I am currently an Associate Professor (Tenured) of International School of Information Science and Engineering at Dalian University of Technology (DUT) . Before joining DUT, I was a researcher at Artificial Intelligence Research Center (AIRC) of AIST from 2018 to 2021. I received the Ph.D. degree from Nagoya University in 2017, an M.Sc. degree from Osaka University in 2012 and a Bachelor degree from Shanghai Jiao Tong University (SJTU) in 2009. I am also a Guest Researcher of AIRC since 2022 and a Guest Associate Professor of Ritsumeikan University since 2022.
I research machine perception, scene understanding and interaction from different scales of the 3D physical world using multimodal sensor data (Camera images, LiDAR 3D point clouds, Radar scans, etc.), aiming to enable machines to see the world in super vision.
News
[2024.03] Two papers accepted by ICME 2024.[2024.02] One paper accepted by CVPR 2024.
[2023.12] Two papers accepted by ICASSP 2024.
[2023.08] One paper accepted by RA-L.
[2023.08] Two papers accepted by PRCV 2023.
[2023.07] One paper accepted by ACM MM 2023.
[2023.04] Homepage renewed.
[2023.02] One paper accepted by ICASSP 2023.
[2022.12] One paper accepted by IJAEOG.
[2022.10] Co-organize a special issue on Real-Time Machine Vision Acceleration Technology and Applications at JRTIP.
Publications
(* indicates corresponding author(s))
[2024]
Point Cloud Compression via Constrained Optimal
Transport
Novel Class Discovery for Ultra-Fine-Grained Visual Categorization
Attribution-based Scanline Perturbation Attack on 3D Detectors of
LiDAR Point Clouds
Sketch-based 3D Shape Retrieval with Multi-view Fusion Transformer
ICASSP 2024,
Paper
[2023]
Snow Removal for LiDAR Point Clouds With Spatio-Temporal Conditional Random Fields
IEEE Robotics and Automation Letters
Enhancing Lidar and Radar Fusion for Vehicle Detection in Adverse Weather via Cross-Modality Semantic Consistency
PRCV 2023,
Paper
Broaden Your Positives: A General Rectification Approach for Novel Class Discovery
PRCV 2023,
Paper
MSECNet: Accurate and Robust Normal Estimation for 3D Point Clouds by Multi-Scale Edge Conditioning
VAN-ICP: GPU-Accelerated Approximate Nearest Neighbor Search for ICP Registration via
Voxel Dilation
Optimizing Local Feature Representations of 3D Point Clouds with Anisotropic Edge
Modeling
MMM 2023,
Paper
DS-Net: A dedicated approach for collapsed building detection from post-event
airborne point clouds
International Journal of Applied Earth Observation and Geoinformation
IJAEOG,
Paper
[2022]
Weakly Supervised Point Cloud Upsampling via Optimal Transport
Surgical Skill Assessment via Video Semantic Aggregation
Spatio-Temporal Perturbations for Video Attribution
IEEE Transactions on Circuits and Systems for Video Technology,
Efficient Stereo Matching on Embedded GPUs with Zero-Means Cross Correlation
Journal of Systems Architecture,
[2021]
Towards Visually Explaining Video Understanding Networks with Perturbation
Delivery of Omnidirectional Video using Saliency Prediction and Optimal Bitrate
Allocation
Signal, Image and Video Processing
SViP,
Paper
[2020]
SOIC: Semantic Online Initialization and Calibration for LiDAR and Camera
Densification of Airborne Lidar Point Cloud with Fused Encoder-Decoder Networks
IGARSS 2020,
Paper
PSNet: A Style Transfer Network for Point Cloud Stylization on Geometry and Color
Weakly Supervised Silhouette-based Semantic Scene Change Detection
Z2-ZNCC: ZigZag Scanning based Zero-means Normalized Cross Correlation
for Fast and
Accurate Stereo Matching on Embedded GPU
ICCD 2020
Paper
[Before 2020]
A Point-wise LiDAR and Image Multimodal Fusion Network (PMNet) for Aerial Point
Cloud 3D Semantic Segmentation
Remote Sensing 2019,
Image-matching based Identification of Store Signage using Web-crawled Information
IEEE Access, 2018
Access
Paper
Image Translation Between Sar and Optical Imagery with Generative Adversarial Nets
IGARSS 2018,
Paper
Reflectance Intensity Assisted Automatic and Accurate Extrinsic Calibration of 3D
LiDAR and Panoramic Camera using a
Printed Chessboard
Remote Sensing 2017,
Filmy Cloud Removal on Satellite Imagery with Multispectral Conditional Generative
Adversarial Nets
Dense Optical Flow based Change Detection Network Robust to Difference of Camera
Viewpoints
Arxiv
Paper
Incremental and enhanced scanline-based segmentation method for surface
reconstruction of sparse LiDAR data
Remote Sensing 2016,
UbiComp/ISWC 2015 PDR Challenge Corpus
UbicompW 2016
Paper
A design of 0.7-V 400-MHz all-digital phase-locked loop for implantable biomedical
devices
IEICE Transactions on Electronics 2016,
IEICE
Paper
Velobug: A Mobile System for 3D Indoor Mapping
UbicompW 2015,
Paper
Teaching
- Information Security, Fall 2021, Fall 2022, Fall 2023
- Software Interface and Human–computer Interaction, Fall 2021, Fall 2022, Fall 2023
- Object Oriented Technology UML, Spring 2022, Spring 2023
Projects
- First Person Vision in 3D Physical World at AIST in 2019-2021.
- Compact Mobile Mapping System at Nagoya University in 2017 and AIST in 2018.
- Indoor and Outdoor Mapping at Nagoya University in 2015-2017 and AIST in 2018-2019.
