• Since June 2023, I am a Principal Research Scientist in the StatML Research Group at Data61❤CSIRO (former NICTA). I am also appointed as an Honorary Associate Professor (level D) at the Australian National University (ANU) and an Adjunct Associate Professor (level D) at the University of New South Wales (UNSW). I was a post-doctoral researcher (2013-2015) in the team LEAR, INRIA, Grenoble. I received my BSc degree in Telecommunications and Software Eng in 2004 from the Warsaw University of Technology, Poland, and my PhD degree in Computer Vision in 2013 at CVSSP, University of Surrey, United Kingdom.
• I work on representation learning (contrastive & self-supervised learning, vision-language models (VLMs), LLMs, deep & graph neural nets), image classificaton & action recognition, zero-, one- & few-shot learning, domain adaptation, incremental learning, object segmentation & detection, generative nets, adversarial robustness, spectral, tensor & hyperbolic learning, RKHS, optimal transportation (OT).
• If you are interested in PhD studies at the Australian National University (ANU), the University of New South Wales (UNSW) or Data61/CSIRO, read here.
• If you represent a company and seek collaboration (Data61/CSIRO, ANU, UNSW), kindly e-mail me.

NEWS

• PK is serving as a Workshop Program Co-Chair (see call for workshops / accepted workshops) at the Web. Conf. (WWW) 2025.
  
• Yao Ni, Shan Zhang and I have received the Best Paper Award for Science-fundamental Research from A&DS/Data61 for our PACE: marrying the generalization of PArameter-efficient fine-tuning with Consistency rEgularization. Very proud that A&DS values our work. Congrats Yao & Shan.
  
• PK served as a Workshop Program Co-Chair (accpeted workshops) for NeurIPS'23. PK is serving/served as a Senior Area Chair for ICML'25, ICLR'25, NeurIPS'24, ICML'24, ICLR'24, NeurIPS'23, and an Area Chair for CVPR'25, AAAI'25, AAAI'24, CVPR'24, ACML'24, ECCV'24 and BMVC'24.
  
• 2x KDD'25, 1x WSDM'25, 1x NeurIPS'24 (spotlight), 1x KDD'24, 1x ACML'24 (oral), 3x ECCV'24, 3x CVPR'24, 1x ICLR'24 (spotlight), 1x AAAI'24, 1x IJCV'24, 1x HAZMAT'24, 1x Neurocomputing'24, 2x WACV'24, 2x ICASSP'24 (one oral), 2x NeurIPS'23 (one spotlight), 1x ICCV'23, 1x TPAMI'23, 1x AAAI'23 (oral), 1x DAMI'23 (at ECML-PKDD'23), 1x ACM IoTDI'23 and 4x CVPR'23 papers accepted. Congrats to Junhao Dong, Yifei Zhang, Hao Zhu, Qixiang Chen, Yao Ni, Lei Wang, Shan Zhang, Changsheng Lu, Zheyuan Liu, Gaurangi Anand, Peipei Song, Maryam Haghighat, Shaheer Mohamed, Zhongyan Zhang, Dahyun Kang, Saimunur Rahman and Arian Prabowo.
  
• PK's talk in IJCAI'24 workshop Generalizing from Limited Resources in the Open World on Understanding and Improving Generative Adversarial Networks in Low-sample Regime is here. PK's talk in IJCAI'23 workshop Generalizing from Limited Resources in the Open World on Few-shot Learning is here and slides are here.
  
• Lei Wang and I have received the Sang Uk Lee Best Student Paper Award from ACCV'22 for our Temporal-Viewpoint Transportation Plan for Skeletal Few-shot Action Recognition. Lei also graduates with PhD. Congrats Dr. Lei.
  
• Peipei Song, Jing Zhang, Nick Barnes and I have received the Runner-up APRS/IAPR Best Student Paper Award from DICTA'22 for our Stereo Saliency Detection by Modeling Concatenation Cost Volume Feature. Congrats Peipei.
  
---show more---
• On the outstanding paper awards committee of ICLR'23. I was also on the outstanding paper awards committee of ICLR'21. Congratulations to winners of outstanding paper awards (ICLR'21). PK also selected as an Outstanding/Highlighted Area Chair by ICLR 2021 and ICLR 2022.
  
• 1x NeurIPS'22, 2x ACCV'22 (one oral, 4.9% acceptance rate), 1x TPAMI'22, 1x IJCV'22, 1x KDD'22 (15% acceptance rate), 2x ECCV'22 (one oral, 2.7% acceptance rate), 4x CVPR'22, 1x WWW'22 (~17.7% acceptance rate), 1x TMM'22, 2x WACV'22, 1x ICIP'22, 1x DICTA'22 (oral), 1x NeurIPS'21, 1x ICLR'21, 2x CVPR'21 (one oral), 1x CIKM'21, 1x ACM MM'21, 1x BMVC'21 and 1x Neurocomputing'21 papers accepted. Congrats to Hao Zhu, Lei Wang, Hongguang Zhang, Yujiao Shi, Shan Zhang, Peipei Song, Yao Ni, Changsheng Lu, Yifei Zhang, Christian Simon, Yusuf Tas and Wei Shao.
  
• Our Next Generation Graduates in AI (NextGenAI) entitled Towards AI on the Edge has been accepted (1.2M AUD). It covers 11 domestic scholarships for PhD, MPhi and Honours students. Prof. Flora Salim, Prof. Tom Gedeon and I are CIs. Get in touch if interested.
  
• PK is a PI on Prof. Dinh Phun, A/Prof. Mehrtash Harandi, Prof. Richard Hartley and Dr. Trung Le's ARC Discovery grant on Exploiting Geometries of Learning for Fast, Adaptive and Robust AI.
  
• PK's talk in CVPR 2021 tutorial Fine-Grained Visual Analysis with Deep Learning (FGVA) entitled High Order Pooling and Fine-grained Classification. Big thanks to all organisers. PK's talk in an ICCV 2021 workshop Multi-Modal Video Reasoning and Analyzing Competition (MMVRAC) can be found here. PK's talk in NeurIPS 2021 pre-conference Australia on contrastive learning and graphs is here.
  
• 2x ECCV'20 (one spotlight ~3.6% acceptance rate), 2x TPAMI'20, CVPR'20, ACCV'20, PAKDD'20, BMVC'20, ICONIP'20, NIPS'19 workshop, BuildSys'19 and SIGSPATIAL'19 papers accepted (plus a first prize for the fast forward presentation for the last paper). Congrats to Shan Zhang, Christian Simon, Hongguang Zhang, Xianjing Wang, Weiwei Hou, Arian Prabowo and Wei Shao.
  
• PK is serving as a Workshop Chair (co-chair) for ACCV 2022 (we hosted 10 exciting ACCV'22 workshops) and ACM Multimedia 2021. PK is serving as an Area Chair for ICML 2023, CVPR 2023, ICLR 2023, NeurIPS 2022, ICML 2022, ICLR 2022, AAAI 2022 and ECCV 2022. I have served so far as an AC for BMVC 2021, CVPR 2021, ICLR 2021, ECCV 2020, BMVC 2020, DICTA 2020 (SR), SPC for AAAI 2020 and an AC for ICLR 2020, ICLR 2019, WACV 2019, ICCV 2019 and BMVC 2019.
  
• See the 1st Workshop on Vision Datasets Understanding in conjunction with CVPR'22. Congratualtions to recipients of best paper/runner-up awards. We organise a special issue on Synthetic Data in Generalizable Video Analytics (info coming soon) in Image and Vision Computing. I am one of Guest Editors.
  
• Fatima Shiri, Hongguang Zhang and Yusuf Tas pass their PhD vivas. Congrats. I will miss you!
  
• PK's mini DST grant on Classification of Subtle Activities completed (CI role, 20K AUD). PK's larger DST grants on FSAR and detection accepted (CI roles, 2x 100K AUD). PK is also a PI on Prof. Tom Gedeon and Dr. Liang Zheng's ARC Discovery grant on Measuring Domain Gap.
  
• PK's talk in ACCV 2020 workshop Webly-Supervised Fine-Grained Recognition Challenge (WebFG) entitled Statistical Representations for Fine-grained Recognition. Big thanks to organisers, especially Xiu-Shen Wei. The talk is here and here.
  
• PK's talk in ECCV 2020 workshop Transferring and Adapting Source Knowledge in Computer Vision (TASK-CV) entitled Few-shot Learning: From Domain Adaptation to Action Recognition to Noisy Gradients. Big thanks to organisers, especially Tatiana Tommasi and Gabriela Csurka. The talk is here.
  
• PK's talk in WACV 2020 workshop Vision Applications & Solutions to Biased or Scarce Data (VASBSD) entitled Statistical Representations for Domain Adaptation and Few-shot Learning. Big thanks to Fatih Porikli and Kuan-Chuan Peng.
  
• One ICCV'19, one UAI'19, two CVPR'19, two WACV'19 and one IJCV'19 papers accepted. Congrats Lei Wang, Fatemeh Shiri and Hongguang Zhang!
  
• I am organising an ICCV 2019 tutorial entitled Second- and Higher-order Representations in Computer Vision with my colleagues Mehrtash Harandi, Lei Wang and Ruiping Wang.
  
• I am the main advisor of five PhD students at CECS/ANU: Lei Wang, Hao Zhu, Yao Ni, Shan Zhang and Changsheng Lu. I am co-supervising (D61/second/associate supervisor, etc.) Christian Simon (ANU) with Dr. Mehrtash Harandi (Monash), Peipei Song (ANU) with A/Prof. Nick Barnes (ANU), and Arian Prabowo with A/Prof. Flora Salim (RMIT). If you are interested in PhD studies at the Australian National University and/or Data61/CSIRO, read here.
  
• I am organising an ACCV 2018 workshop and a mini-challenge entitled Museum Exhibit Identification Challenge (Open MIC) for Domain Adaptation and Few-Shot Learning.
  
• The Open MIC dataset is available for non-commercial academic research Open MIC Dataset (ECCV 2018).
  
• Two ECCV'18 (oral ~2% acceptance rate/poster) and one BMVC'18 (spotlight ~6% acceptance rate) papers accepted. Congrats Yusuf Tas and Tsung-Yu Lin! Also, two CVPR'18 and one WACV'18 papers accepted. Congrats Fatemeh Shiri and Hongguang Zhang!
  
• I have been listed as an Outstanding Reviewer by ICCV 2017, CVPR 2017 and ECCV 2016 Awards Page.
  
• I am organising a full-day CVPR 2017 workshop entitled Tensor Methods in Computer Vision with my colleagues Anoop Cherian and Fatih Porikli.
  
• I have been listed as an Outstanding Reviewer at CVPR 2015 Awards Page and BMVC 2012 Page.
• Beyond Covariance: Higher-order Tensor Descriptors & Applications in CV (Slides), P. Koniusz, ANU talk.

PUBLICATIONS

2025



• Understanding and Mitigating Hyperbolic Dimensional Collapse in Graph Contrastive Learning, Yifei Zhang, Hao Zhu, Menglin Yang, Jiahong Liu, Rex Ying, Irwin King, Piotr Koniusz, ACM International Conference on Knowledge Discovery and Data Mining (KDD), 2025 (19% acceptance rate). Old version available on ArXiV (substantial update coming soon).
• Stabilizing Modality Gap & Lowering Gradient Norms Improves Zero-Shot Adversarial Robustness of VLMs, Junhao Dong, Piotr Koniusz, Xinghua Qu, Yew-Soon Ong, ACM International Conference on Knowledge Discovery and Data Mining (KDD), 2025 (19% acceptance rate).
• Inductive Graph Few-shot Class Incremental Learning, Yayong Li, Peyman Moghadam, Can Peng, Nan Ye, Piotr Koniusz, The Eighteenth International Conference on Web Search and Data Mining (WSDM), 2025 (accepted).



2024



• PACE: marrying the generalization of PArameter-efficient fine-tuning with Consistency rEgularization, Yao Ni, Shan Zhang, Piotr Koniusz, International Conference on Neural Information Processing Systems (NeurIPS), 2024 (spotlight is 2.08% acceptance rate).
• Geometric View of Soft Decorrelation in Self-Supervised Learning, Yifei Zhang, Hao Zhu, Zixing Song, Yankai Chen, Xinyu Fu, Ziqiao Meng, Piotr Koniusz, Irwin King, ACM International Conference on Knowledge Discovery and Data Mining (KDD), 2024 (20% acceptance rate).
• Motion meets Attention: Video Motion Prompts, Qixiang Chen, Lei Wang, Piotr Koniusz, Tom Gedeon, Asian Conference on Machine Learning (ACML), 2024 (oral is 5.67% acceptance rate, all accepted is 26% acceptance rate).
• Multivariate Prototype Representation for Domain-Generalized Incremental Learning, Can Peng, Piotr Koniusz, Kaiyu Guo, Brian C. Lovell, Peyman Moghadam, Computer Vision and Image Undertanding (CVIU), 2024 (accepted). Also, available on ArXiV.
• OpenKD: Opening Prompt Diversity for Zero- and Few-shot Keypoint Detection, Changsheng Lu, Zheyuan Liu, Piotr Koniusz, European Conference on Computer Vision (ECCV), 2024. See also the GitHub code.
• Adversarially Robust Distillation by Reducing the Student-Teacher Variance Gap, Junhao Dong, Piotr Koniusz, Junxi Chen, Yew-Soon Ong, European Conference on Computer Vision (ECCV), 2024.
• Adaptive Multi-head Contrastive Learning, Lei Wang, Piotr Koniusz, Tom Gedeon, Liang Zheng, European Conference on Computer Vision (ECCV), 2024. Also, available on ArXiV.
• Robust Distillation via Untargeted and Targeted Intermediate Adversarial Samples, Junhao Dong, Piotr Koniusz, Junxi Chen, Z. Jane Wang, Yew-Soon Ong, Computer Vision and Pattern Recognition (CVPR), 2024. Also, see the PDF and Suppl. Mat.
• Adversarially Robust Few-shot Learning via Parameter Co-distillation of Similarity and Class Concept Learners, Junhao Dong, Piotr Koniusz, Junxi Chen, Xiaohua Xie, Yew-Soon Ong, Computer Vision and Pattern Recognition (CVPR), 2024. Also, see the PDF and Suppl. Mat.
• CHAIN: Enhancing Generalization in Data-Efficient GAN Training through lipsCHitz continuity constrAIned Normalization, Yao Ni, Piotr Koniusz, Computer Vision and Pattern Recognition (CVPR), 2024. Also, available on ArXiV.
• Pre-training with Random Orthogonal Projection Image Modeling, Maryam Haghighat, Peyman Moghadam, Shaheer Mohamed, Piotr Koniusz, International Conference on Learning Representations (ICLR), 2024 (spotlight ~5% acceptance rate). Also, available on ArXiV.
• Detect Any Keypoints: An Efficient Light-Weight Few-Shot Keypoint Detector, Changsheng Lu, Piotr Koniusz, International Conference on Artificial Intelligence (AAAI), 2024.
• Graph Neural Networks-enhanced RelAtion Prediction for Ecotoxicology (GRAPE), Gaurangi Anand, Piotr Koniusz, Anupama Kumar, Lisa A. Golding, Matthew J. Morgan, Peyman Moghadam, Elsevier's International Journal of Hazardous Materials (HAZMAT), 2024 (accepted, IF: 13.6). Also, see the PDF and Suppl. Mat. and the GitHub code.
• Meet JEANIE: a Similarity Measure for 3D Skeleton Sequences via Temporal-Viewpoint Alignment, Lei Wang, Jun Liu, Liang Zheng, Tom Gedeon, Piotr Koniusz, International Journal of Computer Vision (IJCV), 2024 (accepted).
• Synergizing triple attention with depth quality for RGB-D salient object detection, Peipei Songa, Wenyu Li, Peiyan Zhong, Jing Zhang, Piotr Konuisz, Feng Duan, Nick Barnes, Neurocomputing, 2024 (accepted).
• Semantic Transfer From Head to Tail: Enlarging Tail Margin for Long-Tailed Visual Recognition, Shan Zhang, Yao Ni, Jinhao Du, Yanxia Liu, Piotr Koniusz, Winter Conference on Applications of Computer Vision (WACV), 2024.
• Few-shot Shape Recognition by Learning Deep Shape-aware Features, Wenlong Shi, Changsheng Lu, Ming Shao, Yinjie Zhang, Siyu Xia, Piotr Koniusz, Winter Conference on Applications of Computer Vision (WACV), 2024.
• Saliency-guided meta-hallucinator for few-shot learning, Hongguang Zhang, Chun Liu, Jiandong Wang, Linru Ma, Piotr Koniusz, Philip H. S. Torr, Lin Yang, Science China Information Sciences (SCIS, IF: 7.3), Springer, 2024.
• Flow Dynamics Correction for Action Recognition, Lei Wang, Piotr Koniusz, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2024.
• High-order Tensor Pooling with Attention for Action Recognition, Lei Wang, Ke Sun, Piotr Koniusz, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2024 (oral).



2023



• NICE: NoIse-modulated Consistency rEgularization for Data-Efficient GANs, Yao Ni, Piotr Koniusz, International Conference on Neural Information Processing Systems (NeurIPS), 2023.
• Mitigating the Popularity Bias in Graph-based Collaborative Filtering, Yifei Zhang, Hao Zhu, yankai Chen, Zixing Song, Piotr Koniusz, Irwin King, International Conference on Neural Information Processing Systems (NeurIPS), 2023 (spotlight).
• Learning Spatial-context-aware Global Visual Feature Representation for Instance Image Retrieval, Zhongyan Zhang, Lei Wang, Luping Zhou, Piotr Koniusz, International Conference on Computer Vision (ICCV), 2023. Also, see the Suppl. Mat.
• Exploiting Field Dependencies for Learning on Categorical Data, Zhibin Li, Piotr Koniusz, Lu Zhang, Daniel Edward Pagendam, Peyman Moghadam, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023. Also, see the IEEE Xplore.
• Distilling Self-Supervised Vision Transformers for Weakly-Supervised Few-Shot Classification & Segmentation, Dahyun Kang, Piotr Koniusz, Minsu Cho, Naila Murray, Computer Vision and Pattern Recognition (CVPR), 2023. Also, see the Suppl. Mat.
• Transductive Few-Shot Learning with Prototypes Label-Propagation by Iterative Graph Refinement, Hao Zhu, Piotr Koniusz, Computer Vision and Pattern Recognition (CVPR), 2023. Also, see the Suppl. Mat., ArXiV and the GitHub code.
• Learning Partial Correlation based Deep Visual Representation for Image Classification, Saimunur Rahman, Piotr Koniusz, Lei Wang, Luping Zhou, Peyman Moghadam, Changming Sun, Computer Vision and Pattern Recognition (CVPR), 2023. Also, see the Suppl. Mat., ArXiV and the GitHub code.
• 3Mformer: Multi-order Multi-mode Transformer for Skeletal Action Recognition, Lei Wang, Piotr Koniusz, Computer Vision and Pattern Recognition (CVPR), 2023. Also, see the Suppl. Mat. and ArXiV.
• Multivariate Prototype Representation for Domain-Generalized Incremental Learning, Can Penga, Piotr Koniusz, Kaiyu Guo, Brian C. Lovell, Peyman Moghadam, ArXiV, 2023.
• From Saliency to DINO: Saliency-guided Vision Transformer for Few-shot Keypoint Detection, Changsheng Lu, Hao Zhu, Piotr Koniusz, ArXiV, 2023.
• Message passing neural networks for traffic forecasting, Arian Prabowo, Hao Xue, Wei Shao, Piotr Koniusz, Flora Salim, ArXiV, 2023.
• Traffic Forecasting on New Roads Using Spatial Contrastive Pre-Training (SCPT), Arian Prabowo, Wei Shao, Hao Xue, Piotr Koniusz, Flora Salim, Springer Data Mining and Knowledge Discovery (DAMI), 2023 (in conjunction with ECML-PKDD, 2023). Also, see the Springer page.
• Because Every Sensor Is Unique, so Is Every Pair: Handling Dynamicity in Traffic Forecasting, Arian Prabowo, Wei Shao, Hao Xue, Piotr Koniusz, Flora Salim, ACM International Conference on Internet of Things Design and Implementation (IoTDI), 2023. Also see the GitHub code.
• Spectral Feature Augmentation for Graph Contrastive Learning and Beyond, Yifei Zhang, Hao Zhu, Zixing Song, Piotr Koniusz, Irwin King, International Conference on Artificial Intelligence (AAAI), 2023 (oral). Also, see ArXiV (paper+supplementary).



2022



• Generalized Laplacian Eigenmaps, Hao Zhu, Piotr Koniusz, International Conference on Neural Information Processing Systems (NeurIPS), 2022. Also, see the GitHub code.
• Uncertainty-DTW for Time Series and Sequences, Lei Wang, Piotr Koniusz, European Conference on Computer Vision (ECCV), 2022 (oral ~2.7% acceptance rate). Also, see the Suppl. Mat.
• Time-rEversed diffusioN tEnsor Transformer: A New TENET of Few-Shot Object Detection , Shan Zhang, Naila Murray, Lei Wang, Piotr Koniusz, European Conference on Computer Vision (ECCV), 2022. Also, see the Suppl. Mat.
• Temporal-Viewpoint Transportation Plan for Skeletal Few-shot Action Recognition, Lei Wang, Piotr Koniusz, Asian Conference on Computer Vision (ACCV), 2022 (oral ~4.9% acceptance rate. Also, see the Suppl. Mat. and ArXiV. Received the Sang Uk Lee Best Student Paper Award.
• Improving Few-shot Learning by Spatially-aware Matching and CrossTransformer, Hongguang Zhang, Philip H. S. Torr, Piotr Koniusz, Asian Conference on Computer Vision (ACCV), 2022. Also, see the ArXiV version.
• COSTA: Covariance-Preserving Feature Augmentation for Graph Contrastive Learning, Yifei Zhang, Hao Zhu, Zixing Song, Piotr Koniusz, Irwin King, ACM International Conference on Knowledge Discovery and Data Mining (KDD), 2022 (15% acceptance rate). Also see the ACM Digital Library and the GitHub code.
• Few-Shot Keypoint Detection with Uncertainty Learning for Unseen Species, Changsheng Lu, Piotr Koniusz, Computer Vision and Pattern Recognition (CVPR), 2022. Also, see the Supp. Mat., ArXiV (paper+supplementary) and the GitHub code.
• Kernelized Few-Shot Object Detection With Efficient Integral Aggregation, Shan Zhang, Lei Wang, Naila Murray, Piotr Koniusz, Computer Vision and Pattern Recognition (CVPR), 2022. Also, see the Supp. Mat.
• Manifold Learning Benefits GANs, Yao Ni, Piotr Koniusz, Richard Hartley, Richard Nock, Computer Vision and Pattern Recognition (CVPR), 2022. Also, see the Supp. Mat. and the ArXiV (paper+supplementary).
• EASE: Unsupervised Discriminant Subspace Learning for Transductive Few-Shot Learning, Hao Zhu, Piotr Koniusz, Computer Vision and Pattern Recognition (CVPR), 2022. Also, see the Supp. Mat. and the GitHub code.
• Event-guided Multi-patch Network for Non-uniform Motion Deblurring, Hongguang Zhang, Limeng Zhang, Yuchao Dai, Hongdong Li, Piotr Koniusz, International Journal of Computer Vision (IJCV), 2022.
• Accurate 3-DoF Camera Geo-Localization via Ground-to-Satellite Image Matching, Yujiao Shi, Xin Yu, Liu Liu, Dylan Campbell, Piotr Koniusz, Hongdong Li, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022. Also, see the IEEE Xplore.
• Graph-adaptive Rectified Linear Unit for Graph Neural Networks, Yifei Zhang, Hao Zhu, Ziqiao Meng, Piotr Koniusz, Irwin King, ACM, TheWebConf (WWW), 2022 (~17.7% acceptance rate). Also see the ACM Digital Library.
• Multi-level Second-order Few-shot Learning, Hongguang Zhang, Hongdong Li, Piotr Koniusz, IEEE Transactions on Multimedia (TMM), 2022. Also, see the IEEE Xplore.
• Meta-Learning for Multi-Label Few-Shot Classification, Christian Simon, Piotr Koniusz, Mehrtash Harandi, Winter Conference on Applications of Computer Vision (WACV), 2022.
• Towards a Robust Differentiable Architecture Search under Label Noise, Christian Simon, Piotr Koniusz, Lars Petersson, Yan Han, Mehrtash Harandi, Winter Conference on Applications of Computer Vision (WACV), 2022.
• Multi-modal Transformer for RGB-D Salient Object Detection, Peipei Song, Jing Zhang, Piotr Koniusz, Nick Barnes, International Conference on Image Processing (ICIP), 2022.
• Stereo Saliency Detection by Modeling Concatenation Cost Volume Feature, Peipei Song, Jing Zhang, Piotr Koniusz, Nick Barnes, The International Conference on Digital Image Computing: Techniques and Applications (DICTA, oral), 2022. Received the Runner-up APRS/IAPR Best Student Paper Award.



2021



• Contrastive Laplacian Eigenmaps, Hao Zhu, Ke Sun, Piotr Koniusz, International Conference on Neural Information Processing Systems (NeurIPS), 2021. Also, see the GitHub code.
• On Learning the Geodesic Path for Incremental Learning, Christian Simon, Piotr Koniusz, Mehrtash Harandi, Computer Vision and Pattern Recognition (CVPR), 2021 (oral). Also, see the Supp. Mat. and the GitHub code.
• Rethinking Class Relations: Absolute-Relative Supervised and Unsupervised Few-Shot Learning, Hongguang Zhang, Piotr Koniusz, Songlei Jian, Hongdong Li, Philip H. S. Torr, Computer Vision and Pattern Recognition (CVPR), 2021. Also, see the Supp. Mat.
• Simple Spectral Graph Convolution, Hao Zhu, Piotr Koniusz, International Conference on Learning Representations (ICLR), 2021.
• REFINE: Random RangE FInder for Network Embedding, Hao Zhu, Piotr Koniusz, ACM International Conference on Information and Knowledge Management (CIKM), 2021 (~28% acceptance rate). Also see the ACM Digital Library and the GitHub code.
• Self-supervising Action Recognition by Statistical Moment and Subspace Descriptors, see also the ACM Digital Library, Lei Wang, Piotr Koniusz, ACM Multimedia (ACM MM), 2021.
• Simple Dialogue System with AUDITED, Yusuf Tas, Piotr Koniusz, The British Machine Vision Conference (BMVC), 2021. Also, accessible via the BMVC 2021 website.
• Predicting Flight Delay with Spatio-Temporal Trajectory Convolutional Network and Airport Situational Awareness Map, Wei Shao, Arian Prabowo, Sichen Zhao, Piotr Koniusz, Flora D. Salim, Neurocomputing, 2021. Also, accessible via the ScienceDirect website.
• 3D Skeleton-based Few-shot Action Recognition with JEANIE is not so Naive, Lei Wang, Jun Liu, Piotr Koniusz, ArXiV 2021
• Manifold Learning Benefits GANs, Yao Ni, Piotr Koniusz, Richard Hartley, Richard Nock, ArXiV 2021
• Few-shot Keypoint Detection with Uncertainty Learning for Unseen Species, Changsheng Lu, Piotr Koniusz, ArXiV 2021
• High-order Tensor Pooling with Attention for Action Recognition, Piotr Koniusz, Lei Wang, Ke Sun, ArXiV 2021
• Graph Convolutional Network with Generalized Factorized Bilinear Aggregation, Hao Zhu, Piotr Koniusz, ArXiV 2021



2020



• Few-shot Action Recognition with Permutation-invariant Attention, Hongguang Zhang, Li Zhang, Xiaojuan Qi, Hongdong Li, Philip Torr, Piotr Koniusz, European Conference on Computer Vision (ECCV), 2020 (spotlight ~3.6% acceptance rate). Also, see the Suppl. Mat.
• On Learning to Modulate the Gradient for Fast Adaptation of Neural Networks, Christian simon, Piotr Koniusz, Richard Nock, Mehrtash Harandi, European Conference on Computer Vision (ECCV), 2020. Also, see the Suppl. Mat. and the GitHub code.
• Adaptive Subspaces for Few-Shot Learning, Christian Simon, Piotr Koniusz, Richard Nock, Mehrtash Harandi, Computer Vision and Pattern Recognition (CVPR), 2020. Also, see the Supp. Mat. and the GitHub code.
• Power Normalizations in Fine-grained Image, Few-shot Image and Graph Classification, Piotr Koniusz, Hongguang Zhang, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2020, ArXiV and the IEEE Xplore.
• Tensor Representations for Action Recognition, Piotr Koniusz, Lei Wang, Anoop Cherian, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2020, ArXiV and the IEEE Xplore.
• Few-Shot Object Detection by Second-order Pooling, Shan Zhang, Dawei Luo, Lei Wang, Piotr Koniusz, Asian Conference on Computer Vision (ACCV), 2020. Also, see the Supp. Mat..
• Relation Embedding for Personalised Translation-based POI Recommendation, Xianjing Wang, Flora Salim, Yongli Ren, Piotr Koniusz, Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), 2020 (~21% acceptance rate).
• 6DoF Object Pose Estimation via Differentiable Proxy Voting Loss, Xin Yu, Zheyu Zhuang, Piotr Koniusz, Hongdong Li, The British Machine Vision Conference (BMVC), 2020. Paper on-line, Supp. Mat.
• A Token-wise CNN-based Method for Sentence Compression, Weiwei Hou, Hanna Suominen, Piotr Koniusz, Sabrina Caldwell, Tom Gedeon, International Conference on Neural Information Processing (ICONIP), 2020 (~27% acceptance rate). Also, see the Full Paper /ICONIP 2020/.
• Hallucinating Statistical Moment and Subspace Descriptors from Object and Saliency Detectors for Action Recognition, Lei Wang, Piotr Koniusz, ArXiV 2020
• Few-shot Action Recognition via Improved Attention with Self-supervision, Hongguang Zhang, Li Zhang, Xiaojuan Qi, Hongdong Li, Philip Torr, Piotr Koniusz, ArXiV 2020
• Rethinking Class Relations: Absolute-relative Few-shot Learning, Hongguang Zhang, Philip Torr, Hongdong Li, Songlei Jian, Piotr Koniusz, ArXiV 2020
• Few-shot Learning with Multi-scale Self-supervision, Hongguang Zhang, Philip Torr, Piotr Koniusz, ArXiV 2020



2019



• Fisher-Bures Adversary Graph Convolutional Networks, Ke Sun, Piotr Koniusz, Jeff Wang, Conference on Uncertainty in Artificial Intelligence (UAI), 2019 (~26% acceptance rate). Also, see the GitHub code.
• Hallucinating IDT Descriptors and I3D Optical Flow Features for Action Recognition with CNNs, Lei Wang, Piotr Koniusz, Du Q. Huynh, International Conference on Computer Vision (ICCV), 2019
• Identity-preserving Face Recovery from Stylized Portraits, Fatemeh Shiri, Xin Yu, Fatih Porikli, Richard Hartley, Piotr Koniusz, International Journal of Computer Vision (IJCV), 2019. Also, see the GitHub code and the Springer page.
• A Comparative Review of Recent Kinect-basedAction Recognition Algorithms, Lei Wang, Du Q. Huynh, Piotr Koniusz, IEEE Transactions on Image Processing (TIP), 2019
• Few-Shot Learning via Saliency-guided Hallucination of Samples, Hongguang Zhang, Jing Zhang, Piotr Koniusz, Computer Vision and Pattern Recognition (CVPR), 2019. Also, see the GitHub code.
• Deep Stacked Hierarchical Multi-Patch Network for Image Deblurring, Hongguang Zhang, Yuchao Dai, Hongdong Li, Piotr Koniusz, Computer Vision and Pattern Recognition (CVPR), 2019. Also, see the GitHub code.
• COLTRANE: ConvolutiOnal TRAjectory Network for Deep Map Inference, Arian Prabowo, Piotr Koniusz, Wei Shao, Flora Salim, ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation (BuildSys), 2019 (~21-24% acceptance rate)
• Flight Delay Prediction using Airport Situational Awarness Map, Wei Shao, Arian Prabowo, Sichen Zhao, Siyu Tan, Piotr Koniusz, Jeffrey Chan, Xinhong Hei, Bradley Feest, Flora Salim, ACM International Conference on Advances in Geographic Information Systems (SIGSPATIAL), 2019 (~21-24% acceptance rate)
• Deep Subspace Networks for Few-Shot Learning, Christian Simon, Piotr Koniusz, Richard Nock, Mehrtash Harandi, International Conference on Neural Information Processing Systems (NeurIPS) Workshop, 2019. See the Slides. Our First Version (OpenReview) from 28 Sep 2018 precedes by 8 months a weirdly similar Paper Draft (ArXiv) from 31 May 2019.
• Power Normalizing Second-order Similarity Network for Few-shot Learning, Hongguang Zhang, Piotr Koniusz, Winter Conference on Applications of Computer Vision (WACV), 2019. Also, see the GitHub code.
• Recovering Faces from Portraits with Auxiliary Facial Attributes,
  Fatemeh Shiri, Xin Yu, Fatih Porikli, Richard Hartley, Piotr Koniusz, Winter Conference on Applications of Computer Vision (WACV), 2019



2018



• Model Selection for Generalized Zero-shot Learning, Hongguang Zhang, Piotr Koniusz, European Conference on Computer Vision (ECCV) Workshop, TASK-CV 2018
• CNN-based Action Recognition and Supervised Domain Adaptation on 3D Body Skeletons via Kernel Feature Maps, Yusuf Tas, Piotr Koniusz, The British Machine Vision Conference (BMVC), 2018 (spotlight ~6% acceptance rate)
• Museum Exhibit Identification Challenge for Domain Adaptation and Beyond,
  Piotr Koniusz, Yusuf Tas, Hongguang Zhang, Mehrtash Harandi, Fatih Porikli, Rui Zhang, European Conference on Computer Vision (ECCV), 2018 (oral ~2% acceptance rate, ECCV'18 talk /YouTube/)
• Second-order Democratic Aggregation,
  Tsung-Yu Lin, Subhransu Maji, Piotr Koniusz, European Conference on Computer Vision (ECCV), 2018. Also, see the GitHub code.
• Zero-Shot Kernel Learning, Hongguang Zhang, Piotr Koniusz, Computer Vision and Pattern Recognition (CVPR), 2018. Also, see the GitHub code.
• A Deeper Look at Power Normalizations, Piotr Koniusz, Hongguang Zhang, Fatih Porikli, Computer Vision and Pattern Recognition (CVPR), 2018
• Identity-preserving Face Recovery from Portraits, Fatemeh Shiri, Xin Yu, Fatih Porikli, Richard Hartley, Piotr Koniusz, Winter Conference on Applications of Computer Vision (WACV), 2018



2017



• Face Destylization, Fatemeh Shiri, Xin Yu, Piotr Koniusz, Fatih Porikli,
  The International Conference on Digital Image Computing: Techniques and Applications (DICTA), 2017
• Domain Adaptation by Mixture of Alignments of Second- or Higher-Order Scatter Tensors,,P. Koniusz, Y. Tas, F. Porikli, Computer Vision and Pattern Recognition (CVPR), 2017
• Higher-order Pooling of CNN Features via Kernel Linearization for Action Recognition,
  A. Cherian, P. Koniusz, S. Gould, Winter Conference on Applications of Computer Vision (WACV), 2017
• Artwork Identification from Wearable Camera Images for Enhancing Experience of Museum Audiences, R. Zhang, Y. Tas, P. Koniusz, Museums and the Web (MW), 2017 (acceptance rate 25-33%).



2016



• Domain Adaptation by Mixture of Alignments of Second- or Higher-Order Scatter Tensors,
  P. Koniusz, Y. Tas, F. Porikli, ArXiv Preprint 2016
• Tensor Representations via Kernel Linearization for Action Recognition from 3D Skeletons, P. Koniusz, A. Cherian, F. Porikli, European Conference on Computer Vision (ECCV), 2016
• Tensor Representations via Kernel Linearization for Action Recognition from 3D Skeletons, P. Koniusz, A. Cherian, F. Porikli, ArXiv Preprint, 2016
• Sparse Coding for Third-order Super-symmetric Tensor Descriptors with Application to Texture Recognition, P. Koniusz, A. Cherian, Computer Vision and Pattern Recognition (CVPR), 2016 (spotlight). Also, see the local PDF copy.
• Higher-order Occurrence Pooling for Bags-of-Words: Visual Concept Detection, P. Koniusz, F. Yan, P. H. Gosselin, K. Mikolajczyk, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2016. Also, see the local PDF copy.



2015



• Dictionary Learning and Sparse Coding for Third-order Super-symmetric Tensors, P. Koniusz, A. Cherian, F. Porikli, ArXiv Preprint, 2015



2014



• Convolutional Kernel Networks, J. Mairal, P. Koniusz, Z. Harchaoui, C. Schmid, International Conference on Neural Information Processing Systems (NeurIPS), 2014 (spotlight). Also, available on ArXiV.



2013



• Higher-order Occurrence Pooling on Mid- and Low-level Features: Visual Concept Detection, P. Koniusz, F. Yan, P. H. Gosselin, K. Mikolajczyk, Technical Report (2013) that was the first version (submitted to TPAMI in 2013) of Higher-order Occurrence Pooling for Bags-of-Words: Visual Concept Detection (TPAMI 2016).
• Robust Multi-Speaker Tracking via Dictionary Learning and Identity Modelling, M. Barnard, P. Koniusz, W. Wang, J. Kittler, S. M. Naqvi, J. Chambers, IEEE Transactions on Multimedia (TMM), 2013.
• A Robust and Scalable Visual Category and Action Recognition System using Kernel Discriminant Analysis with Spectral Regression, M. A. Tahir, F. Yan, P. Koniusz, M. Awais, M. Barnard, K. Mikolajczyk, A. Bouridane, J. Kittler, IEEE Transactions on Multimedia (TMM), 2013.
• Novel Image Representations for Visual Categorisation with Bag-of-Words, P. Koniusz, PhD Dissertation (supervised by Dr. K. Mikolajczyk, reviewed by Prof. M. Bober and Prof. Theo Gevers), 2013.



2012



• Comparison of Mid-Level Feature Coding Approaches And Pooling Strategies in Visual Concept Detection, P. Koniusz, F. Yan, K. Mikolajczyk, Computer Vision and Image Undertanding (CVIU), 2012. Also, see the local PDF copy.



2011



• Spatial Coordinate Coding To Reduce Histogram Representations, Dominant Angle And Colour Pyramid Match, P. Koniusz, K. Mikolajczyk, IEEE International Conference on Image Processing (ICIP), 2011 (oral). This paper is a precursor of positional embedding so popular now in transformers. Also, see the local PDF copy.
• Soft assignment of visual words as Linear Coordinate Coding and optimisation of its reconstruction error, P. Koniusz, K. Mikolajczyk, IEEE International Conference on Image Processing (ICIP), 2011. Also, see the local PDF copy.



2010



• On a Quest for Image Descriptors Based on Unsupervised Segmentation Maps, Dominant Angle And Colour Pyramid Match, P. Koniusz, K. Mikolajczyk, IEEE International Conference on Pattern Recognition (ICPR), 2010 (oral). Also, see the local PDF copy.



2009



• Segmentation Based Interest Points and Evaluation of Unsupervised Image Segmentation Methods, P. Koniusz, K. Mikolajczyk, The British Machine Vision Conference (BMVC), 2009. Also, see the local PDF copy.

Studying for a PhD at the University of New South Wales (UNSW) and the Australian National University (ANU)

• I always look for motivated and hard-working students who are interested in doing research with me. However, you must have good mathematical and computational skills, preferably with prior experience in machine learning and/or computer vision. Strong programming skills in Python, Matlab and/or TensorFlow are a must, hands-on deep learning know-how is important too. Integrity, honesty, and ability to work under pressure and explore new problems while taking strict directions are a desired ability.
• The scholarships at the ANU and UNSW are decided by a panel on the competitive basis. Normally, 2-4 candidates are selected among as many as 20-50 applicants aspiring to join our group. The candidates are expected to come from high-quality universities highly ranked in the QS Word University Rankings, e.g. see QS Global World Ranking for the ANU. The candidates are expected to have graduated with distinction (top 1% of university cohort, often university medalists, HD grades, minimum 5% of cohort and 1st class), have a very high GPA, have outstanding references from ideally professor-level referees and often have already a paper or two in top computer vision and machine learning conferences/journals such as CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, IJCAI, AAAI, KDD, WWW, TPAMI, IJCV, TIP, TNNLS, BMVC, WACV, etc., and/or even hold patents.
• There is a round of scholarships at the Comp. Science & Engineering / UNSW due on the 9th May 2025. I believe the next round closes on the 5th September 2025. See more details here. An option may be also a scholarship from the Chinese Scholarship Council (closes on the 17 January, 2025).
• There are two rounds of CECC/ANU scholarships, e.g. one around the 1st of April, and second around the 1st of August (including the domestic round). See more details here and here though be sure to e-mail HDR/research office for key dates as they tend to move around. An option may be also a scholarship from the Chinese Scholarship Council (I believe candidates must be already in touch with CSC and ANU before December). English-wise, an IELTS (or equivalent) with an overall score of 6.5 with a minimum of 6.0 in each component is required (taken no later than one year ago but the uni. can always proceed firstly with a conditional offer).
• I do not normally accept BSc/MSc (etc.) students for honours projects etc. simply due to lack of time. However, I may make an exception if an ANU student is on their way towards obtaining a high distinction (top 1% of university cohort, running for an university medalists, having HD grades and very high GPA, or at least being in minimum 5% of cohort and going for a clear cut 1st class degree), has interest in my research work and is seriously planning on pursuing a PhD under my guidance at the ANU (and has an understanding of general requirements and dedication required during PhD studies already explained above).

0
1600
800
400
1200
24 23 22 21 20 19 18 17 16 15

• citations: 6101
• h-index: 39
• h10-index: 76

• Study for PhD
• TMCV 2017
• Open MIC (ECCV 2018 Dataset Request)
• Open MIC (ACCV 2018 Workshop)
• SecOrd CV (ICCV 2019 Tutorial)
• HigherOrd CV (ACCV 2022 Tutorial)
• Contact me

• NeurIPS+ICLR+AAAI +KDD+UAI+ACML (21 papers)
• CVPR+ICCV+ECCV (31 papers)
• TPAMI+IJCV+TIP (10 papers)
• WACV+ACCV+BMVC +ACM MM+DICTA (16 papers)
• Neurocomputing, TMM, CVIU (8 papers)
• ICIP, ICPR, ICONIP, ICASSP (11 papers)
• ArXiV (67 papers)
• oral+spotlight (17 papers)
• all papers (119 papers)