| Shape or texture: Understanding discriminative features in cnns MA Islam, M Kowal, P Esser, S Jia, B Ommer, KG Derpanis, N Bruce International Conference on Learning Representations, 2021 | 103 | 2021 |
| Position, padding and predictions: A deeper look at position information in cnns MA Islam, M Kowal, S Jia, KG Derpanis, NDB Bruce International Journal of Computer Vision, 2021 | 102 | 2021 |
| Global Pooling, More than Meets the Eye: Position Information is Encoded Channel-Wise in CNNs MA Islam, M Kowal, S Jia, KG Derpanis, NDB Bruce Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021 | 49 | 2021 |
| A deeper dive into what deep spatiotemporal networks encode: Quantifying static vs. dynamic information M Kowal, M Siam, MA Islam, NDB Bruce, RP Wildes, D Konstantinos G Proceedings of the IEEE conference on computer vision and pattern …, 2022 | 39* | 2022 |
| Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models T Fel, ES Lubana, JS Prince, M Kowal, V Boutin, I Papadimitriou, B Wang, ... International Conference on Machine Learning, 2025 | 24 | 2025 |
| Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment H Thasarathan, J Forsyth, T Fel, M Kowal, K Derpanis International Conference on Machine Learning, 2025 | 19 | 2025 |
| Understanding Video Transformers via Universal Concept Discovery M Kowal, A Dave, R Ambrus, A Gaidon, KG Derpanis, P Tokmakov (Spotlight) Proceedings of the IEEE conference on computer vision and …, 2024 | 19 | 2024 |
| Visual Concept Connectome (VCC): Open World Concept Discovery and their Interlayer Connections in Deep Models M Kowal, RP Wildes, KG Derpanis (Spotlight) Proceedings of the IEEE conference on computer vision and …, 2024 | 13 | 2024 |
| SegMix: Co-occurrence Driven Mixup for Semantic Segmentation and Adversarial Robustness MA Islam, M Kowal, KG Derpanis, NDB Bruce International Journal of Computer Vision, 2021 | 11 | 2021 |
| Feature binding with category-dependant mixup for semantic segmentation and adversarial robustness MA Islam, M Kowal, KG Derpanis, NDB Bruce (Oral) British Machine Vision Conference, 2020 | 11 | 2020 |
| It's the Thought that Counts: Evaluating the Attempts of Frontier LLMs to Persuade on Harmful Topics M Kowal, J Timm, JF Godbout, T Costello, AA Arechar, G Pennycook, ... arXiv preprint arXiv:2506.02873, 2025 | 6 | 2025 |
| Quantifying and Learning Static vs. Dynamic Information in Deep Spatiotemporal Networks M Kowal, M Siam, MA Islam, NDB Bruce, RP Wildes, KG Derpanis Transactions on Pattern Analysis and Machine Intelligence, 2024 | 5* | 2024 |
| Boundary Effects in CNNs: Feature or Bug? MA Islam, M Kowal, S Jia, KG Derpanis, N Bruce | 3 | 2020 |
| Into the rabbit hull: From task-relevant concepts in DINO to minkowski geometry T Fel, B Wang, MA Lepori, M Kowal, A Lee, R Balestriero, S Joseph, ... arXiv preprint arXiv:2510.08638, 2025 | 2 | 2025 |
| Multi-modal News Understanding with Professionally Labelled Videos (ReutersViLNews) SH Chou, M Kowal, Y Niknam, D Moyano, S Mehdi, R Pito, C Zhang, ... Canadian Artificial Intelligence Conference, 2024 | 1 | 2024 |
| Large language models can effectively convince people to believe conspiracies TH Costello, K Pelrine, M Kowal, AA Arechar, JF Godbout, A Gleave, ... arXiv preprint arXiv:2601.05050, 2026 | | 2026 |
| Emergent Persuasion: Will LLMs Persuade Without Being Prompted? V Chang, T Ho, S Dev, K Zhu, S Feng, K Pelrine, M Kowal arXiv preprint arXiv:2512.22201, 2025 | | 2025 |
| Self-supervised compositional feature representation for video understanding MP KOWAL, P Tokmakov, RA AMBRUS, AD GAIDON US Patent App. 18/807,734, 2025 | | 2025 |
| Maximizing Mutual Shape Information MA Islam, M Kowal, P Esser, B Ommer, KG Derpanis, NDB Bruce, ... British Machine Vision Conference, 2022 | | 2022 |
| An Evaluation of Modalities for Action Recognition M Kowal Toronto Metropolitan University, 2020 | | 2020 |
Konstantinos G. DerpanisYork University and Samsung AI Centre TorontoVerified email at eecs.yorku.ca
