Greetings! Dr Xiaojun Chang is a Senior Lecturer at Vision & Lanugage Group, Department of Data Science and AI, Faculty of Information Technology, Monash University Clayton Campus, Australia. Dr Chang is an ARC Discovery Early Career Researcher Award (DECRA) Fellow between 2019-2021 (awarded in 2018).
Before joining Monash, he was a Postdoc Research Associate in School of Computer Science, Carnegie Mellon University, working with Prof. Alex Hauptmann. He has focused his research on exploring multiple signals (visual, acoustic, textual) for automatic content analysis in unconstrained or surveillence videos. His team has won multiple prizes from international grand challenges which hosted competitive teams from MIT, University of Maryland, Facebook AI Research (FAIR) and Baidu VIS, and aim to advance visual understanding using deep learning. For example, he won the first place in the TrecVID 2019 - Activity Extended Video (ActEV) challenge, which was held by National Institute of Standards and Technology, US.
Dr Chang also has been working on developing deep learning models to automatically annotate the disease labels from multi-source patient data (eg data from medical record) in Intensive Care Units (ICUs). The successful outcome of this project has greatly benefited health care and management in ICU of Royal Brisbane and Women's Hospital, considering that the automated diagnosis code annotation can significantly improve the quality and management of health care for both patients and caregivers. The outcome has been published in IEEE Transactions on Knowledge and Data Engineering in December 2016. Recently, he has successfully developed an automatic report generation system for critically ill COVID-19 patients using deep learning techniques with US public COVID-19 CT scan dataset. He collaborated with researchers from Australian Alliance for Artificial Intelligence in Healthcare on this project. The system achieves state-of-the-art performance on report generation and can generate reports very close to doctor handwritten report.
He received the Ph.D. degree in Centre for Artificial Intelligence & Faculty of Engineering and Information Technology, University of Technology Sydney, under the supervision of Prof. Yi Yang. During his PhD study, he was sequentially mentored by Prof. Feiping Nie and Yaoliang Yu. His research focus in this period was mainly on developing machine learning algorithms and apply them to multimedia analysis and computer vision. He received his master and bachelor degrees from School of Information Science and Technology and School of Physics, both from Northwest University. In this period, his research interests were FPGA and VLSI.
His general research interest is to develop structured machine learning models for computer vision and multimedia tasks. He mainly investigates how to explore the information contained in videos and develop the advanced artificial intelligence systems. Recently, he focuses on the following topics, include:
Video Analysis, including event detection, object detection, segmentation.
Learning with Limited Supervision, including few-shot learning, zero-shot learning.
Vision-Language Grounding, including vision-language navigation, vision-and-dialog navigation, and medical report generation.
Automated Machine Learning (AutoML)
Dr Chang is actively looking for talented and motivated PhD students. The research topics include multimedia, computer vision and vision-language learning. Monash is ranked: 75th globally in the Times Higher Education World University Rankings 2020; 73rd globally and third in Australia in ShanghaiRanking’s Academic Ranking of World Universities 2019; 21st in the World’s Most International Universities in 2017 as released by Times Higher Education.
|May 8th, 2021||Our paper on Neural Architecture Search has been accepted by ICML 2021!|
|April 16th, 2021||Our survey paper on Person Search has been accepted by IJCAI 2021 Survey Track. Congratulations to Xiangtan!|
|April 9th, 2021||Our ICCV workshop "Human Interaction for Robotic Navigation" has been accepted!|
|March 1st, 2021||Two papers accepted by CVPR 2021!|
|January 18th, 2021||Our survey on Neural Architecture Search has been accepted by ACM Computing Surveys!|
|January 13rd, 2021||One paper on multi-agent reinforcement learning has been accepted by ICLR 2021 as spotlight presentation! [pdf]|
|December 14th, 2020||One paper on large-scale multimedia retrieval has been accepted by IEEE Transactions on Multimedia (T-MM)!|
|October 31st, 2020||One paper on Object Tracking accepted by IEEE Transactions on Image Processing (T-IP)!|
|October 27th, 2020||One paper on Neural Architecture Search (NAS) accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI)!|
|September 26th, 2020||Two papers on Neural Architecture Search (NAS) accepted by NeurIPS 2020!|
|August 9th, 2020||A survey on Deep Active Learning is released! [pdf]|
|July 29th, 2020||Paper accepted by ACM MM 2020 on scene graph! Paper title - Memory-Based Network for Scene Graph with Unbalanced Relations.|
|July 11th, 2020||Paper accepted by IEEE Transactions on Image Processing on zero-shot object detection! Paper title - Semantics Preserving Graph Propagation for Zero-Shot Object Detection.|
|July 3rd, 2020||Paper accepted by ECCV 2020 on video object detection! Paper title - Mining Inter-Video Proposal Relations for Video Object Detection.|
|June 19th, 2020||Our work on COVID-19 CT Report Generation was covered by [The Australian], [Mirage News], [ResearchNews], [AZoRobotics] and [Monash IT News]! [AI for Social Good]|
|June 6th, 2020||We have released the first public COVID-19 CT Report dataset! [Project Page] | [pdf]|
|June 1st, 2020||A survey on Neural Architecture Search is released! [arXiv] | [pdf] | [专知]|
|May 16th, 2020||Two papers accepted by KDD 2020!|
|May 16th, 2020||One paper accepted by KDD 2020 on Graph Neural Networks and Time Series Preidiction! Paper title - Connecting the Dots. Multivariate Time Series Forecasting with Graph Neural Networks. [pdf]|
|April 20th, 2020||One paper accepted by IJCAI 2020 on graphical model estimation! Paper title - Quadratic Sparse Gaussian Graphical Model Estimation Method for Massive Variables.|
|April 7th, 2020||I am approved to be promoted to Senior Lecturer with effect from 1 July 2020!|
|April 4th, 2020||One paper accepted by ACL 2020 on multimodal neural machine translation! Paper title - Unsupervised Multimodal Neural Machine Translation with Pseudo Visual Pivoting [pdf]|
|April 3rd, 2020||A survey on Person Search is released! [pdf]|
|April 1st, 2020||A survey on Scene Graph is released! [pdf] [Awesome Paper List]|
|Febuary 23rd, 2020||Six papers accepted by CVPR 2020!|
|Febuary 23rd, 2020||Paper accepted by CVPR 2020 on vision-lanuage navigation! Paper title - Vision-Language Navigation with Self-Supervised Auxiliary Reasoning Tasks [pdf] [DEMO] [Oral]|
|Febuary 23rd, 2020||Paper accepted by CVPR 2020 on zero-shot temporal activity detection! Paper title - ZSTAD Zero-Shot Temporal Activity Detection [pdf]|
|Febuary 23rd, 2020||Paper accepted by CVPR 2020 on person re-identification! Paper title - Unity Style Transfer for Person Re-Identification [pdf]|
|Febuary 23rd, 2020||Paper accepted by CVPR 2020 on nueral architecture search! Paper title - Neural Architecture Search by Block-wisely Distilling Architecture Knowledge [pdf] [code]|
|Feburary 23rd, 2020||Paper accepted by CVPR 2020 on visual-dialog navigation! Paper title - Vision Dialogue Navigation by Exploring Cross-modal Memory [pdf] [code]|
|January 11th, 2020||Paper accepted by WWW 2020 on graph convolutional networks! Paper title - Unsupervised Domain Adaptive Graph Convolutional Networks [pdf]|
|November 23rd, 2019||We got the Best Paper Award from The 15th International Conference on Advanced Data Mining and Applications (ADMA 2019)!|
|November 15th, 2019||We achieved first place in the TRECVID 2019 ActEV Challenge! [DEMO]|
|August 29th, 2019||Demo presentation accepted by ICCV 2019! Title - Traffic Danger Recognition With Surveillance Cameras Without Training Data [DEMO]|
|August 12nd, 2019||Paper accepted by EMNLP/IJCNLP 2019 on multi-modal learning! Paper title - Multi-Head Attention with Diversity for Learning Grounded Multilingual Multimodal Representations [pdf]|
|July 1st, 2019||Paper accepted by ACM MM 2019 on multi-modal learning! Paper title - Annotation Efficient Cross-Modal Retrieval with Adversarial Attentive Alignment [pdf]|
|December 3rd, 2018||I have joined the Faculty of Information Technology, Monash University as a Lecturer (tenure-track Asssitant Professor) and a DECRA Fellow!|
|November 28th, 2018||I have been awarded an Australian Research Council (ARC) Discovery Early Career Researcher Award (DECRA) Fellowship!|
|October 15th, 2018||I will join the Faculty of Information Technology, Monash University as a Lecturer (tenure-track Assistant Professor) in December 2018.|