Skip to menu Skip to content Skip to footer
Associate Professor Jiajun Liu
Associate Professor

Jiajun Liu

Email: 

Overview

Background

Dr. Jiajun Liu is Principal Research Scientist and Science Leader for the Distributed Sensing Systems Group (DSSG) at the CSIRO, and leads the Distributed Intelligence team in the DSSG. He is also an Adjunct Associate Professor@UQ. He received his PhD/BEng from the University of Queensland, Australia, and Nanjing University, China, in 2013 and 2006, respectively.

His research interest covers a range of topics in Machine Learning and Data Science, including efficient neural nets, graph learning, and multimedia/multimodal analytics. At CSIRO he is looking into how to make sensing systems more intelligent and efficient, by developing knowledge distillation and efficient neural architectures to enable efficient AI models on edge devices and distributed sensing applications.

He also serves as a reviewer/TPC member/Area Chair for numerous international journals and conferences, such as IEEE Transactions on Knowledge and Data Engineering, The VLDB Journal, IEEE Transactions on Multimedia, IEEE Transactions on Big Data, Clustering Computing, Ad Hoc Networks, Neurocomputing, Multimedia Systems, ACM Multimedia Conference 14' 21', CIKM 21', PAKDD 17~20', APWeb 16', etc.

Availability

Associate Professor Jiajun Liu is:
Available for supervision

Works

Search Professor Jiajun Liu’s works on UQ eSpace

76 works between 2011 and 2026

21 - 40 of 76 works

2024

Conference Publication

ROLeR: effective Reward Shaping in Offline Reinforcement Learning for Recommender Systems

Zhang, Yi, Qiu, Ruihong, Liu, Jiajun and Wang, Sen (2024). ROLeR: effective Reward Shaping in Offline Reinforcement Learning for Recommender Systems. 33rd ACM International Conference on Information and Knowledge Management (CIKM), Boise, ID USA, 21-25 October 2024. New York, NY USA: Association for Computing Machinery. doi: 10.1145/3627673.3679633

ROLeR: effective Reward Shaping in Offline Reinforcement Learning for Recommender Systems

2024

Conference Publication

Real-time Multi-modal Object Detection and Tracking on Edge for Regulatory Compliance Monitoring

Lim, Jia Syuen, Wang, Ziwei, Liu, Jiajun, Khamis, Abdelwahed, Arablouei, Reza, Barlow, Robert and McAllister, Ryan (2024). Real-time Multi-modal Object Detection and Tracking on Edge for Regulatory Compliance Monitoring. 33rd International Joint Conference on Artificial Intelligence (IJCAI), Jeju, South Korea, 3-9 August 2024. Freiburg, Germany: IJCAI. doi: 10.24963/ijcai.2024/1018

Real-time Multi-modal Object Detection and Tracking on Edge for Regulatory Compliance Monitoring

2024

Conference Publication

Edge deployable online domain adaptation for underwater object detection

Etchegaray, Djamahl, Luo, Yadan, Li, Yang, Do, Brendan, Liu, Jiajun, Huang, Zi and Kusy, Branislav (2024). Edge deployable online domain adaptation for underwater object detection. 2024 International Joint Conference on Neural Networks (IJCNN), Yokohama, Japan, 30 June - 5 July 2024. Piscataway, NJ, United States: IEEE. doi: 10.1109/ijcnn60899.2024.10650705

Edge deployable online domain adaptation for underwater object detection

2024

Conference Publication

DynAmic Token Pruning in plain vision transformers for semantic segmentation

Tang, Quan, Zhang, Bowen, Liu, Jiajun, Liu, Fagui and Liu, Yifan (2024). DynAmic Token Pruning in plain vision transformers for semantic segmentation. 2023 IEEE/CVF International Conference on Computer Vision (ICCV), Paris, France, 1-6 October 2023. Piscataway, NJ United States: Institute of Electrical and Electronics Engineers. doi: 10.1109/ICCV51070.2023.00078

DynAmic Token Pruning in plain vision transformers for semantic segmentation

2024

Conference Publication

GTP-ViT: efficient vision transformers via graph-based token propagation

Xu, Xuwei, Wang, Sen, Chen, Yudong, Zheng, Yanping, Wei, Zhewei and Liu, Jiajun (2024). GTP-ViT: efficient vision transformers via graph-based token propagation. 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, United States, 3-8 January 2024. Piscataway, NJ, United States: IEEE. doi: 10.1109/wacv57701.2024.00016

GTP-ViT: efficient vision transformers via graph-based token propagation

2024

Conference Publication

Why only text: empowering vision-and-language navigation with multi-modal prompts

Hong, Haodong, Wang, Sen, Huang, Zi, Wu, Qi and Liu, Jiajun (2024). Why only text: empowering vision-and-language navigation with multi-modal prompts. 33rd International Joint Conference on Artificial Intelligence (IJCAI), Jeju, South Korea, 3-9 August 2024. Palo Alto, CA, United States: AAAI Press. doi: 10.24963/ijcai.2024/93

Why only text: empowering vision-and-language navigation with multi-modal prompts

2024

Book Chapter

Towards cost-efficient federated multi-agent RL with learnable aggregation

Zhang, Yi, Wang, Sen, Chen, Zhi, Xu, Xuwei, Funiak, Stano and Liu, Jiajun (2024). Towards cost-efficient federated multi-agent RL with learnable aggregation. Advances in knowledge discovery and data mining. (pp. 171-183) Heidelberg, Germany: Springer. doi: 10.1007/978-981-97-2253-2_14

Towards cost-efficient federated multi-agent RL with learnable aggregation

2023

Conference Publication

No token left behind: efficient vision transformer via dynamic token idling

Xu, Xuwei, Li, Changlin, Chen, Yudong, Chang, Xiaojun, Liu, Jiajun and Wang, Sen (2023). No token left behind: efficient vision transformer via dynamic token idling. 36th Australasian Joint Conference on Artificial Intelligence, Brisbane, QLD Australia, 28 November-1 December 2023. Singapore: Springer. doi: 10.1007/978-981-99-8388-9_3

No token left behind: efficient vision transformer via dynamic token idling

2023

Conference Publication

SkySea: connecting satellite, UAV and underwater imagery for benthic habitat mapping

Do, Brendan, Liu, Jiajun, Wang, Ziwei, Kusy, Brano, Merz, Torsten, Steven, Andy, Carlin, Geoffrey, Crosswell, Joseph, Li, Yang, Mortimer, Nicholas, Nayyeri, Fereshteh, Vanderklift, Mat and Wilson, Mark (2023). SkySea: connecting satellite, UAV and underwater imagery for benthic habitat mapping. 31st ACM International Conference on Multimedia, Ottawa, ON Canada, 2 November 2023. New York, NY USA: Association for Computing Machinery. doi: 10.1145/3607834.3616570

SkySea: connecting satellite, UAV and underwater imagery for benthic habitat mapping

2023

Conference Publication

Object detection difficulty: suppressing over-aggregation for faster and better video object detection

Zhang, Bingqing, Wang, Sen, Liu, Yifan, Kusy, Brano, Li, Xue and Liu, Jiajun (2023). Object detection difficulty: suppressing over-aggregation for faster and better video object detection. 31st ACM International Conference on Multimedia, MM 2023, Ottawa, ON Canada, 29 October - 3 November 2023. New York, NY United States: Association for Computing Machinery. doi: 10.1145/3581783.3612090

Object detection difficulty: suppressing over-aggregation for faster and better video object detection

2023

Conference Publication

OCHID-Fi: Occlusion-Robust Hand Pose Estimation in 3D via RF-Vision

Zhang, Shujie, Zheng, Tianyue, Chen, Zhe, Hu, Jingzhi, Khamis, Abdelwahed, Liu, Jiajun and Luo, Jun (2023). OCHID-Fi: Occlusion-Robust Hand Pose Estimation in 3D via RF-Vision. 2023 IEEE/CVF International Conference on Computer Vision (ICCV), Paris, France, 1-6 October 2023. Piscataway, NJ United States: Institute of Electrical and Electronics Engineers. doi: 10.1109/iccv51070.2023.01387

OCHID-Fi: Occlusion-Robust Hand Pose Estimation in 3D via RF-Vision

2023

Conference Publication

Decoupled graph neural networks for large dynamic graphs

Zheng, Yanping, Wei, Zhewei and Liu, Jiajun (2023). Decoupled graph neural networks for large dynamic graphs. 49th International Conference on Very Large Data Bases, Vancouver, BC, Canada, 28 August-1 September 2023. New York, NY United States: Association for Computing Machinery. doi: 10.14778/3598581.3598595

Decoupled graph neural networks for large dynamic graphs

2022

Conference Publication

A real-time edge-AI system for reef surveys

Li, Yang, Liu, Jiajun, Kusy, Brano, Marchant, Ross, Do, Brendan, Merz, Torsten, Crosswell, Joey, Steven, Andy, Tychsen-Smith, Lachlan, Ahmedt-Aristizabal, David, Oorloff, Jeremy, Moghadam, Peyman, Babcock, Russ, Malpani, Megha and Oerlemans, Ard (2022). A real-time edge-AI system for reef surveys. ACM MobiCom '22: The 28th Annual International Conference on Mobile Computing and Networking, Sydney, NSW Australia, 17-21 October 2022. New York, NY, USA: ACM. doi: 10.1145/3495243.3558278

A real-time edge-AI system for reef surveys

2022

Conference Publication

InvisibiliTee: Angle-Agnostic Cloaking from Person-Tracking Systems with a Tee

Li, Yaxian, Zhang, Bingqing, Zhao, Guoping, Zhang, Mingyu, Liu, Jiajun, Wang, Ziwei and Wen, Jirong (2022). InvisibiliTee: Angle-Agnostic Cloaking from Person-Tracking Systems with a Tee. 31st International Conference on Artificial Neural Networks, ICANN 2022, Bristol, United Kingdom, 6–9 September 2022. Cham, Switzerland: Springer. doi: 10.1007/978-3-031-15934-3_14

InvisibiliTee: Angle-Agnostic Cloaking from Person-Tracking Systems with a Tee

2022

Conference Publication

Instant Graph Neural Networks for Dynamic Graphs

Zheng, Yanping, Wang, Hanzhi, Wei, Zhewei, Liu, Jiajun and Wang, Sibo (2022). Instant Graph Neural Networks for Dynamic Graphs. Association for Computing Machinery. doi: 10.1145/3534678.3539352

Instant Graph Neural Networks for Dynamic Graphs

2022

Conference Publication

Integrating Dependency Tree into Self-Attention for Sentence Representation

Ma, Junhua, Li, Jiajun, Liu, Yuxuan, Zhou, Shangbo and Li, Xue (2022). Integrating Dependency Tree into Self-Attention for Sentence Representation. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Singapore, 23-27 May 2022. Piscataway, NJ United States: Institute of Electrical and Electronics Engineers. doi: 10.1109/ICASSP43922.2022.9747221

Integrating Dependency Tree into Self-Attention for Sentence Representation

2022

Journal Article

AP-GAN: Adversarial patch attack on content-based image retrieval systems

Zhao, Guoping, Zhang, Mingyu, Liu, Jiajun, Li, Yaxian and Wen, Ji-Rong (2022). AP-GAN: Adversarial patch attack on content-based image retrieval systems. GeoInformatica, 26 (2), 347-377. doi: 10.1007/s10707-020-00418-7

AP-GAN: Adversarial patch attack on content-based image retrieval systems

2022

Conference Publication

A Novel Policy for Pre-trained Deep Reinforcement Learning for Speech Emotion Recognition

Rajapakshe, Thejan, Rana, Rajib, Khalifa, Sara, Liu, Jiajun and Schuller, Bjorn (2022). A Novel Policy for Pre-trained Deep Reinforcement Learning for Speech Emotion Recognition. Association for Computing Machinery. doi: 10.1145/3511616.3513104

A Novel Policy for Pre-trained Deep Reinforcement Learning for Speech Emotion Recognition

2022

Conference Publication

Improved feature distillation via projector ensemble

Chen, Yudong, Wang, Sen, Liu, Jiajun, Xu, Xuwei, de Hoog, Frank and Huang, Zi (2022). Improved feature distillation via projector ensemble. 36th Conference on Neural Information Processing Systems (NeurIPS 2022), New Orleans, LA, United States, 29 November-1 December 2022. New Orleans, LA, United States: Neural information processing systems foundation.

Improved feature distillation via projector ensemble

2022

Conference Publication

STAR-GNN: Spatial-Temporal Video Representation for Content-Based Retrieval

Zhao, Guoping, Zhang, Bingqing, Zhang, Mingyu, Li, Yaxian, Liu, Jiajun and Wen, Ji-Rong (2022). STAR-GNN: Spatial-Temporal Video Representation for Content-Based Retrieval. IEEE Computer Society. doi: 10.1109/ICME52920.2022.9859598

STAR-GNN: Spatial-Temporal Video Representation for Content-Based Retrieval

Supervision

Availability

Associate Professor Jiajun Liu is:
Available for supervision

Looking for a supervisor? Read our advice on how to choose a supervisor.

Supervision history

Current supervision

Completed supervision

Media

Enquiries

For media enquiries about Associate Professor Jiajun Liu's areas of expertise, story ideas and help finding experts, contact our Media team:

communications@uq.edu.au