Dr Yuanbo Wu

Uwch-ddarlithydd

Computer Science

l.y.wu@abertawe.ac.uk

223
Ail lawr
Y Ffowndri Gyfrifiadol
Campws y Bae

Ar gael ar gyfer Goruchwyliaeth Ôl-raddedig

Dolenni Ymchwil

https://orcid.org/0000-0001-6119-058X

Google Scholar

ResearcherID

Trosolwg

Derbyniodd Dr Lin Yuanbo Wu ei PhD o Brifysgol New South Wales, Kensington, Sydney, Awstralia. Mae ganddi ddiddordebau ymchwil eang o ran tasgau golwg cyfrifiadurol a dysgu peirianyddol gyda chymhelliad cryf i fynd i'r afael â heriau'r byd go iawn ac mae wedi cyhoeddi'n helaeth dros 70 o erthyglau ymchwil a adolygwyd gan gymheiriaid (gan gynnwys dwy bennod mewn llyfr) mewn cyfnodolion a thrafodion o bwys. Arbenigedd Dr Wu yw deall cynnwys fideo (megis segmentu enghreifftiau /panoptig/gwrthrychau, canfod/olrhain gwrthrychau mewn fideo), ail-nodi targedau, dysgu fesul cam, deallusrwydd artiffisial cynhyrchiol, a datblygiadau deallusrwydd artiffisial ar gyfer astudiaethau meddygol. Derbyniodd Wobr Twf 2021 yn 4edd Gystadleuaeth Arloesi ac Entrepreneuriaeth Eureka (Eureka IIEC 2021, Melbourne, Awstralia). Ar hyn o bryd mae Dr Wu yn Olygydd Cysylltiol IEEE Trans on Neural Networks and Learning Systems (IF: 14.255), IEEE Trans on Multimedia (IF: 8.182), IEEE Trans on Big Data (IF: 4.271), a Pattern Recognition Letters (IF: 4.757). Fe'i gwahoddwyd i fod yn Gadeirydd Ardal gyda ACM Multimedia 2023 (Ottawa), 2022 (Lisbon). Mae Dr Wu yn Uwch-aelod o’r IEEE.

Meysydd Arbenigedd

Gweld â chymorth cyfrifiadur
Canfod gwrthrych
Olrhain sawl gwrthrych
Segmentu enghreifftiau o delweddau a gwrthrych a segmentu panoptig
Dysgu peirianyddol
Deallusrwydd artiffisial ar gyfer biowyddoniaeth
Cynhyrchu fideos
Amcangyfrif gwrthrychau 6D

Uchafbwyntiau Gyrfa

Ymchwil

Mae Lin yn canolbwyntio ar heriau ymchwil sy'n torri tir newydd mewn amrywiaeth o feysydd gyda golwg cyfrifiadurol, dysgu peirianyddol, a disgyblaethau deallusrwydd artiffisial a’r biowyddorau sy'n dod i'r amlwg ac sy'n mynd y tu hwnt i ffiniau. Mae cyfleoedd presennol yn cael eu hamlinellu gyda chynhyrchu/golygu fideos, segmentu esiamplau ar ddelweddau a fideos, cynhyrchu/rhagfynegi strwythur proteinau, amcangyfrif gwrthrychau 6D ac ail-adnabod targedau mewn gwaith goruchwylio.

Dyma her deallusrwydd artiffisial cynhyrchiol cynllun ymchwil archwiliol Lin: A Tracking-Discriminating Deep Generative Model for Real-Time Anomaly Detection in Videos, wedi'i ariannu'n llawn gan Airbus Endeavr, Cymru (Mai 2023-Ebrill 2024, £150,000), gydag estyniad posib o fis Mai 2024-Ebrill 2026 (tua £300,000).

Cyhoeddiadau

Uchafbwyntiau Ymchwil

Yuan, X., Zhang, Z., Wang, X., & Wu, Y. (2023). Semantic-Aware Adversarial Training for Reliable Deep Hashing Retrieval. IEEE Transactions on Information Forensics and Security, 18, 4681-4694.
https://doi.org/10.1109/tifs.2023.3297791, SU Repository: https://cronfa.swan.ac.uk/Record/cronfa64127
Wu, Y., Liu, L., Wang, Y., Zhang, Z., Boussaid, F., Bennamoun, M., & Xie, X. (2023). Learning Resolution-Adaptive Representations for Cross-Resolution Person Re-Identification. IEEE Transactions on Image Processing, 32, 4800-4811.
https://doi.org/10.1109/tip.2023.3305817, SU Repository: https://cronfa.swan.ac.uk/Record/cronfa64124
http://dx.doi.org/10.1109/tip.2023.3305817
Liu, D., Wu, L., Li, B., Boussaid, F., Bennamoun, M., Xie, X., Liang, C., & Wu, Y. (2024). Jacobian norm with Selective Input Gradient Regularization for interpretable adversarial defense. Pattern Recognition, 145, 109902
https://doi.org/10.1016/j.patcog.2023.109902, SU Repository: https://cronfa.swan.ac.uk/Record/cronfa64108
http://dx.doi.org/10.1016/j.patcog.2023.109902
Wu, Y., Hong, R., Wang, Y., & Wang, M. (2019). Cross-Entropy Adversarial View Adaptation for Person Re-identification. IEEE Transactions on Circuits and Systems for Video Technology, 1-1.
https://doi.org/10.1109/tcsvt.2019.2909549, SU Repository: https://cronfa.swan.ac.uk/Record/cronfa63560
http://dx.doi.org/10.1109/tcsvt.2019.2909549
Liu, D., Wu, Y., Hong, R., Ge, Z., Shen, J., Boussaid, F., & Bennamoun, M. (2023). Generative Metric Learning for Adversarially Robust Open-world Person Re-Identification. ACM Transactions on Multimedia Computing, Communications, and Applications, 19(1), 1-19.
https://doi.org/10.1145/3522714, SU Repository: https://cronfa.swan.ac.uk/Record/cronfa63558
http://dx.doi.org/10.1145/3522714
Wu, Y., Liu, D., Guo, X., Hong, R., Liu, L., & Zhang, R. (2022). Multi-scale Spatial Representation Learning via Recursive Hermite Polynomial Networks. In Proceedings of the Thirty-First International Joint Conference on Artificial IntelligenceInternational Joint Conferences on Artificial Intelligence Organization.
https://doi.org/10.24963/ijcai.2022/204, SU Repository: https://cronfa.swan.ac.uk/Record/cronfa63557
http://dx.doi.org/10.24963/ijcai.2022/204
Wu, Y., Wang, Y., Yin, H., Wang, M., & Shao, L. (2019). Few-Shot Deep Adversarial Learning for Video-Based Person Re-Identification. IEEE Transactions on Image Processing, 29, 1233-1245.
https://doi.org/10.1109/tip.2019.2940684, SU Repository: https://cronfa.swan.ac.uk/Record/cronfa63201
http://dx.doi.org/10.1109/tip.2019.2940684
Wu, Y., Wang, Y., Gao, J., Wang, M., Zha, Z., & Tao, D. (2021). Deep Coattention-Based Comparator for Relative Representation Learning in Person Re-Identification. IEEE Transactions on Neural Networks and Learning Systems, 32(2), 722-735.
https://doi.org/10.1109/tnnls.2020.2979190, SU Repository: https://cronfa.swan.ac.uk/Record/cronfa63200
http://dx.doi.org/10.1109/tnnls.2020.2979190
Lin, Z., Zhang, D., Shi, D., Xu, R., Tao, Q., Wu, Y., He, M., & Ge, Z. (2023). Contrastive pre-training and linear interaction attention-based transformer for universal medical reports generation. Journal of Biomedical Informatics, 138, 104281
https://doi.org/10.1016/j.jbi.2023.104281, SU Repository: https://cronfa.swan.ac.uk/Record/cronfa63181
Liu, D., Wu, Y., Zheng, F., Liu, L., & Wang, M. (2022). Verbal-Person Nets: Pose-Guided Multi-Granularity Language-to-Person Generation. IEEE Transactions on Neural Networks and Learning Systems, 1-13.
https://doi.org/10.1109/tnnls.2022.3151631, SU Repository: https://cronfa.swan.ac.uk/Record/cronfa63180
http://dx.doi.org/10.1109/tnnls.2022.3151631

Holl Ymchwil

Erthyglau Cylchgronau

Liu, D., Wu, L., Li, B., Boussaid, F., Bennamoun, M., Xie, X., Liang, C., & Wu, Y. (2024). Jacobian norm with Selective Input Gradient Regularization for interpretable adversarial defense. Pattern Recognition, 145, 109902
https://doi.org/10.1016/j.patcog.2023.109902, SU Repository: https://cronfa.swan.ac.uk/Record/cronfa64108
http://dx.doi.org/10.1016/j.patcog.2023.109902
Wu, Y., Liu, L., Wang, Y., Zhang, Z., Boussaid, F., Bennamoun, M., & Xie, X. (2023). Learning Resolution-Adaptive Representations for Cross-Resolution Person Re-Identification. IEEE Transactions on Image Processing, 32, 4800-4811.
https://doi.org/10.1109/tip.2023.3305817, SU Repository: https://cronfa.swan.ac.uk/Record/cronfa64124
http://dx.doi.org/10.1109/tip.2023.3305817
Yuan, X., Zhang, Z., Wang, X., & Wu, Y. (2023). Semantic-Aware Adversarial Training for Reliable Deep Hashing Retrieval. IEEE Transactions on Information Forensics and Security, 18, 4681-4694.
https://doi.org/10.1109/tifs.2023.3297791, SU Repository: https://cronfa.swan.ac.uk/Record/cronfa64127
Lin, Z., Zhang, D., Shi, D., Xu, R., Tao, Q., Wu, Y., He, M., & Ge, Z. (2023). Contrastive pre-training and linear interaction attention-based transformer for universal medical reports generation. Journal of Biomedical Informatics, 138, 104281
https://doi.org/10.1016/j.jbi.2023.104281, SU Repository: https://cronfa.swan.ac.uk/Record/cronfa63181
Hu, C., Xie, X., & Wu, Y. (2023). Face reenactment via generative landmark guidance. Image and Vision Computing, 130, 104611
https://doi.org/10.1016/j.imavis.2022.104611, SU Repository: https://cronfa.swan.ac.uk/Record/cronfa62159
Liu, D., Wu, Y., Hong, R., Ge, Z., Shen, J., Boussaid, F., & Bennamoun, M. (2023). Generative Metric Learning for Adversarially Robust Open-world Person Re-Identification. ACM Transactions on Multimedia Computing, Communications, and Applications, 19(1), 1-19.
https://doi.org/10.1145/3522714, SU Repository: https://cronfa.swan.ac.uk/Record/cronfa63558
http://dx.doi.org/10.1145/3522714
Ji, Z., Hu, J., Liu, D., Wu, Y., & Zhao, Y. (2023). Asymmetric Cross-Scale Alignment for Text-Based Person Search. IEEE Transactions on Multimedia, 25, 7699-7709.
https://doi.org/10.1109/tmm.2022.3225754, SU Repository: https://cronfa.swan.ac.uk/Record/cronfa62251
Wu, Y., Liu, D., Zhang, W., Chen, D., Ge, Z., Boussaid, F., Bennamoun, M., & Shen, J. (2022). Pseudo-Pair Based Self-Similarity Learning for Unsupervised Person Re-Identification. IEEE Transactions on Image Processing, 31, 4803-4816.
https://doi.org/10.1109/tip.2022.3186746, SU Repository: https://cronfa.swan.ac.uk/Record/cronfa61771
Liu, D., Wu, Y., Zheng, F., Liu, L., & Wang, M. (2022). Verbal-Person Nets: Pose-Guided Multi-Granularity Language-to-Person Generation. IEEE Transactions on Neural Networks and Learning Systems, 1-13.
https://doi.org/10.1109/tnnls.2022.3151631, SU Repository: https://cronfa.swan.ac.uk/Record/cronfa63180
http://dx.doi.org/10.1109/tnnls.2022.3151631
Wu, Y., Wang, Y., Gao, J., Wang, M., Zha, Z., & Tao, D. (2021). Deep Coattention-Based Comparator for Relative Representation Learning in Person Re-Identification. IEEE Transactions on Neural Networks and Learning Systems, 32(2), 722-735.
https://doi.org/10.1109/tnnls.2020.2979190, SU Repository: https://cronfa.swan.ac.uk/Record/cronfa63200
http://dx.doi.org/10.1109/tnnls.2020.2979190
Wu, Y., Wang, Y., Yin, H., Wang, M., & Shao, L. (2019). Few-Shot Deep Adversarial Learning for Video-Based Person Re-Identification. IEEE Transactions on Image Processing, 29, 1233-1245.
https://doi.org/10.1109/tip.2019.2940684, SU Repository: https://cronfa.swan.ac.uk/Record/cronfa63201
http://dx.doi.org/10.1109/tip.2019.2940684
Wu, Y., Hong, R., Wang, Y., & Wang, M. (2019). Cross-Entropy Adversarial View Adaptation for Person Re-identification. IEEE Transactions on Circuits and Systems for Video Technology, 1-1.
https://doi.org/10.1109/tcsvt.2019.2909549, SU Repository: https://cronfa.swan.ac.uk/Record/cronfa63560
http://dx.doi.org/10.1109/tcsvt.2019.2909549

Cyfraniadau Cynadleddau

Wu, Y., Liu, D., Guo, X., Hong, R., Liu, L., & Zhang, R. (2022). Multi-scale Spatial Representation Learning via Recursive Hermite Polynomial Networks. In Proceedings of the Thirty-First International Joint Conference on Artificial IntelligenceInternational Joint Conferences on Artificial Intelligence Organization.
https://doi.org/10.24963/ijcai.2022/204, SU Repository: https://cronfa.swan.ac.uk/Record/cronfa63557
http://dx.doi.org/10.24963/ijcai.2022/204

Goruchwyliaeth

An Advanced Quantitative Framework for Unsupervised Multi-Object Instance Segmentation: Integrating Latent Dynamics, Stochastic Geometry, Algebraic Topology, Persistent Homology and more (cyfredol)

PhD

Goruchwyliwr arall: Prof Xianghua Xie
The Assessment and Spotting of Generative Artificial Intelligence (cyfredol)

PhD

Goruchwyliwr arall: Prof Xianghua Xie
Enhancing the designability and functional efficacy of the anti-body using deep learning methods. (cyfredol)

MSc

Goruchwyliwr arall: Dr Benjamin Mora
Generative AI in Protein Design: De novo Protein Design and Multi-Motif Scaffolding (cyfredol)

MSc

Goruchwyliwr arall: Dr Jonathan Mullins

Modiwlau a Addysgir

CS-109 Technologies for Information Presentation

This module is about the technologies and markup languages that make various forms of data presentation possible. It will explore web-based presentation languages including HTML, XML and CSS, text presentation languages including LaTeX, and mathematical / graphical presentation through R. After studying this module, students will be able to build web sites, produce professional-quality reports and typeset and visualize mathematical formulae and data, using the appropriate graphs for the data. The students will also be able to produce a crawler / scraper that can pull data from websites automatically for analysis.
CSC009 Technologies for Information Presentation

This module is about the technologies and markup languages that make various forms of data presentation possible. It will explore web-based presentation languages including HTML, XML and CSS, text presentation languages including LaTeX, and mathematical / graphical presentation through R. After studying this module, students will be able to build web sites, produce professional-quality reports and typeset and visualize mathematical formulae and data, using the appropriate graphs for the data. The students will also be able to produce a crawler / scraper that can pull data from websites automatically for analysis.
CSCM77 Computer Vision and Deep Learning

This module introduces students to the important and modern topics and concepts of computer vision and deep learning, including image processing, feature extraction, camera calibration, stereo vision, motion and tracking, recognition, deep neural network and their application to vision problems. It teaches techniques that are used to understand and interpret the contents of images and videos and dissects state-of-the-art vision systems, such as Microsoft Kinect. Practical examples in Python are provided throughout the lectures.

Dr Yuanbo Wu

Cyfeiriad ebost

Dolenni Ymchwil

Trosolwg

Meysydd Arbenigedd

Uchafbwyntiau Gyrfa

Cyhoeddiadau

Uchafbwyntiau Ymchwil

Holl Ymchwil

Erthyglau Cylchgronau

Cyfraniadau Cynadleddau

Goruchwyliaeth

An Advanced Quantitative Framework for Unsupervised Multi-Object Instance Segmentation: Integrating Latent Dynamics, Stochastic Geometry, Algebraic Topology, Persistent Homology and more (cyfredol)

The Assessment and Spotting of Generative Artificial Intelligence (cyfredol)

Enhancing the designability and functional efficacy of the anti-body using deep learning methods. (cyfredol)

Generative AI in Protein Design: De novo Protein Design and Multi-Motif Scaffolding (cyfredol)

Modiwlau a Addysgir

CS-109 Technologies for Information Presentation

CSC009 Technologies for Information Presentation

CSCM77 Computer Vision and Deep Learning