Publications

You can also find my articles on my Google Scholar profile.

Datasets and Surveys

Video Unsupervised Domain Adaptation with Deep Learning: A Comprehensive Survey

ACM Computing Surveys, 2024

Yuecong Xu, Haozhi Cao, Zhenghua Chen, Xiaoli Li, Lihua Xie, Jianfei Yang

[Project Site] [Paper] [Arxiv]

MCD: Diverse Large-Scale Multi-Campus Dataset for Robot Perception

Conference on Computer Vision and Pattern Recognition (CVPR), 2024

Thien-Minh Nguyen, Shenghai Yuan, Thien Hoang Nguyen, Pengyu Yin, Haozhi Cao, Lihua Xie, Maciej Wozniak, Patric Jensfelt, Marko Thiel, Justin Ziegenbein, Noel Blunder

[Project Site] [Paper] [Arxiv]

Going Deeper into Recognizing Actions in Dark Environments: A Comprehensive Benchmark Study

International Journal of Computer Vision (IJCV), 2023

Yuecong Xu*, Haozhi Cao*, Jianxiong Yin, Zhenghua Chen, Xiaoli Li, Zhengguo Li, Qianwen Xu, Jianfei Yang

[Paper] [Arxiv]

Arid: A New Dataset for Recognizing Action in the Dark

International Workshop on Deep Learning for Human Activity Recognition, 2021

Yuecong Xu, Jianfei Yang, Haozhi Cao, Kezhi Mao, Jianxiong Yin, Simon See

[Project Site] [Paper] [Arxiv]

Conferences and Journals

SplatSSC: Decoupled Depth-Guided Gaussian Splatting for Semantic Scene Completion

The 40th Annual AAAI Conference on Artificial Intelligence (AAAI 2026), 2025

Rui Qian*, Haozhi Cao*, Tianchen Deng, Shenghai Yuan, Lihua Xie

[Code] [Arxiv]

GERA: Geometric Embedding for Efficient Point Registration Analysis

International Conference on Robotics and Automation (ICRA), 2025

Geng Li*, Haozhi Cao*, Mingyang Liu, Shenghai Yuan, Jianfei Yang

[Arxiv]

Reliable Spatial-Temporal Voxels For Multi-Modal Test-Time Adaptation

European Conference on Computer Vision (ECCV), 2024

Haozhi Cao, Yuecong Xu, Jianfei Yang, Pengyu Yin, Xingyu Ji, Shenghai Yuan, Lihua Xie

[Code] [Project Site] [Paper] [Arxiv]

Outram: One-shot Global Localization via Triangulated Scene Graph and Global Outlier Pruning

International Conference on Robotics and Automation (ICRA), 2024

Pengyu Yin, Haozhi Cao, Thien-Minh Nguyen, Shenghai Yuan, Shuyang Zhang, Kangcheng Liu, Lihua Xie

[Code] [Paper] [Arxiv] [Video]

MoPA: Multi-Modal Prior Aided Domain Adaptation for 3D Semantic Segmentation

International Conference on Robotics and Automation (ICRA), 2024

Haozhi Cao, Yuecong Xu, Jianfei Yang, Pengyu Yin, Shenghai Yuan, Lihua Xie

[Code] [Paper] [Arxiv] [Video]

Multi-Modal Continual Test-Time Adaptation for 3D Semantic Segmentation

International Conference on Computer Vision (ICCV), 2023

Haozhi Cao*, Yuecong Xu*, Jianfei Yang, Pengyu Yin, Shenghai Yuan, Lihua Xie

[Project Site] [Paper] [Arxiv]

Segregator: Global Point Cloud Registration with Semantic and Geometric Cues

International Conference on Robotics and Automation (ICRA), 2023

Pengyu Yin, Shenghai Yuan, Haozhi Cao, Xingyu Ji, Shuyang Zhang, and Lihua Xie

[Code] [Paper] [Arxiv]

Self-Supervised Video Representation Learning by Video Incoherence Detection

IEEE Transactions on Cybernetics (T-Cyber), 2023

Haozhi Cao*, Yuecong Xu*, Kezhi Mao, Lihua Xie, Jianxiong Yin, Simon See, Qianwen Xu, Jianfei Yang

[Code] [Paper] [Arxiv]

Aligning Correlation Information for Domain Adaptation in Action Recognition

IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2022

Yuecong Xu*, Haozhi Cao*, Kezhi Mao, Zhenghua Chen, Lihua Xie, Jianfei Yang

[Paper] [Arxiv]

Effective Action Recognition with Embedded Key Point Shifts

Pattern Recognition (PR), 2021

Haozhi Cao, Yuecong Xu, Jianfei Yang, Kezhi Mao, Jianxiong Yin, Simon See

[Paper] [Arxiv]