Portrait de Kaleem Siddiqi

Kaleem Siddiqi

Membre académique associé
Professeur, McGill University, École d'informatique
Sujets de recherche
Apprentissage automatique médical
Biologie computationnelle
Neurosciences computationnelles
Vision par ordinateur
Site web
Google Scholar

Biographie

Kaleem Siddiqi est professeur d'informatique à l'Université McGill et membre du Centre sur les machines intelligentes de McGill. Il est membre académique associé de Mila – Institut québécois d’intelligence artificielle, du Département de mathématiques et de statistiques de McGill et du Centre de recherche sur le cancer Goodman de McGill. Il est titulaire d'une Chaire de recherche double en intelligence artificielle en santé / santé numérique et sciences de la vie du Fonds de recherche du Québec - Santé (FRQS) avec Keith Murai. Ses recherches portent sur la vision par ordinateur, l'analyse d'images biologiques, les neurosciences, la perception visuelle et la robotique. Il est rédacteur en chef du journal Frontiers in Computer Science et a été rédacteur en chef adjoint des IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), de Pattern Recognition et de Frontiers in ICT. Il est coauteur, avec Steve Pizer, du livre Medial Representations: Mathematics, Algorithms and Applications (Springer, 2008).

Étudiants actuels

Kathie Cai
Doctorat - McGill
Github
Elise Donszelmann-Lund
Maîtrise recherche - McGill
Github
Sophie Ellwood
Maîtrise recherche - McGill
Github
Dima Fedorenko
Doctorat - McGill
Github
Google Scholar
Isabel Frolick
Maîtrise recherche - McGill
Github
Faizan Jilani
Maîtrise recherche - McGill
Arnab Kumar-Mondal
Doctorat - McGill
Superviseur⋅e principal⋅e :
Siamak Ravanbakhsh
Site web
Github
Google Scholar
Ben Lo
Maîtrise recherche - McGill
Megan Ng
Doctorat - McGill
Marc Theveneau
Doctorat - McGill
Github
Marina Zhou
Maîtrise recherche - McGill

Publications

Predicting histopathology markers of endometrial carcinoma with a quantitative image analysis approach based on spherical harmonics in multiparametric MRI.
Thierry L. Lefebvre
Ozan Ciga
Sahir Bhatnagar
Yoshiko Ueno
S. Saif
Eric Winter-Reinhold
Anthony Dohan
P. Soyer
Reza Forghani
Kaleem Siddiqi
Jan Seuntjens
Caroline Reinhold
Peter Savadjiev
2022-10-01
Diagnostic and Interventional Imaging (publié)
doi.org
Medial Spectral Coordinates for 3D Shape Analysis
Morteza Rezanejad
Mohammad Khodadad
Hamidreza Mahyar
Hervé Lombaert
Michael Gruninger
Dirk B. Walther
Kaleem Siddiqi
In recent years there has been a resurgence of interest in our community in the shape analysis of 3D objects repre-sented by surface meshes,… (voir plus) their voxelized interiors, or surface point clouds. In part, this interest has been stimulated by the increased availability of RGBD cameras, and by applications of computer vision to autonomous driving, medical imaging, and robotics. In these settings, spectral co-ordinates have shown promise for shape representation due to their ability to incorporate both local and global shape properties in a manner that is qualitatively invariant to iso-metric transformations. Yet, surprisingly, such coordinates have thus far typically considered only local surface positional or derivative information. In the present article, we propose to equip spectral coordinates with medial (object width) information, so as to enrich them. The key idea is to couple surface points that share a medial ball, via the weights of the adjacency matrix. We develop a spectral feature using this idea, and the algorithms to compute it. The incorporation of object width and medial coupling has direct benefits, as illustrated by our experiments on object classification, object part segmentation, and surface point correspondence.
2022-06-18
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (publié)
doi.org
arxiv.org
Neural correlates of local parallelism during naturalistic vision
John Wilder
Morteza Rezanejad
Sven Dickinson
Kaleem Siddiqi
Allan Jepson
Dirk B. Walther
Human observers can rapidly perceive complex real-world scenes. Grouping visual elements into meaningful units is an integral part of this p… (voir plus)rocess. Yet, so far, the neural underpinnings of perceptual grouping have only been studied with simple lab stimuli. We here uncover the neural mechanisms of one important perceptual grouping cue, local parallelism. Using a new, image-computable algorithm for detecting local symmetry in line drawings and photographs, we manipulated the local parallelism content of real-world scenes. We decoded scene categories from patterns of brain activity obtained via functional magnetic resonance imaging (fMRI) in 38 human observers while they viewed the manipulated scenes. Decoding was significantly more accurate for scenes containing strong local parallelism compared to weak local parallelism in the parahippocampal place area (PPA), indicating a central role of parallelism in scene perception. To investigate the origin of the parallelism signal we performed a model-based fMRI analysis of the public BOLD5000 dataset, looking for voxels whose activation time course matches that of the locally parallel content of the 4916 photographs viewed by the participants in the experiment. We found a strong relationship with average local symmetry in visual areas V1-4, PPA, and retrosplenial cortex (RSC). Notably, the parallelism-related signal peaked first in V4, suggesting V4 as the site for extracting paralleism from the visual input. We conclude that local parallelism is a perceptual grouping cue that influences neuronal activity throughout the visual hierarchy, presumably starting at V4. Parallelism plays a key role in the representation of scene categories in PPA.
2022-01-21
PLoS ONE (publié)
doi.org
Neural correlates of local parallelism during naturalistic vision
John Wilder
Morteza Rezanejad
Sven J. Dickinson
Kaleem Siddiqi
A. Jepson
Dirk. B. Walther
Human observers can rapidly perceive complex real-world scenes. Grouping visual elements into meaningful units is an integral part of this p… (voir plus)rocess. Yet, so far, the neural underpinnings of perceptual grouping have only been studied with simple lab stimuli. We here uncover the neural mechanisms of one important perceptual grouping cue, local parallelism. Using a new, image-computable algorithm for detecting local symmetry in line drawings and photographs, we manipulated the local parallelism content of real-world scenes. We decoded scene categories from patterns of brain activity obtained via functional magnetic resonance imaging (fMRI) in 38 human observers while they viewed the manipulated scenes. Decoding was significantly more accurate for scenes containing strong local parallelism compared to weak local parallelism in the parahippocampal place area (PPA), indicating a central role of parallelism in scene perception. To investigate the origin of the parallelism signal we performed a model-based fMRI analysis of the public BOLD5000 dataset, looking for voxels whose activation time course matches that of the locally parallel content of the 4916 photographs viewed by the participants in the experiment. We found a strong relationship with average local symmetry in visual areas V1-4, PPA, and retrosplenial cortex (RSC). Notably, the parallelism-related signal peaked first in V4, suggesting V4 as the site for extracting paralleism from the visual input. We conclude that local parallelism is a perceptual grouping cue that influences neuronal activity throughout the visual hierarchy, presumably starting at V4. Parallelism plays a key role in the representation of scene categories in PPA.
2022-01-21
PLoS ONE (published)
doi.org
Medial Spectral Coordinates for 3D Shape Analysis
Morteza Rezanejad
Mohammad Khodadad
H. Mahyar
Hervé Lombaert
M. Gruninger
Dirk. B. Walther
Kaleem Siddiqi
In recent years there has been a resurgence of interest in our community in the shape analysis of 3D objects repre-sented by surface meshes,… (voir plus) their voxelized interiors, or surface point clouds. In part, this interest has been stimulated by the increased availability of RGBD cameras, and by applications of computer vision to autonomous driving, medical imaging, and robotics. In these settings, spectral co-ordinates have shown promise for shape representation due to their ability to incorporate both local and global shape properties in a manner that is qualitatively invariant to iso-metric transformations. Yet, surprisingly, such coordinates have thus far typically considered only local surface positional or derivative information. In the present article, we propose to equip spectral coordinates with medial (object width) information, so as to enrich them. The key idea is to couple surface points that share a medial ball, via the weights of the adjacency matrix. We develop a spectral feature using this idea, and the algorithms to compute it. The incorporation of object width and medial coupling has direct benefits, as illustrated by our experiments on object classification, object part segmentation, and surface point correspondence.
2021-11-26
ArXiv (preprint)
doi.org
arxiv.org