Dr Mahsa Baktashmotlagh
ARC Future Fellow
School of Electrical Engineering and Computer Science
+61 7 336 57597
Researcher biography
Mahsa Baktashmotlagh is currently a Senior Lecturer at UQ with a research focus, developing machine learning techniques applied in: Visual data analysis (Visual domain generalization, Video classification), Road traffic networks (Mining large scale road traffic networks), Biomedical data (Antibacterial activity prediction), Cyber Security (Detecting websites defacement), and Finance (Hedging foreign exchange trading risks).
| Featured projects | Duration |
|---|---|
| ML and data mining | |
| Using ML to detect cyber-attacks | |
| Interpretable machine learning models for medical imaging |
Book Chapters
Rahman, Mohammad Mahfujur, Fookes, Clinton, Baktashmotlagh, Mahsa and Sridharan, Sridha (2020). On minimum discrepancy estimation for deep domain adaptation. Domain adaptation for visual understanding. (pp. 81-94) edited by Richa Singh, Mayank Vatsa, Vishal M. Patel and Nalini Ratha. Cham, Switzerland: Springer International Publishing. doi: 10.1007/978-3-030-30671-7_6
Baktashmotlagh, Mahsa, Harandi, Mehrtash and Salzmann, Mathieu (2017). Learning Domain Invariant Embeddings by Matching Distributions. Domain Adaptation in Computer Vision Applications. (pp. 95-114) Cham, Switzerland: Springer. doi: 10.1007/978-3-319-58347-1_5
Journal Articles
Layeghy, Siamak, Baktashmotlagh, Mahsa and Portmann, Marius (2023). DI-NIDS: domain invariant network intrusion detection system. Knowledge-Based Systems, 273 110626, 110626. doi: 10.1016/j.knosys.2023.110626
Luo, Yadan, Wang, Zijian, Chen, Zhuoxiao, Huang, Zi and Baktashmotlagh, Mahsa (2023). Source-free progressive graph learning for open-set domain adaptation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45 (9), 1-16. doi: 10.1109/tpami.2023.3270288
Luo, Yadan, Huang, Zi, Chen, Hongxu, Yang, Yang, Yin, Hongzhi and Baktashmotlagh, Mahsa (2021). Interpretable signed link prediction with signed infomax hyperbolic graph. IEEE Transactions on Knowledge and Data Engineering, PP (99), 1-1. doi: 10.1109/TKDE.2021.3139035
Al-Saffar, Ahmed, Bialkowski, Alina, Baktashmotlagh, Mahsa, Trakic, Adnan, Guo, Lei and Abbosh, Amin (2020). Closing the gap of simulation to reality in electromagnetic imaging of brain strokes via deep neural networks. IEEE Transactions on Computational Imaging, 7 9274540, 13-21. doi: 10.1109/tci.2020.3041092
Rahman, Mohammad Mahfujur, Fookes, Clinton, Baktashmotlagh, Mahsa and Sridharan, Sridha (2020). Correlation-aware adversarial domain adaptation and generalization. Pattern Recognition, 100 107124. doi: 10.1016/j.patcog.2019.107124
Cunningham-Nelson, Samuel, Baktashmotlagh, Mahsa and Boles, Wageeh (2019). Visualizing student opinion through text analysis. IEEE Transactions on Education, 62 (4) 8759085, 305-311. doi: 10.1109/TE.2019.2924385
Baktashmotlagh, Mahsa, Harandi, Mehrtash and Salzmann, Mathieu (2016). Distribution-matching embedding for visual domain adaptation. Journal of Machine Learning Research, 17 108, 1-30.
Carstens, Bodil B., Berecki, Geza, Daniel, James T., Lee, Han Siean, Jackson, Kathryn A. V., Tae, Han-Shen, Sadeghi, Mahsa, Castro, Joel, O'Donnell, Tracy, Deiteren, Annemie, Brierley, Stuart M., Craik, David J., Adams, David J. and Clark, Richard J. (2016). Structure-Activity Studies of Cysteine-Rich α-Conotoxins that Inhibit High Voltage-Activated Calcium Channels via GABAB Receptor Activation Reveal a Minimal Functional Motif. Angewandte Chemie - International Edition, 55 (15), 4692-4696. doi: 10.1002/anie.201600297
Baktashmotlagh, Mahsa, Harandi, Mehrtash, Lovell, Brian C. and Salzmann, Mathieu (2014). Discriminative non-linear stationary subspace analysis for video classification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36 (12) 6857376, 2353-2366. doi: 10.1109/TPAMI.2014.2339851
Conference Papers
Khramtsova, Ekaterina, Zhuang, Shengyao, Baktashmotlagh, Mahsa, Wang, Xi and Zuccon, Guido (2023). Selecting which dense retriever to use for zero-shot search. SIGIR-AP 2023 - Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region, Beijing, China, 26-28 November 2023. New York, United States: Association for Computing Machinery. doi: 10.1145/3624918.3625330
Luo, Yadan, Chen, Zhuoxiao, Fang, Zhen, Zhang, Zheng, Baktashmotlagh, Mahsa and Huang, Zi (2023). KECOR: Kernel Coding Rate Maximization for Active 3D Object Detection. IEEE/CVF International Conference on Computer Vision 2023 (ICCV), Paris, France, 2-6 October 2021. Paris, France: Computer Vision Foundation. doi: 10.1109/iccv51070.2023.01676
Michalkiewicz, Mateusz, Faraki, Masoud, Yu, Xiang, Chandraker, Manmohan and Baktashmotlagh, Mahsa (2023). Domain Generalization Guided by Gradient Signal to Noise Ratio of Parameters. IEEE/CVF International Conference on Computer Vision 2023 (ICCV), Paris, France, 2-6 October 2023. Paris, France: Computer Vision Foundation. doi: 10.1109/iccv51070.2023.00568
Wang, Zijian, Luo, Yadan, Zheng, Liang, Huang, Zi and Baktashmotlagh, Mahsa (2023). How Far Pre-trained Models Are from Neural Collapse on the Target Dataset Informs their Transferability. IEEE/CVF International Conference on Computer Vision 2023 (ICCV), Paris, France, 2-6 October 2023. Paris, France: Computer Vision Foundation. doi: 10.1109/iccv51070.2023.00511
Chen, Zhuoxiao, Luo, Yadan, Wang, Zheng, Baktashmotlagh, Mahsa and Huang, Zi (2023). Revisiting Domain-Adaptive 3D Object Detection by Reliable, Diverse and Class-balanced Pseudo-Labeling. IEEE/CVF International Conference on Computer Vision 2023 (ICCV), Paris, France, 2-6 October 2023. Paris, France: Computer Vision Foundation. doi: 10.1109/iccv51070.2023.00344
Luo, Yadan, Chen, Zhuoxiao, Wang, Zijian, Yu, Xin, Huang, Zi and Baktashmotlagh, Mahsa (2023). Exploring active 3D object detection from a generalization perspective. 11th International Conference on Learning Representations (ICLR), Kigali, Rwanda, 1 - 5 May 2023. New York, NY, United States: Cornell Tech. doi: 10.48550/arXiv.2301.09249
Wang, Zijian, Luo, Yadan, Huang, Zi and Baktashmotlagh, Mahsa (2023). FFM: injecting out-of-domain knowledge via factorized frequency modification. 23rd IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, United States, 3-7 January 2023. Piscataway, NJ, United States: Institute of Electrical and Electronics Engineers. doi: 10.1109/wacv56688.2023.00412
Khramtsova, Ekaterina, Zuccon, Guido, Wang, Xi and Baktashmotlagh, Mahsa (2023). Convolutional Persistence as a Remedy to Neural Model Analysis. International Conference on Artificial Intelligence and Statistics, Valencia, Spain, 25-27 April 2023. Brookline, MA United States: ML Research Press.
Chen, Tianle, Baktashmotlagh, Mahsa, Wang, Zijian and Salzmann, Mathieu (2023). Center-aware adversarial augmentation for single domain generalization. 23rd IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, United States, 2-7 January 2023. Piscataway, NJ, United States: Institute of Electrical and Electronics Engineers. doi: 10.1109/wacv56688.2023.00414
Chen, Tianle, Baktashmotlagh, Mahsa and Salzmann, Mathieu (2022). Contrastive Class-aware Adaptation for Domain Generalization. 2022 26th International Conference on Pattern Recognition (ICPR), Montreal, QC Canada, 21-25 August 2022. Piscataway, NJ United States: IEEE. doi: 10.1109/icpr56361.2022.9956262
Khramtsova, Ekaterina, Zuccon, Guido, Wang, Xi and Baktashmotlagh, Mahsa (2022). Rethinking persistent homology for visual recognition. Topological, Algebraic and Geometric Learning Workshops, Online, 25-22 July 2022. Brookline, MA United States: ML Research Press.
Baktashmotlagh, Mahsa, Chen, Tianle and Salzmann, Mathieu (2022). Learning to generate the unknowns as a remedy to the open-set domain shift. 22nd IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, United States, 3-8 January 2022. Piscataway, NJ, United States: Institute of Electrical and Electronics Engineers. doi: 10.1109/WACV51458.2022.00379
Hawkins, Philip, Maire, Frederic, Denman, Simon and Baktashmotlagh, Mahsa (2022). Modular construction planning using graph neural network heuristic search. 34th Australasian Joint Conference on Artificial Intelligence (AI), Electr Network, 2-4 February 2022. Heidelberg, Germany: Springer. doi: 10.1007/978-3-030-97546-3_19
Reddy, Nikhil, Singhal, Abhinav, Kumar, Abhishek, Baktashmotlagh, Mahsa and Arora, Chetan (2022). Master of all: simultaneous generalization of urban-scene segmentation to all adverse weather conditions. Computer Vision – ECCV 2022, Tel Aviv, Israel, 23-27 October 2022. Heidelberg, Germany: Springer. doi: 10.1007/978-3-031-19842-7_4
Chen, Zhuoxiao, Luo, Yadan and Baktashmotlagh, Mahsa (2021). Conditional Extreme Value Theory for Open Set Video Domain Adaptation. MMAsia '21: ACM Multimedia Asia, Gold Coast, QLD Australia, 1 - 3 December 2021. New York, NY United States: Association for Computing Machinery. doi: 10.1145/3469877.3490600
Moskvyak, Olga, Maire, Frederic, Dayoub, Feras, Armstrong, Asia O. and Baktashmotlagh, Mahsa (2021). Robust Re-identification of Manta Rays from Natural Markings by Learning Pose Invariant Embeddings. 2021 Digital Image Computing: Techniques and Applications (DICTA), Gold Coast, QLD Australia, 29 November 2021 - 1 December 2021. Piscataway, NJ United States: IEEE. doi: 10.1109/dicta52665.2021.9647359
Wang, Zijian, Luo, Yadan, Qiu, Ruihong, Huang, Zi and Baktashmotlagh, Mahsa (2021). Learning to diversify for single domain generalization. 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC Canada, 10-17 October 2021. Piscataway, NJ USA: Institute of Electrical and Electronics Engineers. doi: 10.1109/ICCV48922.2021.00087
Moskvyak, Olga, Maire, Frederic, Dayoub, Feras and Baktashmotlagh, Mahsa (2021). Keypoint-aligned embeddings for image retrieval and re-identification. IEEE Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, United States, 3-8 January 2021. Piscataway, NJ, United States: Institute of Electrical and Electronics Engineers. doi: 10.1109/WACV48630.2021.00072
Moghimifar, Farhad, Qu, Lizhen, Zhuo, Yue, Haffari, Gholamreza and Baktashmotlagh, Mahsa (2021). Neural-symbolic commonsense reasoner with relation predictors. 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Online, 1-6 August 2021. Stroudsburg, PA, United States: Association for Computational Linguistics (ACL). doi: 10.18653/v1/2021.acl-short.100
Moghimifar, Farhad, Qu, Lizhen, Zhuo, Yue, Baktashmotlagh, Mahsa and Haffari, Gholamreza (2020). CosMo: Conditional Seq2Seq-based Mixture Model for Zero-Shot Commonsense Question Answering. 28th International Conference on Computational Linguistics, Barcelona, Spain, 8-13 December 2020. Stroudsburg, PA United States: International Committee on Computational Linguistics. doi: 10.18653/v1/2020.coling-main.467
Michalkiewicz, Mateusz, Parisot, Sarah, Tsogkas, Stavros, Baktashmotlagh, Mahsa, Eriksson, Anders and Belilovsky, Eugene (2020). Few-shot single-view 3-D object reconstruction with compositional priors. Computer Vision – ECCV 2020, Glasgow, United Kingdom, 23-28 August 2020. Heidelberg, Germany: Springer. doi: 10.1007/978-3-030-58595-2_37
Luo, Yadan, Huang, Zi, Wang, Zijian, Zhang, Zheng and Baktashmotlagh, Mahsa (2020). Adversarial bipartite graph learning for video domain adaptation. ACM International Conference on Multimedia, Seattle, WA, United States, 12-16 October 2020. New York, United States: Association for Computing Machinery. doi: 10.1145/3394171.3413897
Wang, Zijian, Luo, Yadan, Huang, Zi and Baktashmotlagh, Mahsa (2020). Prototype-matching graph network for heterogeneous domain adaptation. MM '20: 28th ACM International Conference on Multimedia, Online, October 2020. New York, NY, United States: ACM. doi: 10.1145/3394171.3413662
Luo, Yadan, Huang, Zi, Zhang, Zheng, Wang, Ziwei, Baktashmotlagh, Mahsa and Yang, Yang (2020). Learning from the past: continual meta-learning with Bayesian Graph Neural Networks. The Thirty-Fourth AAAI Conference on Artificial Intelligence/ The Thirty-Second Conference on Innovative Applications of Artificial Intelligence/ The Tenth Symposium on Educational Advances in Artificial Intelligence, New York, United States, 7-12 February 2020. Palo Alto, CA, United States: Association for the Advancement of Artificial Intelligence (AAAI). doi: 10.1609/aaai.v34i04.5942
Moskvyak, Olga, Maire, Frederic, Dayoub, Feras and Baktashmotlagh, Mahsa (2020). Learning Landmark Guided Embeddings for Animal Re-identification. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Snowmass, CO United States, 1-5 March 2020. Piscataway, NJ United States: Institute of Electrical and Electronics Engineers. doi: 10.1109/WACVW50321.2020.9096932
Michalkiewicz, Mateusz, Belilovsky, Eugene, Baktashmotlagh, Mahsa and Eriksson, Anders (2020). A Simple and Scalable Shape Representation for 3D Reconstruction. British Machine Vision Association, BMVA.
Moghimifar, Farhad, Haffari, Gholamreza and Baktashmotlagh, Mahsa (2020). Domain Adaptative Causality Encode. Australasian Language Technology Association.
Moghimifar, Farhad, Rahimi, Afshin, Baktashmotlagh, Mahsa and Li, Xue (2020). Learning Causal Bayesian Networks from Text. Australasian Language Technology Association.
Luo, Yadan, Wang, Zijian, Huang, Zi and Baktashmotlagh, Mahsa (2020). Progressive graph learning for open-set domain adaptation. 37th International Conference on Machine Learning ICML 2020, Vienna, Austria, 12-18 July 2020 . International Machine Learning Society .
Michalkiewicz, Mateusz, Pontes, Jhony Kaesemodel, Jack, Dominic, Baktashmotlagh, Mahsa and Eriksson, Anders (2020). Implicit surface representations as layers in neural networks. 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea, 27 October -2 November, 2019 . Piscataway, NJ, United States: Institute of Electrical and Electronics Engineers. doi: 10.1109/ICCV.2019.00484
Rahman, Mohammad Mahfujur, Fookes, Clinton, Baktashmotlagh, Mahsa and Sridharan, Sridha (2019). Multi-Component Image Translation for Deep Domain Generalization. 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI United States, 7-11 January 2019. Piscataway, NJ United States: IEEE. doi: 10.1109/wacv.2019.00067
Baktashmotlagh, Mahsa, Faraki, Masoud, Drummond, Tom and Salzmann, Mathieu (2019). Learning factorized representations for open-set domain adaptation. 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, United States, 6 - 9 May 2019. International Conference on Learning Representations, ICLR.
Hawkins, Philip, Maire, Frederic, Denman, Simon and Baktashmotlagh, Mahsa (2019). Object graph networks for spatial language grounding. APRS International Conference on Digital Image Computing - Techniques and Applications (DICTA), Perth, Australia, 2-4 December 2019. Piscataway, NJ, United States: Institute of Electrical and Electronics Engineers. doi: 10.1109/DICTA47822.2019.8946101
Al-Ali, Ahmed Kamil Hasan, Dean, David, Senadji, Bouchra, Baktashmotlagh, Mahsa and Chandran, Vinod (2017). Speaker verification with multi-run ICA based speech enhancement. 2017 11th International Conference on Signal Processing and Communication Systems (ICSPCS), Gold Coast, QLD Australia, 13-15 December 2017. Piscataway, NJ United States: IEEE. doi: 10.1109/icspcs.2017.8270505
Ghasemi, Afsaneh, Baktashmotlagh, Mahsa, Denman, Simon, Sridharan, Sridha, Tien, Dung Nguyen and Fookes, Clinton (2017). Deep discovery of facial motions using a shallow embedding layer. 2017 IEEE International Conference on Image Processing (ICIP), Beijing, China, 17-20 September 2017. Piscataway, NJ, United States: IEEE. doi: 10.1109/icip.2017.8296545
Erfani, Sarah, Baktashmotlagh, Mahsa, Moshtaghi, Masud, Nguyen, Vinh, Leckie, Christopher, Bailey, James and Ramamohanarao, Kotagiri (2017). From Shared Subspaces to Shared Landmarks: A Robust Multi-Source Classification Approach. Thirty-First AAAI Conference on Artificial Intelligence, San Francisco, CA United States, 4-9 February 2017. Palo Alto, CA United States: Association for the Advancement of Artificial Intelligence. doi: 10.1609/aaai.v31i1.10870
Erfani, Sarah M., Baktashmotlagh, Mahsa, Rajasegarad, Sutharshan, Nguyen, Vinh, Leckie, Christopher, Bailey, James and Ramamohanarao, Kotagiri (2016). R1STM: One-class support tensor machine with randomised kernel. 2016 SIAM International Conference on Data Mining (SDM), Miami, FL United States, 5-7 May 2016. Philadelphia, PA United States: Society for Industrial and Applied Mathematics. doi: 10.1137/1.9781611974348.23
Erfani, Sarah M., Baktashmotlagh, Mahsa, Moshtaghi, Masud, Nguyen, Vinh, Leckie, Christopher, Bailey, James and Ramamohanarao, Kotagiri (2016). Robust domain generalisation by enforcing distribution invariance. 25th International Joint Conference on Artificial Intelligence, IJCAI 2016, New York, NY, United States, 9-15 July 2016. Palo Alto, CA United States: AAAI Press / International Joint Conferences on Artificial Intelligence.
Harandi, Mehrtash, Salzmann, Mathieu and Baktashmotlagh, Mahsa (2015). Beyond Gauss: Image-Set Matching on the Riemannian Manifold of PDFs. 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, 7-13 December 2015. Piscataway, NJ United States: IEEE. doi: 10.1109/iccv.2015.468
Erfani, Sarah M., Baktashmotlagh, Mahsa, Rajasegarar, Sutharshan, Karunasekera, Shanika and Leckie, Chris (2015). R1SVM: A randomised nonlinear approach to large-scale anomaly detection. AI Access Foundation.
M. Erfani, Sarah, Baktashmotlagh, Mahsa, Rajasegarar, Sutharshan, Karunasekera, Shanika and Leckie, Chris (2015). R1SVM: A randomised nonlinear approach to large-scale anomaly detection. Twenty-Ninth AAAI Conference on Artificial Intelligence, Austin, TX, United States, 25-30 January 2015. Palo Alto, CA, United States: Association for the Advancement of Artificial Intelligence (AAAI). doi: 10.1609/aaai.v29i1.9208
Baktashmotlagh, Mahsa, Harandi, Mehrtash T., Lovell, Brian C. and Salzmann, Mathieu (2014). Domain adaptation on the statistical manifold. 27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014, Columbus, OH, United States, 23-28 June 2014. Piscataway, NJ, United States: I E E E Computer Society. doi: 10.1109/CVPR.2014.318
Baktashmotlagh, Mahsa, Harandi, Mehrtash T., Lovell, Brian C. and Salzmann, Mathieu (2013). Unsupervised domain adaptation by Domain Invariant Projection. 2013 IEEE International Conference on Computer Vision (ICCV), Sydney, Australia, 1-8 December 2013. Piscataway, NJ, United States: IEEE. doi: 10.1109/ICCV.2013.100
Baktashmotlagh, Mahsa, Harandi, Mehrtash T., Bigdeli, Abbas, Lovell, Brian C. and Salzmann, Mathieu (2013). Non-linear stationary subspace analysis with application to video classification. 30th International Conference on Machine Learning, Atlanta, GA, United States, 16 - 21 June 2013. Germany: International Machine Learning Society (IMLS).
Ahmadi, Amin, Bigdeli, Abbas, Baktashmotlagh, Mahsa and Lovell, Brian C. (2012). A wireless mesh sensor network for hazard and safety monitoring at the Port of Brisbane. 37th Annual IEEE Conference on Local Computer Networks (LCN 2012), Clearwater, FL, United States, 22-25 October 2012. Washington, DC, United States: IEEE. doi: 10.1109/LCN.2012.6423601
Norouznezhad, Ehsan, Harandi, Mehrtash T., Bigdeli, Abbas, Baktash, Mahsa, Postula, Adam and Lovell, Brian C. (2012). Directional space-time oriented gradients for 3D visual pattern analysis. 12th European Conference on Computer Vision, ECCV 2012, Florence, Italy, 7 - 13 October 2012. Heidelberg, Germany: Springer. doi: 10.1007/978-3-642-33712-3_53
Baktashmotlagh, Mahsa, Bigdeli, Abbas and Lovell, Brian C. (2011). Dynamic resource aware sensor networks: Integration of sensor cloud and ERPs. 8th IEEE International Conference on Advanced Video and Signal-Based Surveillance (AVSS), 2011, Klagenfurt, Austria, 30 August - 2 September 2011. Piscataway, NJ, United States: IEEE. doi: 10.1109/AVSS.2011.6027375
Thesis
Baktashmotlagh, Mahsa (2014). Learning Invariances for High-Dimensional Data Analysis. PhD Thesis, School of Information Technology and Electrical Engineering, The University of Queensland. doi: 10.14264/uql.2014.183