*equal contribution ^corresponding

Please refer to [Google Scholar]  for the full publication list

Reference: [CORE] Conference Ranking and [JCR] Journal Ranking

Preprint

[Arxiv’24] "Group-aware Parameter-efficient Updating for Content-Adaptive Neural Video Compression" 

Zhenghao Chen, Luping Zhou, Zhihao Hu, Dong Xu

arXiv: 2405.04274, 2024 [paper] 


[Arxiv'24] "WEATHER-5K: A Large-scale Global Station Weather Dataset Towards Comprehensive Time-series Forecasting Benchmark"

Tao Han, Song Guo, Zhenghao Chen, Wanghan Xu, Lei Bai

arXiv: 2406.14399, 2024 [code] [paper]


[Arxiv’24] "CRA5: Extreme Compression of ERA5 for Portable Global Climate and Weather Research via an Efficient Variational Transformer" 

Tao Han, Zhenghao Chen, Song Guo, Wanghan Xu, Lei Bai

arXiv: 2405.03376, 2024 [code] [paper]


[Arxiv’24] "PoinTramba: A Hybrid Transformer-Mamba Framework  for Point Cloud Analysis" 

Zicheng Wang,  Zhenghao Chen, Yiming Wu, Zhen Zhao, Luping Zhou, Dong Xu

arXiv: 2405.15463, 2024 [code] [paper] 


[ArXiv'24] "Improving CXR Bone Suppression by Exploiting Domain-level and Instance-level Information"

Ling Yang,  Zhenghao Chen^ (Corresponding Author),  Kaisiyuan Wang, Luping Zhou

Under Reviewing (Submitted to T-MI)


[Arxiv’24] "MedXChat: A Unified Multimodal Large Language Model Framework towards CXRs Understanding and Generation" 

Ling Yang, Zhanyu Wang, Zhenghao Chen, Xinyu Liang, Luping Zhou

arXiv: 2312.02233, 2024 [paper] 


[ArXiv'23] "Neural Vector Fields: Generalizing Distance Vector Fields by Codebooks and Zero-Curl Regularization"

Xianghui Yang, Guosheng Lin, Zhenghao Chen, Luping Zhou 

arXiv: 2309.01512, 2023 [paper] 

Journal

[T-IP'22] "Exploiting Intra-slice and Inter-slice Redundancy for Learning-based Lossless Volumetric Image Compression"

Zhenghao Chen, Shuhang Gu, Guo Lu, Dong Xu 

IEEE TRANSACTIONS ON IMAGE PROCESSING (T-IP), 2022 [paper] (JCR Q1) 

Highlight: the first end-to-end optimized learning framework for lossless 3D volumetric image compression (e.g., 3D Medical MRI/CT Volume,  Hyperspectral Image)

Conference

[AAAI'24] "UFDA: Universal Federated Domain Adaptation with Practical Assumption"

Xinhui Liu, Zhenghao Chen, Luping Zhou, Dong Xu, Wei Xi, Gairui Bai, Yihan Zhao,  Jizhong Zhao

Proceedings of the annual AAAI Conference on Artificial Intelligence (AAAI), 2024 [paper] (CORE A*) 


[MM'23]  "Neural Video Compression with Spatio-Temporal Cross-Covariance Transformers"

Zhenghao Chen, Lucas Relic, Roberto Azevedo, Yang Zhang, Markus Gross, Dong Xu, Luping Zhou, Christopher Schroers

Proceedings of the ACM International Conference on Multimedia (MM), 2023, 8543-8551 [paper] (CORE A*) 


[MM'23]  "ICMH-Net: Neural Image Compression Towards both Machine Vision and Human Vision"

Lei Liu, Zhihao Hu, Zhenghao Chen, Dong Xu

Proceedings of the ACM International Conference on Multimedia (MM), 2023, 8047–8056 [paper]  (CORE A*)


[CVPR'23] "Neural Vector Fields: Implicit Representation by Explicit Learning"

 Xianghui Yang, Guosheng Lin, Zhenghao Chen, Luping Zhou 

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023, 16727-16738 [code][paper] (CORE A*) 


[ECCV'22] "Improving RGB-D Point Cloud Registration by Learning Multi-scale Local Linear Transformation"

Ziming Wang, Xiaoliang Huo, Zhenghao Chen, Jing Zhang, Lu Sheng, Dong Xu

Proceedings of the European Conference on Computer Vision (ECCV), 2022, 175-191 [code][paper] (CORE A*)


[CVPR'22] "LSVC: A Learning-based Stereo Video Compression Framework"

Zhenghao Chen, Guo Lu, Zhihao Hu, Shan Liu, Wei Jiang, Dong Xu

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022, 6073-6082 [paper] (CORE A*) 

Highlight: the first end-to-end optimized learning framework for multi-view/stereo video compression (2 strong accepts + 1 weak accept)


[ICME'21] "Improving Facial Attribute Recognition by Group and Graph Learning"

Zhenghao Chen^ (Corresponding Author), Shuhang Gu, Feng Zhu,  Jing Xu, Rui Zhao.  

IEEE International Conference on Multimedia & Expo (ICME), 2021, Oral, 1-6 [paper]  (CORE A)


[ECCV'20] "Improving Deep Video Compression by Resolution-adaptive Flow Coding" 

Zhihao Hu*, Zhenghao Chen* (Equal Contribution), Dong Xu, Guo Lu, Wanli Ouyang, Shuhang Gu. 

Proceedings of the European Conference on Computer Vision (ECCV), 2020, Oral (2% acceptance rate), 193-209 [paper] (CORE A*)


[CVPR'20] "Unifying Spatial-Temporal Graph Convolutions with Disentangled Multi-Scale Aggregators for Skeleton-Based Action Recognition" 

Ziyu Liu, Hongwen Zhang, Zhenghao Chen, Zhiyong Wang, Wanli Ouyang.

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020, Oral (5.7% acceptance rate), 143-152 [code] [paper] (CORE A*)

Workshop

[IJCAI'24, GLOW] "Towards Point Cloud Compression for Machine Perception: A Simple and Strong Baseline by Learning the Octree Depth Level Predictor"

Lei Liu, Zhihao Hu, Zhenghao Chen

International Joint Conference on Artificial Intelligence (IJCAI) 2024, 2nd Workshop on International Workshop on Generalizing from Limited Resources in the Open World (GLOW) [paper]

Patent

Zhenghao Chen, Roberto Azevedo, Christopher Schroers, Yang Zhang, Lucas Relic

Submitted to US Patent and Trademark Office Under DISYP009


Zhenghao Chen, Jing Xu, Feng Zhu, Rui Zhao 

WO2021063056A1, TWI753588B, JP2022547595A, KR20220044828A, CN111339813B


Zhenghao Chen, Jing Xu, Rui Zhao

US11455830B2, TWI717923B, SG11202006192YA,  JP7038829B2, WO2020155606A1, KR102390580B1, CN109800737B

Thesis

[USYD Ph.D. Thesis] "Deep Learning for Visual Data Compression"  Zhenghao Chen. The University of Sydney, 2022 [thesis]