road boundary via multi-source data Chenglu Wen, Changbin You, Hai Wu, Cheng Wang, Xiaoliang Fan, Jonathan Li ISPRS Journal of Photogrammetry and Remote Sensing. 2019 paper

Codebase

Activities

Reviewer:

IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
AAAI Conference on Artificial Intelligence (AAAI)
IEEE Transactions on Image Processing (TIP)
IEEE Transactions on Geoscience and Remote Sensing (TGRS)
IEEE Transactions on Intelligent Transportation Systems (TITS)
Transportation Research Part C
ISPRS Journal of Photogrammetry and Remote Sensing

Presentation:

Virtual Sparse Convolution for Multimodal 3D Object Detection, CVPR, Vancouver, Canada, 2023
Transformation-equivariant 3D object detection for autonomous driving, AAAI, Washington, D.C., USA, 2023
Tracklet Proposal Network for Multi-Object Tracking on Point Clouds, Japan, 2021

Internship:

Research Intern, March 2022 - June 2022, Inceptio technology, Shanghai, China.
Advised by Ruigang Yang.

Awards

National scholarship for graduate student, 2023
Excellent student scholarship, 2021
Second prize in data processing at LiDAR Conference, 2023