Short Bio
I am now an Associate Professor in the
College of informatics at the Huazhong Agricultural University (HZAU). Before coming to HZAU, I worked in DJI as a senior perception engineer on autonomous driving.
I received my Ph.D. in Information and Communication Engineering from
Huazhong University of Science and Technology, supervised by Prof.
Xiang Bai. My research interests mainly include 3D vision, Vision & Language domain, helping machine to understand the world better. I recently focus on Out of Distribution Detection (OOD), with an emphasis on industrial anomaly detection, open-set learning on point clouds, 3D shape retreival, and 3D object detection.
Openings
I am looking for self-motivated PhD, Master and Undergraduate students. Please send me an email with your CV if you are interested.
课题组招收博士生、硕士生和对科研感兴趣的本科生,目前有如下多个科研课题:1. 基于大模型的3D表征学习;2. 工业异常检测;3. 医学图像分析;4. 大模型安全分析。感兴趣的同学欢迎发邮件(xwhe@mail.hzau.edu.cn)与我们交流。
Selected Publications
For full publications, please see my
Google Scholar
-
[ICCV 2025] Describe, Adapt and Combine: Empowering CLIP Encoders for Open-set 3D Object Retrieval
Zhichuan Wang, Yang Zhou, Zhe Liu, Rui Yu, Song Bai, Yulong Wang, Xinwei He, Xiang Bai,
in ICCV , 2025.
-
[ICCV 2025] Llava-kd: A framework of distilling multimodal large language models
Yuxuan Cai, Jiangning Zhang, Haoyang He, Xinwei He, Ao Tong, Zhenye Gan, Chengjie Wang, Zhucun Xue, Yong Liu, Xiang Bai,
in ICCV , 2025.
-
[CVPR 2025] WeakMCN: Multi-task Collaborative Network for Weakly Supervised Referring Expression Comprehension and Segmentation
Silin Cheng, Yang Liu, Xinwei He, Sebastien Ourselin, Lei Tan, Gen Luo,
in CVPR , 2025.
-
[SIGIR 2025] CLIP-AdaM: Adapting Multi-view CLIP for Open-set 3D Object Retrieval
Xinwei He, Liang Ma, Yuxuan Cheng, Zhichuan Wang, Yulong Wang, Yang Zhou, Xiang Bai,
in SIGIR , 2025.
-
[IJCAI 2025] From Individual to Universal: Regularized Multi-view Joint Representation for Multi-view Subspace-Preserving Recovery
Libin Wang, Yulong Wang, Xinwei He, Qiwei Xie, Kit Ian Kou, Yuan Yan Tang,
in IJCAI , 2025.
-
[TII 2025] Dynamic Expert Routing for Unsupervised Continual Anomaly Detection
Yuxuan Cai, Xinwei He, Ao Tong, Xiang Bai,
in TII , 2024.
-
[PR 2024] Latformer: locality-aware point-view fusion transformer for 3d shape recognition
Xinwei He, Silin Cheng, Dingkang Liang, Song Bai, Xi Wang, Yingying Zhu,
in PR , 2024.
-
[PR 2023] Haar wavelet downsampling: A simple but effective downsampling module for semantic segmentation
Guoping Xu, Wentao Liao, Xuan Zhang, Chang Li, Xinwei He, Xinglong Wu,
in PR , 2023.
-
[TITS 2024] Multi-modal 3D object detection by box matching
Zhe Liu, Xiaoqing Ye, Zhikang Zou, Xinwei He, Xiao Tan, Errui Ding, Jingdong Wang, Xiang Bai,
in TITS , 2024.
-
[TII 2023] A discrepancy aware framework for robust anomaly detection
Yuxuan Cai, Dingkang Liang, Dongliang Luo, Xinwei He, Xin Yang, Xiang Bai,
in TII , 2023.
-
[TIP 2021] Pra-net: Point relation-aware network for 3d point cloud analysis
Silin Cheng, Xiwu Chen, Xinwei He, Zhe Liu, Xiang Bai,
in TIP , 2021.
-
[TIP 2020] An improved multi-view convolutional neural network for 3D object retrieval
Xinwei He, Song Bai, Jiajia Chu, Xiang Bai,
in TIP , 2020.
-
[ICCV 2019] View n-gram network for 3d object retrieval
Xinwei He, Song Bai, Xiang Bai,
in ICCV , 2019.
-
[CVPR 2018] Triplet-center loss for multi-view 3d object retrieval
Xinwei He, Yang Zhou, Zhichao Zhou, Song Bai, Xiang Bai,
in CVPR , 2018.