Dr Piotr Koniusz
PhD
Principal Research Scientist at Data61/CSIRO + Hon. Associate Professor at the ANU
ANU College of Engineering, Computing and Cybernetics
Areas of expertise
- Computer Vision 460304
- Machine Learning 4611
- Artificial Intelligence 4602
- Neural Networks 461104
- Deep Learning 461103
- Pattern Recognition 460308
- Video Processing 460309
- Semi And Unsupervised Learning 461106
- Graph, Social And Multimedia Data 460506
- Recommender Systems 460510
- Knowledge Representation And Reasoning 460206
- Multimodal Analysis And Synthesis 460307
- Adversarial Machine Learning 461101
Biography
Currently, I am a senior researcher in MLRG at Data61/CSIRO and a senior honorary lecturer at the ANU. Previously, I worked as a post-doctoral researcher in the team LEAR, INRIA, France. I received my B.Sc. degree in Telecommunications and Software Engineering in 2004 from the Warsaw University of Technology, Poland, and completed my PhD degree in Computer Vision in 2013 at CVSSP, University of Surrey, UK.
Publications
- Koniusz, P & Zhang, H 2021, 'Power Normalizations in Fine-grained Image, Few-shot Image and Graph Classification', IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 2, pp. 1-16.
- Koniusz, P, Wang, L & Cherian, A 2021, 'Tensor Representations for Action Recognition', IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 2, pp. 1-16.
- Zhang, H, Koniusz, P, Jian, S et al. 2021, 'Rethinking Class Relations: Absolute-relative Supervised and Unsupervised Few-shot Learning', 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021, IEEE Computer Society, United States, pp. 9427-9436.
- Wang, L & Koniusz, P 2021, 'Self-supervising Action Recognition by Statistical Moment and Subspace Descriptors', MM '21: ACM Multimedia Conference, Association for Computing Machinery (ACM), New York, NY, United States, pp. 4324-4333.
- Wang, L, Koniusz, P & Huynh, D 2020, 'Hallucinating IDT descriptors and I3D optical flow features for action recognition with CNNs', 2019 IEEE/CVF International Conference on Computer Vision, ICCV 2019, ed. Kyoung Mu Lee, David Forsyth, Marc Pollefeys, Xiaoou Tang, IEEE, Institute of Electrical and Electronics Engineers, United States, pp. 8697-8707.
- Zhang, H, Dai, Y, Li, H et al. 2020, 'Deep stacked hierarchical multi-patch network for image deblurring', 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019, IEEE, United States, pp. 5971-5979.
- Zhang, H, Zhang, L, Qi, X et al. 2020, 'Few-Shot Action Recognition with Permutation-Invariant Attention', 16th European Conference on Computer Vision, ECCV 2020, ed. A. Vedaldi, H. Bischof, T. Brox & J-M. Frahm, Springer, Cham, Switzerland, pp. 525-542.
- Hou, W, Suominen, H, Koniusz, P et al. 2020, 'A Token-Wise CNN-Based Method for Sentence Compression', 27th International Conference on Neural Information Processing, ICONIP 2020, ed. H. Yang, K. Pasupa, A.C.-S Leung, J.T. Kwok, J.H Chan & I. King, Springer, Germany, pp. 668-679.
- Shiri, F, Yu, X, Porikli, F et al 2019, 'Recovering faces from portraits with auxiliary facial attributes', 19th IEEE Winter Conference on Applications of Computer Vision, WACV 2019, IEEE, Piscataway, United States, pp. 406-415.
- Shiri, F, Yu, X, Porikli, F et al. 2019, 'Identity-Preserving Face Recovery from Stylized Portraits', International Journal of Computer Vision, vol. 127, pp. 863-883.
- Koniusz, P, Zhang, H & Porikli, F 2018, 'A Deeper Look at Power Normalizations', 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, United States, pp. 5774-5783.
- Koniusz, P, Tas, Y, Zhang, H et al. 2018, 'Museum Exhibit Identification Challenge for the Supervised Domain Adaptation and Beyond', 15th European Conference on Computer Vision, ECCV 2018, ed. L Leal-Taixe, S Roth, Springer Verlag, Germany, pp. 815-833.
- Shiri, F, Yu, X, Porikli, F et al 2018, 'Identity-preserving face recovery from portraits', 18th IEEE Winter Conference on Applications of Computer Vision, WACV 2018, IEEE, USA, pp. 102-111.
- Cherian, A, Koniusz, P & Gould, S 2017, 'Higher-order pooling of cnn features via kernel linearization for action recognition', 17th IEEE Winter Conference on Applications of Computer Vision, WACV 2017, Institute of Electrical and Electronics Engineers (IEEE Inc), Piscataway, New Jersey, US, pp. 130-138.
- P. Koniusz, Y. Tas, F. Porikli, 2017, 'Domain adaptation by mixture of alignments of second- or higher-order scatter tensors', 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, pp. 7139-7148.
- P. Koniusz, A. Cherian, F. Porikli, 2016, 'Tensor representations via kernel linearization for action recognition from 3D skeletons', European Conference on Computer Vision, ECCV 2016, pp. 37-53.
Projects and Grants
Grants information is drawn from ARIES. To add or update Projects or Grants information please contact your College Research Office.
- Automatic Training Data Search and Model Evaluation by Measuring Domain Gap (Secondary Investigator)
