Christopher Pal

Professeur agrégé / Associate Professor
École Polytechnique de Montréal
Département de génie informatique et génie logiciel


Biographie / Biography

Coordonnées / Contact Info:

Département de
génie informatique et génie logiciel
Lassonde et MacKay-Lassonde
Montréal, Québec, Canada, H3T 1J4

Téléphone / Telephone:
(514) 340-5121 x.7174 

Local / Office: M 3408 

    Recherche / Research:

    Apprentissage profond, intelligence artificielle, la vision par ordinateur, la reconnaissance de formes et l'apprentissage automatique avec des applications à l'infographie, l'analyse du langage naturel et l'exploration des données.

    Deep Learning, Artificial Intelligence, Computer vision and pattern recognition, computational photography, natural language processing, statistical machine learning and applications to human computer interaction.

Nouvelles / News


I am looking for new PhD students and postdocs interested in research at the intersection of Deep Learning, Computer Vision, Natural Language Understanding and Artificial Intelligence involving: convolutional neural networks for video, automatically describing video using natural language, medical image analysis and bioinformatics - among a few other themes and projects. I am a member of Montréal Institute for Learning Algorithms (MILA). If you are interested in applying or would like more information, please contact me directly at the address above and/or apply through the MILA admissions system.

Recherche récente / Recent Research

Vorontsov, E., Trabelsi, C., Kadoury, S., & Pal, C. (2017). On orthogonality and learning recurrent networks with long term dependencies. To appear in Proc. ICML 2017. arXiv preprint arXiv:1702.00071.

Maharaj, T., Ballas, N., Rohrbach, A., Courville, A. and Pal, C., (2017). A dataset and exploration of models for understanding video data through fill-in-the-blank question-answering. To appear in Proc. CVPR. arXiv preprint arXiv:1611.07810.

Rohrbach, A., et al. (2017). Movie Description. International Journal of Computer Vision. vol. 123, issue 1, pp. 94-120. arXiv preprint arXiv:1605.03705.

Beckham, C. and Pal, C. (2017) A new formulation for deep ordinal classification. To appear in Proc. ICML 2017. arXiv preprint arXiv:1705.05278.

Krueger, D., Maharaj, T., Kramár, J., Pezeshki, M., Ballas, N., Ke, N.R., Goyal, A., Bengio, Y., Larochelle, H., Courville, A. and Pal, C., (2017). Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations. In Proc. ICLR. arXiv preprint arXiv:1606.01305.

Maier, O. et al., (2017) ISLES 2015 - A public evaluation benchmark for ischemic stroke lesion segmentation from multispectral MRI. Medical Image Analysis. Journal Online Link

Ibrahim, M. H., Pal, C., & Pesant, G. (2016). Improving probabilistic inference in graphical models with determinism and cycles. Machine Learning, 1-54. Journal Online Link.

Honari, S., Yosinski, J., Vincent, P., & Pal, C. (2016). Recombinator Networks: Learning Coarse-to-Fine Feature Aggregation. In the Proceedings of CVPR. arXiv preprint arXiv:1511.07356.

Havaei, M., et al. (2016). Brain tumor segmentation with deep neural networks. Medical Image Analysis. Journal Online Link. arXiv preprint arXiv:1505.03540.

Witten, I. H., Frank, E., Hall, M. A., and Pal, C. J. (2016). Data Mining: Practical machine learning tools and techniques. 4th Edition. Morgan Kaufmann.

Drozdzal, M. Vorontsov, E., Chartrand, G., Kadoury, S., Pal, C. (2016) The Importance of Skip Connections in Biomedical Image Segmentation. In the 2nd Workshop on Deep Learning in Medical Image Analysis (DLMIA) at MICCAI 2016. arXiv preprint arXiv:1608.04117

Bhole, C. and Pal., C. (2016) Fully automatic person segmentation in unconstrained video using spatio-temporal conditional random fields. Image and Vision Computing. Journal Online Link

Rim, D., Honari, S., Hasan, M. K., & Pal, C. (2016). Improving Facial Analysis and Performance Driven Animation through Disentangling Identity and Expression. Image and Vision Computing. Journal Online Link. arXiv preprint arXiv:1512.08212

Moniz, J. and Pal, C. (2016). Convolutional Residual Memory Networks. arXiv preprint arXiv:1606.05262

The Theano Development Team, (2016). Theano: A Python framework for fast computation of mathematical expressions. arXiv preprint arXiv:1605.02688.

Vorontsov, E., Tang, A., Roy, D., Pal, C. J., & Kadoury, S. (2016). Metastatic liver tumour segmentation with a neural network-guided 3D deformable model. Medical & biological engineering & computing, 1-13. Journal Online Link

Thong, W., Kadoury, S., Piché, N., & Pal, C. J. (2016). Convolutional networks for kidney segmentation in contrast-enhanced CT scans. Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 1-6. Journal Online Link

Harvey, F. G., & Pal, C. (2015). Semi-supervised Learning with Encoder-Decoder Recurrent Neural Networks: Experiments with Motion Capture Sequences. arXiv preprint arXiv:1511.06653.

Ballas, N., Yao, L., Pal, C. and Courville, A. (2015). Delving Deeper into Convolutional Networks for Learning Video Representations. In the Proceedings of ICLR. arXiv preprint arXiv:1511.06432.

Kahou, S.E., Michalski, V., Konda, K., Memisevic, R., and Pal, C. Recurrent Neural Networks for Emotion Recognition in Video, In the proceedings of ICMI 2015.

Li Yao, Atousa Torabi, Kyunghyun Cho, Nicolas Ballas, Christopher Pal, Hugo Larochelle and Aaron Courville. Describing Videos by Exploiting Temporal Structure. In the proceedings of ICCV 2015. Preprint on [arxiv]

Brain Tumor Segmentation with Deep Neural Networks [arxiv] Mohammad Havaei, Axel Davy, David Warde-Farley, Antoine Biard, Aaron Courville, Yoshua Bengio, Chris Pal, Pierre-Marc Jodoin, Hugo Larochelle, arXiv, 2015.

Using Descriptive Video Services to Create a Large Data Source for Video Annotation Research [arxiv] Atousa Torabi, Christopher Pal, Hugo Larochelle and Aaron Courville, arXiv, 2015.

Ibrahim, M., Pal, C., and Pesant, G. (2015) Exploiting Determinism to Scale Relational Inference, To appear in the proceedings of AAAI 2015.

Rim, D., Hasan, M.K., Puech, F., and Pal, C. (2015) Learning from Weakly Labeled Faces and Video in the Wild, Pattern Recognition, Vol. 48, Issue 3, Pages 759-771.

Axel Davy, Mohammad Havaei, David Warde-Farley, Antoine Biard, Lam Tran, Pierre-Marc Jodoin, Aaron Courville, Hugo Larochelle, Chris Pal, and Yoshua Bengio (2014) Brain Tumor Segmentation with Deep Neural Networks. In the BRATS 2014 workshop at MICCAI 2014. The poster for this work is also available here.

Kahou, S.E., Froumenty, P. and Pal, C. (2014) Facial Expression Analysis Based on High Dimensional Binary Features. In proceedings of the ECCV 2014 workshop on computer vision with local binary patterns. Note: this paper received the best paper award.

Hasan, Md. K. and Pal, C. (2014) Experiments on Visual Information Extraction with the Faces of Wikipedia. In the Proceedings of AAAI 2014. Please see the project webpage if you wish to use the data.

Kahou, S. E., Pal, C., Bouthillier, X., Froumenty, P., Gülçehre, Ç., *, Memisevic, R., Vincent, P., Courville, A. and Bengio, Y. (2013) Combining Modality Specific Deep Neural Networks for Emotion Recognition in Video. In Proceedings of the 15th ACM International Conference on Multimodal Interaction (ICMI '13) pp. 543-550. [ACM digital library definitive version].

*Note: Please see the additional authors section in the .pdf of the paper above for the full author list. Additional authors should be inserted at the *. (This paper describes our winning entry to the ICMI 2013 Grand Challenge on Emotion Recognition in the Wild. The challenge baseline accuracy was 27.5% - our approach yielded 41.0%)

Enseignement / Teaching

Automne 2016, INF 8702 - Infographie avancée (Advanced Computer Graphics)
Hiver 2016, INF 8225 - Intelligence artificielle : techniques probabilistes et d'apprentissage
Automne 2014, INF 8702 - Infographie avancée (Advanced Computer Graphics)
Automne 2014 INF 1005A - Programmation procédurale
Hiver 2014, INF 8225 - Intelligence artificielle : techniques probabilistes et d'apprentissage
Automne 2013, INF 8702 - Infographie avancée (Advanced Computer Graphics)
Automne 2013, INF 1005A - Programmation procédurale
Hiver 2013, INF 8225 - Intelligence artificielle : techniques probabilistes et d'apprentissage
Hiver 2013, INF 1005A - Programmation procédurale
Automne 2012, INF 8702 - Infographie avancée (Advanced Computer Graphics)
Hiver 2012, INF 8225 - Intelligence artificielle : techniques probabilistes et d'apprentissage
Automne 2011, INF 1005A - Programmation procédurale
Automne 2011, INF 8702 - Infographie avancée (Advanced Computer Graphics)
Hiver 2011, INF 8953A - Intelligence artificielle : concepts et applications
Automne 2010, INF 8702 - Infographie avancée (Advanced Computer Graphics)
Hiver 2010, INF 4215 - Introduction à l'intelligence artificielle (Intro. AI)
Automne 2009, INF 8702 - Infographie avancée (Advanced Computer Graphics)
Hiver 2009, INF 6953E - Multimedia Data Analysis and Processing
Winter (Rochester) 2008, CSC 577 - Seminar in AI: Advanced Topics in Pattern Recognition
Fall (Rochester) 2007, CSC 290A - Topics in CS: Computational Photography and Video

More Contributions

Bhole, Chetan and Pal, Christopher and Rim, David and Wismüller, Axel (2013) 3D segmentation of abdominal CT imagery with graphical models, conditional random fields and learning. Machine Vision and Applications, pp. 1-25 (Springer Online First Article).

Messing, R., Torabi, A., Courville, A. and Pal, C. (2013) Evaluating and Extending Trajectory Features for Activity Recognition. Invited book chapter (to appear).

Hasan, M.K. and Pal, C. (2012) Creating a Big Data Resource from the Faces of Wikipedia. In the proceedings of BigVision 2012 (NIPS Workshop).

Bhole, C. and Pal, C. (2012) Automated Person Segmentation in Videos In the proceedings of ICPR 2012.

Pal, C., Weinmann, J.J., Tran, L.C., and Scharstein, D. (2012) On Learning Conditional Random Fields for Stereo : Exploring Model Structures and Approximate Inference International Journal of Computer Vision (IJCV). [IJCV Online link], vol. 99, no. 99, pp. 319-337.

Tran, L.C., Bal, C. Pal, C. and Nguyen, T.Q. (2012) On consistent inter-view synthesis for autostereoscopic displays. 3D Research, vol. 3, no. 1, pp. 1-10.

Rim, D., Hasan, K. and Pal, C. (2011) Semi Supervised Learning for Wild Faces and Video. In Proc. BMVC.

Wei, B. and Pal, C. (2011) Heterogeneous Transfer Learning with RBMs. In Proc. AAAI.

Bhole, C., Morsillo, N. and Pal, C. (2011) 3D Segmentation in CT Imagery with Conditional Random Fields and Histograms of Oriented Gradients. In the Second International Workshop on Machine Learning in Medical Imaging (MLMI), held in conjunction with MICCAI 2011.

Hasan, K. M. and Pal, C. (2011) Improving Alignment of Faces for Recognition. IEEE Symposium on Robotic and Sensors Environments (ROSE).

Tran, L. Khoshabeh, R., Jain, A., Pal, C. and Nguyen, T. (2011) Spatially Consistent View Synthesis with Coordinate Alignment. In Proc. IEEE ICASSP.

Jojic, N. and Pal, C. (2011) Interactive montages of sprites for indexing and summarizing video. US Patent 7,982,738.

Tram, L., Pal, C. and Nguyen, T.Q. (2010)
View Synthesis Based on Conditional Random Fields and Graph-cuts In the proceedings of ICIP.

Morsillo, N., Mann, G., and Pal, C. (2010) YouTube Scale, Large Vocabulary Video Annotation. Book chapter to appear in Video Search and Mining, Springer-Verlag series on Studies in Computational Intelligence.

Wei, B. and Pal, C. (2010) Cross Lingual Adaptation: An Experiment on Sentiment Classifications. In the proceedings of the ACL.

Messing, R., Pal, C., and Kautz, H. (2009) Activity recognition using the velocity histories of tracked keypoints. In the proceedings of ICCV 2009. Note: our data and code can also be found on the [Project Page].

Morsillo, N., Pal, C. and Nelson, R. (2009) Semi-Supervised Learning of Visual Classifiers from Web Images and Text. In the proceedings of the International Joint Conference on Artificial Intelligence (IJCAI).

Chris Pal, Drew Steedly and Richard Szeliski. (2008) Video registration and image sequence stitching. US Patent 7,460,730.

Patrick Baudish, Chris Pal, Eric Rudolph, Drew Steedly, Richard Szeliski, Desney Tan and Matthew Uyttendaele. (2008) Real-time preview for panoramic images. US Patent 7,424,218 .

with Jerod Weinman and Lam Tran. (2008) Efficiently Learning Random Fields for Stereo Vision with Sparse Message Passing. In proc. European Conf. on Computer Vision (ECCV), Springer-Verlag LNCS, vol. 1, pp. 617-630.

with Gideon Mann and Richard Minerich. (2007) Putting Semantic Information Extraction on the Map: Noisy Label Models for Fact Extraction. In the proceedings of the AAAI Workshop on Information Integration on the Web (IIWeb 2007).

with Xuerui Wang and Andrew McCallum. (2007) Generalized Component Analysis for Text with Heterogeneous Attributes In the proceedings of Knowledge Discovery and Data Mining (KDD).

with Greg Druck, Jerry Zhu and Andrew McCallum. (2007) Semi-Supervised Classification with Hybrid Generative/Discriminative Methods. In the proceedings of Knowledge Discovery and Data Mining (KDD).

with Pallika Kanani and Andrew McCallum. (2007) Improving Author Coreference by Resource-bounded Information Gathering from the Web In the proceedings of the Twentieth International Joint Conference on Artificial Intelligence (IJCAI).

with Daniel Scharstein (2007) Learning Conditional Random Fields for Stereo In the proceedings of Computer Vision and Pattern Recognition (CVPR).

with Manjunatha N. Jagalur, Erik Learned-Miller, R. T. Zoeller and David Kulp. (2007) Analyzing in situ Gene Expression in the Mouse Brain with Image Registration, Feature Extraction and Block Clustering BMC Bioinformatics vol. 8, suppl. 10, Dec. 21. [BMC Online]

with Patrick Baudisch, Desney Tan, Drew Steedly, Eric Rudolph, Matt Uyttendaele and Richard Szeliski. (2006) An Exploration of User Interface Designs for Real-time Panoramic Photography. Australian Journal of Information Systems (AJIS), vol. 13, no. 2.

Chris Pal, Michael Kelm, Xuerui Wang, Greg Druck and Andrew McCallum (2006) On Discriminative and Semi-Supervised Dimensionality Reduction. In Advances in Neural Information Processing Systems (NIPS) Workshop on Novel Applications of Dimensionality Reduction.

with Michael Kelm and Andrew McCallum. (2006) Combining Generative and Discriminative Methods for Pixel Classification with Multi-Conditional Learning In the proceedings of ICPR 2006. vol. 2 pp. 828-832. [BibTeX]

with Charles Sutton and Andrew McCallum. (2006) Sparse Forward-Backward using Minimum Divergence Beams for Fast Training of Conditional Random Fields. In the proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), vol. 5, pp. 581-584.[BibTeX]

with Andrew McCallum, Greg Druck and Xuerui Wang. (2006) Multi-Conditional Learning: Generative/Discriminative Training for Clustering and Classification In the proceedings of AAAI 2006.[BibTeX]

with Manjunatha N. Jagalur, Erik Learned-Miller, R. T. Zoeller and David Kulp. (2006) The Processing and Analysis of in situ Gene Expression Images of the Mouse Brain. In Advances in Neural Information Processing Systems (NIPS) Workshop on New Problems and Methods in Computational Biology. [Project Page].

with Drew Steedly and Richard Szeliski. (2005) Efficiently Registering Video into Panoramic Mosaics.In the proceedings of the IEEE International Conference on Computer Vision, ICCV 2005, Beijing, China, October 15-21.[BibTeX] [Project Page]

Aseem Agarwala, Colin Zheng, Chris Pal, Maneesh Agrawala, Michael Cohen, Brian Curless, David Salesin, and Richard Szeliski. (2005) Panoramic video textures. Proceedings of ACM SIGGRAPH 2005, ACM Transactions on Graphics, vol. 24, issue 3, pp. 821-827.[BibTeX] [Project Page] [Video (.wmv)]

Pal, C. and Jojic, N. (2005) Interactive Montages of Sprites for Indexing and Summarizing Security Video. In the Video Proceedings of IEEE Computer Vision and Pattern Recognition, CVPR 2005. vol. 2, pp. 1192.[BibTeX] [Video (.wmv)]

Baudisch, P., Tan, D., Steedly, D., Rudolph, E., Uyttendaele, M.,
Pal, C., and Szeliski, R. (2005) Panoramic Viewfinder: providing a real-time preview to help users avoid flaws in panoramic pictures. In the Proceedings of OZCHI 2005, Canberra, Australia, November 2005.[BibTeX] [Project Page] [Video (.mov)]

Pal, C. (2004) Probability Models for Information Processing and Machine Perception. PhD Thesis, University of Waterloo.

Pal, C., Szeliski, R., Uyttendaele, M. and Jojic, N. (2004) Probability Models for High Dynamic Range Imaging. In the Proceedings of IEEE Computer Vision and Pattern Recognition, CVPR 2004. vol. 2, pp. 173-180.[BibTeX] [Project Page]

Peng, W., et al. (2003) A Panoramic View of Yeast Non-Coding RNA processing. Cell, vol. 113, pp. 919-933.[BibTeX]

Pal, C., Frey, B. and Jojic, N. (2002) Learning Montages of Transformed Latent Images as Representations of Objects that Change in Appearance. In the proceedings of ECCV: The European Conference on Computer Vision, Springer-Verlag lecture notes in Computer Science, vol. 4, pp. 715-731. [BibTeX]

Pal, C., Frey, B. and Kristjansson, T. (2002) Noise Robust Speech Recognition Using Gaussian Basis Functions For Non-linear Likelihood Function Approximation . In the proceedings of IEEE ICASSP: International Conference on Acoustics Speech and Signal Processing, Orlando, Florida May 13-17, 2002.[BibTeX]

Pal, C. (2001) Probabilistic Models and Decision Problems . An Invited Tutorial Presented at the International Symposium for Environmental Software Systems, ISESS 2001, Banff, Alberta, Canada, May 22-25, 2001.

Pal, C. and Hu, M. (2001) Methodologies for Constructing and Training Large Hierarchical Hidden Markov Models for Sequence Analysis . Research in Computational Biology. RECOMB 2001. Abstract for Poster Presentation. April 22-25, 2001. Poster [here] in .pdf format (Note: you will need a recent version of Adobe Acrobat to view properly): 

Pal, C. Swayne, D. and Frey, B. (2001) The Automated Extraction of Environmentally Relevant Features from Digital Imagery using Bayesian Multi-Resolution Analysis . Advances in Environmental Research. vol. 5, issue 4, pp 435-444.

Dorner, S. Swayne, D. A., Rudra, R. P., Pal, C., Newald, C. (2001) Integrating Parametric Uncertainty and Modelling Results into an Advisory System for Watershed Management . Advances in Environmental Research.. vol. 5, issue 4, pp. 445-451

Pal, C., Slaney, M. and Adams, R. (2000) Sound-based Event Control Using Timbral Analysis . United States Patent number: 6,054,646

Pal, C. (2000) A Probabilistic Approach to Image Feature Extraction, Segmentation and Interpretation . Masters of Mathematics Thesis. University of Waterloo. 

Pal, C. Swayne, D. and Frey, B. (2000) Image Interpretation and Segmentation with Hierarchical Probabilistic Models . 4th International Conference on Integrating GIS and Environmental Modeling (GIS/EM4). Banff, Alberta , Canada, September 2-8, 2000. 

Dorner, S., Pal, C. and Swayne, D.A. (1999) Case Libraries and Information Theoretic Case Matching for Water Resource Management. Proceedings of  ISESS 1999, The International Symposium on Environmental Software Systems

Pal, C. (1998) A Technique for Illustrating Dynamic Component Level Interactions Within a Software Architecture . Proceedings of CASCON 1998. The IBM Centre for Advanced Studies Conference . pp. 134-146. 

MacKenzie, I.S., Soukoreff, R.W. & Pal, C. (1997) A two ball mouse affords three degrees of freedom . Extended Abstracts of CHI 1997. The ACM Conference on Human Factors in Computing Systems , pp. 303-304. New York: ACM.


Conférences invitées / Selected Invited Talks

Jan. 2009, McGill University - Montreal
May 2008, University of Rochester - Computer Science Graduation Ceremony
Oct. 2007, Cornell - Bill and Melinda Gates Foundation Workshop
March 2007, Google
March 2007, MIT
Dec. 2006, Kodak Research
Dec. 2006, Michael Smith Genomic Sciences Centre - Vancouver
Nov. 2006, McGill University - Montreal
Sept. 2006, Invention to Venture - University of Massachusetts Business School, Guest Speaker
Sept. 2006, Advanced Invention to Venture - Massachusetts Biomedical Center, UMass Worcester
Sept. 2006, Canadian Independent Media Arts Alliance - National Conference Speaker
July 2006, Microsoft Research - Redmond, WA.
May 2006, Microsoft Research - Cambridge, UK.

Chris Pal (2006) What Did We See? A Talk for Microsoft Research's Memex Day.

Copyright Information:

All copyrights for these documents are retained by the copyright holder, and permission to copy this work should be obtained from the copyright holder in writing. This copyright notice must be kept together with the downloaded or printed document.

In my opinion, there are some nice images on this site as well. I believe the low resolution version of the images belong to the paper copyright holders while the high resolution versions belong to some combination of the photographers, my co-authors and myself. I am looking into this issue and will post a statement as soon as I can get a clearer determination.

Older Technical Reports and Course Projects  

Kamel, M. Keast, J. and Pal, C. (1997) The Architecture of the Linux Kernel

Pal, C. (1997) Multimedia Vector Processing

Pal, C. (2000) Learning and Representing Semantic Information in WordNet and MindNet. 

Pal, C. (2000) Numerical Methods for Pricing Financial Options

Pal, C. (2000) Probabilistic Models for Document Collections: Latent Semantic Indexing

Hu, M. Ingram, C. Sirski, M. Pal, C., Swamy, S. Patten, C. (2000) A Hierarchical HMM Implementation for Vertebrate Gene Splice Site Prediction

Older Presentations

The SVD, Principal Component Analysis and the Latent Semantic Indexing of Documents

Masters Thesis Presentation

Some links to past and present mentors and collaborators

Brendan Frey (University of Toronto, ECE),
Tim Hughes (University of Toronto, Medical Research),
Nebojsa Jojic (Microsoft Research),
Trausti Kristjansson (Google),
Andrew McCallum (University of Massachusetts, CS),
Quaid Morris (University of Toronto),
Sam Roweis University of Toronto, CS),
Malcolm Slaney (Yahoo Research),
Rick Szeliski (Microsoft Research),
Matt Uyttendaele (Microsoft Research)