Professor Xuefeng Liang

School of Artifical Intelligent 

Address: Main Building, Zone II, 419

Email: xliang@xidian.edu.cn

Tel:

I am currently with the School of Artificial Intelligence, Xidian University, China. In general, my research interests are visual perception & cognition, computer vision and intelligent algorithms. I received my Ph.D. from Japan Advanced Institute of Science and Technology in 2006. During the three-year program, I explored computational geometry algorithms on a variety of vision problems. Afterward, I moved to National Institute of Advanced Industrial Science and Technology at Tsukuba, and worked on robotics vision. From 2008, I simultaneously worked at University College London & Queen Mary University of London for the research of visual perception on motion. From 2010, I was assigned as Associate Professor at Graduate School of Informatics, Kyoto University. In 2018, I joined Xidian University.

1. Our paper "Leveraging Knowledge of Modality Experts for Incomplete Multimodal Learning", has been accepted by ACM MM 2024 (Top conference in Multimedia, Oral presentation, Honorable Mention Award ！！！4385 submissions, 1149 papers were accepted，1 best paper award, 2 best student paper awards, 7 Honorable Mention Awards.
2. Our paper "Interpret Positional Information in Perspective of Word Order", has been accepted by ACL 2023 (Top conference in NLP).
3. Our paper "Inferring Affective Experience from the Big Picture Metaphor: A Two-dimensional Visual Breadth Model", has been accepted by CVPR 2023  Workshop ABAW, Congratulations, J.Y. Duan and S. Tong! (Top conference in AI).
4. Our paper "Adaptive Mask Co-optimization for Modal Dependence in Multimodal Learning", has been accepted by ICASSP 2023 (Oral presentation, Acceptance rate: 5%), Congratulations, Y. Zhou, S.Q. Zheng and H.J. Xuan! (Top conference in Speech).
5. Our paper, "Multi-pattern Mining using Pattern-level Contrastive Learning and Multi-pattern Activation Map", has been accepted by IEEE Transactions on Neural Networks and Learning Systems (IF 14.255)， Congratulations! My students. Multi-pattern Mining is a new vision task that includes classification and clustering together. What an interesting task! Welcome to read [Link]. 
6. Our paper "Unsupervised Outlier Detection using Memory and Contrastive Learning", has been accepted by  IEEE Transactions on Image Processing (IF 11.041).
7. Our paper "A Joint Framework for Mining Discriminative and Frequent Visual Representation", has been accepted by Neurocomputing (ELSEVIER) IF(5.719). Congratulations, Zhou Ying, Xiaosong Zhang, Zhihui Liang, Chenyang Wang, and Yifei Yin! [Link]
8. Our paper "Multi-Classifier Interactive Learning for Ambiguous Speech Emotion Recognition" has been accepted by IEEE/ACM Transactions on Audio, Speech and Language Processing, Congratulations, Zhou Ying, Yin Yifei, Yao Longshan! [Link]
9. Our paper “CALLip: Lipreading using Contrastive and Attribute Learning" has been accepted by ACMMM 2021, Congratulations, my student! 
10. The 9th International Conference on Information Technology: IoT and Smart City, ICIT 2021 will take place in Guangzhou, China.
11. Our paper “Progressive Co-teaching for Ambiguous Speech Emotion Recognition” has been accepted by ICASSP2020, Congratulations, my students!
12. Our paper ``Element-wise Feature Relation Learning Network for Cross-Spectral Image Patch Matching\'\', has been accepted by IEEE Trans. on Neural Networks and Learning Systems, IF(8.793).
13. My collaborating research with Kyoto University "Putative Ratios of Facial Attractiveness in a Deep Neural Network" has been accepted by Vision Research. It is one of my representative works in recent years. [Link]
14. I serve as the conference chair of  The 8th International Conference on Information Technology: IoT and Smart City, ICIT 2020 will take place on December 25-27, 2020 in Xi\'an, China.
15. Our paper “Jointly Discriminating and Frequent Visual Representation Mining” has been accepted by ACCV2020, Congratulations, my students!
16. Our paper “UAV Autonomous Target Search Based on Deep Reinforcement Learning in Complex Disaster Scene” has been accepted by IEEE ACCESS, IF(4.098), 2019.
17. Our two papers have been accepted by ICCV2019，where "AFD-Net: Aggregated Feature Difference Learning for Cross-Spectral Image Patch Matching" is accepted as Oral, Congratulations, my students! (Oral ratio 4.3%)
18. We orgnize a workshop "Interpretable & Reasonable Deep Learning and its Applications (IReDLiA)" in conjunction with IJCAI-ECAI 2018.
19. I received an academic Award of Governors of Kyoto Prefecture, Japan.
20. I serve as an expert advisor for the Chinese AI Research Association (Japan).

1. The 7th International Conference on Information Technology: IoT and Smart City (ICIT 2019),  December 20-23, 2019 in Shanghai, China.
2. The 2nd International Conference on Data Science and Information Technology, July 19-21, 2019, in Seoul, Korea.
3. International workshope "Interpretable & Reasonable Deep Learning and its Applications (IReDLiA)" in conjunction with IJCAI-ECAI 2018.
4. International Conference on Video and Image Processing. December 27-29, 2017, at Nanyang Technological University.
5. Kyoto University & Queen Mary University of London Joint Workshop, Intelligent Sensing on Media Data. March 26~27, 2015, at Kyoto University.
6. Kyoto University & University College London Workshop on Perception of Motion and Pattern. March 12, 2013, at Kyoto University.
7. Kyoto University & Queen Mary University of London Symposium on Intelligent Sensing. March 18~20, 2013, at Kyoto University.

1. “Modelling and Sensing Scary Motions on Road”@ 2023 International Conference on Intelligent Perception and Computer Vision (CIPCV 2023), 19-21, May, 2023.

2. "Learning Features for Image Patch Matching", Southern University of Science and Technology, Oct. 2019, Shenzhen, China.

3. "View Angles may Reveal Your Mood: A psychological explanation and an example in the real world"，Tsinghua University, Institute for Interdisciplinary Information Science, May, 2019, Beijing, China.

4. "View Angles may Reveal Your Mood: A psychological explanation and an example in the real world", International Conference of Union of Mathematical Imaging (UMI2019), May, 2019, Beijing, China.

5. "Learning the Shared Feature from Cross Domains for Vision Applications & Tackling Data Issues in the Real World Scenario", @ International Conference on Information Technology, HongKong, (Dec. 2018).
6. "Happier Mood Trigger Bigger Pictures", @ International Workshop on Bio-inspired Systems, Bio-electronics, Machine Intelligence, Taiwan, (Jan, 2018). [Link]
7. "Viewing Bigger Pictures Promotes Happier Mood: a psychological explanation and an example in the wild", @ International Conference on Video and Image Processing, Singapore, (Dec. 2017). [Link]
8. "Visual Attention and Emotion", @ The 19th Academic Symposium of the Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, China, (Oct. 2017). [Link]
9. "Studying Visual Attention in Image and Video", @ The 9th International Conference on Intelligent Robotics and Applications (Aug. 2016). [Link]
10. "Modeling visual attention in image and video", @ Kyoto-Bordeaux mini-symposium, Japan (Feb. 2016).
11. "How does Robot Understand the Visual Motion?", @ AcademicDay, Japan (Oct. 2015)
12. "Motion Segmentation in Complex Video", @ Tianjin University, China (Aug. 2015).
13. "Dynamic saliency detection", @ Xi\\\\\\\\\\\\\\\\\\'dian University, China (Jul. 2014).
14. "Salient Motion Detection from Complex Video using Potential Surface", @ Seoul National University, Korea (Sept.2013).
15. "Salient Information, from Static to Dynamic", @ National TsingHua University, Taiwan (Mar. 2013).