Multiple Instance Learning: A Survey of Problem Characteristics and Applications MA Carbonneau, V Cheplygina, E Granger, G Gagnon Pattern Recognition 77, 329-353, 2018 | 687 | 2018 |
Measuring Disentanglement: A Review of Metrics MA Carbonneau, J Zaïdi, J Boilard, G Gagnon IEEE Transactions on Neural Networks and Learning Systems, 2022 | 79 | 2022 |
A comparison of discrete and soft speech units for improved voice conversion B Van Niekerk, MA Carbonneau, J Zaïdi, M Baas, H Seuté, H Kamper ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022 | 66 | 2022 |
Robust multiple-instance learning ensembles using random subspace instance selection MA Carbonneau, E Granger, AJ Raymond, G Gagnon Pattern recognition 58, 83-99, 2016 | 60 | 2016 |
ZeroEGGS: Zero‐shot Example‐based Gesture Generation from Speech S Ghorbani, Y Ferstl, D Holden, NF Troje, MA Carbonneau Computer Graphics Forum 42 (1), 206-216, 2023 | 53 | 2023 |
Energy disaggregation using variational autoencoders A Langevin, MA Carbonneau, M Cheriet, G Gagnon Energy and Buildings 254, 111623, 2022 | 43 | 2022 |
Bag-level aggregation for multiple-instance active learning in instance classification problems MA Carbonneau, E Granger, G Gagnon IEEE transactions on neural networks and learning systems 30 (5), 1441-1451, 2018 | 36 | 2018 |
Detection of alarms and warning signals on an digital in-ear device MA Carbonneau, N Lezzoum, J Voix, G Gagnon International Journal of Industrial Ergonomics 43 (6), 503-511, 2013 | 36 | 2013 |
Feature learning from spectrograms for assessment of personality traits MA Carbonneau, E Granger, Y Attabi, G Gagnon IEEE Transactions on Affective Computing 11 (1), 25-31, 2017 | 35 | 2017 |
Intravascular Imaging and Computer Assisted Stenting, and large-scale annotation of biomedical data and expert label synthesis MJ Cardoso, T Arbel, SL Lee, V Cheplygina, S Balocco, D Mateus, ... CVII-STENT and Second International Workshop, LABELS, 2017 | 24 | 2017 |
Daft-Exprt: Cross-Speaker Prosody Transfer on Any Text for Expressive Speech Synthesis J Zaïdi, H Seuté, B van Niekerk, MA Carbonneau arXiv preprint arXiv:2108.02271, 2021 | 18* | 2021 |
Real-time visual play-break detection in sport events using a context descriptor MA Carbonneau, AJ Raymond, E Granger, G Gagnon 2015 IEEE International Symposium on Circuits and Systems (ISCAS), 2808-2811, 2015 | 16 | 2015 |
Exemplar-based stylized gesture generation from speech: An entry to the GENEA Challenge 2022 S Ghorbani, Y Ferstl, MA Carbonneau Proceedings of the 2022 International Conference on Multimodal Interaction …, 2022 | 12 | 2022 |
Witness identification in multiple instance learning using random subspaces MA Carbonneau, E Granger, G Gagnon 2016 23rd International Conference on Pattern Recognition (ICPR), 3639-3644, 2016 | 11 | 2016 |
Artist guided generation of video game production quality face textures C Murphy, S Mudur, D Holden, MA Carbonneau, D Ghafourzadeh, ... Computers & Graphics 98, 268-279, 2021 | 8 | 2021 |
Multiple instance learning under real-world conditions MA Carbonneau École de technologie supérieure, 2017 | 6 | 2017 |
Recognition of blowing sound types for real-time implementation in mobile devices MA Carbonneau, G Gagnon, R Sabourin, J Dubois 2013 IEEE 11th International New Circuits and Systems Conference (NEWCAS), 1-4, 2013 | 6 | 2013 |
Appearance controlled face texture generation for video game characters C Murphy, S Mudur, D Holden, MA Carbonneau, D Ghafourzadeh, ... Proceedings of the 13th ACM SIGGRAPH Conference on Motion, Interaction and …, 2020 | 3 | 2020 |
Score thresholding for accurate instance classification in multiple instance learning MA Carbonneau, E Granger, G Gagnon 2016 sixth international conference on image processing theory, tools and …, 2016 | 2 | 2016 |
EDMSound: Spectrogram Based Diffusion Models for Efficient and High-Quality Audio Synthesis G Zhu, Y Wen, MA Carbonneau, Z Duan NeurIPS Machine Learning for Audio Workshop, 2023 | 1 | 2023 |