Marco Pedersoli
Assistant Professor
ETS Montreal
email
phone: +1 (514) 396-8742
office: A-3480

Since February 2017 I am assistant professor at École de technologie supérieure (ETS), the youngest and fastest-growing university located in the center of Montreal, the AI Mountain!

In 2015-2016 I have been post-doc in THOTH at INRIA Grenoble with Dr. Cordelia Schmid and Dr. Jakob Verbeek. From 2012 to 2015 I was in VISICS at KU Leuven with prof. Tinne Tuytelaars. I obtained my Ph.D. at the Computer Vision Center and the Autonomous University of Barcelona (UAB) under the supervision of Jordi Gonzàlez and Juan José Villanueva. For more details check my CV.

The current bottleneck in deep learning is not much about the amount of available data, but rather the capability to process this data and the cost of annotating it.

My main objectives are:

  • investigate and develop methodologies to reduce the computational cost of modern visual recognition techniques and models.
  • find strategies and new algorithms to improve these methods performance on limited training data and/or annotations.

    • This will open the doors to the deployment of modern computer vision algorithms on the increasingly demanding market of small and computation limited portable and embedded devices.

    I am looking for motivated PhD students in the field of Computer Vision and Machine Learning. Their research will focus on learning deep models with reduced supervision; for instance, but not limited to weakly-supervised learning, semi-supervised learning, active learning on images, video, audio and text. Also, methods for reducing the computational cost of deep learning approaches will be investigated and developed. Apart form this position, you can find research funds opportunities to work in my lab at this page.

    Position:

  • The successful candidates will be conducting cutting-edge research at ETS, the youngest and fastest-growing university located in the heart of Montreal!
  • Possible collaborations with top labs in Canada and abroad.
  • Salaries are competitive and tax-free!

    • Qualifications:

  • Hold a MSc in computer science or related fields.
  • Strong mathematical background.
  • Strong programming in Python, C/C++, Matlab.
  • Knowledge of Deep Learning libraries such as pytorch, keras, MatConvNet.

    • Application:

  • Send a motivation letter including your CV, transcript of records and the names of 2 references to Prof. Marco Pedersoli (email).

    • Weakly Supervised Learning

  • Deep Learning with reduced Supervision: Deep learning requires Big data, but what about annotations? Do we really need each sample to be annotated? How far can we go with a reduced set of annotations? Can we compensate the lack of annotations with more computation? Is it better to use a few clean annotations or more but noisy annotations?
  • Learning where to position parts in 3D, Marco Pedersoli, Tinne Tuytelaars, in ICCV, December 2015. (pdf poster)
  • Weakly Supervised Object Detection with Convex Clustering, Hakan Bilen, Marco Pedersoli, Tinne Tuytelaars, in CVPR, June 2015. (pdf)
  • Is 2D information enough for viewpoint estimation?, Amir Ghodrati, Marco Pedersoli, Tinne Tuytelaars, in BMVC, September 2014. (pdf)
  • Weakly Supervised Object Detection with Posterior Regularization, Hakan Binen, Marco Pedersoli, Tinne Tuytelaars, in BMVC, September 2014. (pdf)
  • Using a deformation field model for localizing faces and facial points under weak supervision, Marco Pedersoli, Tinne Tuytelaars, Luc Van Gool, in CVPR, June 2014. (pdf,video1,video2,video3)
  • Object Classification with Adaptable Regions, Hakan Bilen, Marco Pedersoli, Vinay P. Namboodiri, Tinne Tuytelaars, Luc Van Gool, in CVPR, June 2014. (pdf)

    • Explore Data

  • Learning by Exploration: Most of the common datasets used in Computer Vision are composed of samples (e.g. images) and labels (e.g. image categories). This is an ideal case that makes training and evaluation clear and simple. However, in the real world often data comes from an environment that should be explored. Here then new, yet very interesting problems appear. How to select from which data to learn? How and when to use supervision if the size of the environment to explore is exponentially large? How to evaluate the performance?
  • Combining where and what in change detection for unsupervised foreground learning in surveillance, Ivan Huerta, Marco Pedersoli, Jordi Gonzàlez, Alberto Sanfeliu, in Pattern Recognition 48 (3), 709-719, 2015. (pdf)
  • An Elastic Deformation Field Model for Object Detection and Tracking, Marco Pedersoli, Radu Timofte, Tinne Tuytelaars, Luc Van Gool, International Journal of Computer Vision, June 2014. (pdf)

    • Efficient Computation

  • Efficient Computation: Datasets are getting larger and predictive models are becoming computationally very expensive. In this research line we study and propose methods for reducing the computational cost of deep learning models at both training and inference time.
  • DeepProposal: Hunting Objects by Cascading Deep Convolutional Layers, Amir Ghodrati, Ali Diba, Marco Pedersoli, Tinne Tuytelaars, Luc Van Gool, in ICCV, December 2015. (pdf)
  • A scalable 3D HOG model for fast object detection and viewpoint estimation, Marco Pedersoli, Tinne Tuytelaars, in 3DV, December 2014. (pdf)
  • Toward Real-Time Pedestrian Detection Based on a Deformable Template Model, Marco Pedersoli, Jordi Gonzàlez, Xu Hu, Xavier Roca, IEEE Transactions on Intelligent Transportation Systems, 15(1), September 2013. (pdf)
  • Hierarchical Multiresolution Models for fast Object Detection, Marco Pedersoli, Phd Thesis, September 2012. (pdf,bib)
  • A Coarse-to-fine approach for fast deformable object detection, Marco Pedersoli, Andrea Vedaldi, Jordi Gonzàlez, in CVPR, June 2011. (pdf,pptx,bib)
  • Recursive Coarse-to-Fine Localization for fast Object Detection , Marco Pedersoli, Jordi Gonzàlez, Andrew D. Bagdanov, Juan J. Villanueva, in ECCV, September 2010. (pdf,poster,bib)

    • Privacy-Preserving Person Detection Using Low-Resolution Infrared Cameras,T Dubail, FAG Peña, HR Medeiros, M Aminbeidokhti, E Granger, in ECCV Workshop, 2022. (pdf)
    • Semi-Weakly Supervised Object Detection by Sampling Pseudo Ground-Truth Boxes, A Meethal, M Pedersoli, Z Zhu, FP Romero, E Granger, in IJCNN, 2022. (pdf)
    • Self-paced contrastive learning for semi-supervised medical image segmentation with meta-labels,Jizong Peng, Ping Wang, Christian Desrosiers, Marco Pedersoli, in NeurIPS, 2021. (pdf)
    • Adversarial Learning of General Transformations for Data Augmentation, Saypraseuth Mounsaveng, David Vazquez, Ismail Ben Ayed, Marco Pedersoli, in ICLR Workshop, 2019. (pdf)
    • An Attention Model for group-level emotion recognition, Aarush Gupta, Dakshit Agrawal, Hardik Chauhan, Jose Dolz, Marco Pedersoli, in ACM International Conference on Multimodal Interaction, October 2018. (pdf)
    • Areas of Attention for Image Captioning, Marco Pedersoli, Thomas Lucas, Cordelia Schmid, Jakob Verbeek, in International Conference of Computer Vision, October 2017. (pdf)
    • DeepProposal: Hunting Objects and Actions by Cascading Deep Convolutional Layers, Amir Ghodrati, Ali Diba, Marco Pedersoli, Tinne Tuytelaars, Luc Van Gool, in International Journal of Computer Vision, March 2017. (pdf,iccv15,code)
    • Towards Automatic Image Editing: Learning to See another You, Xu Jia, Amir Ghodrati, Marco Pedersoli, Tinne Tuytelaars in BMVC, September 2016. (pdf,extended abstract,code)
    • Learning where to position parts in 3D, Marco Pedersoli, Tinne Tuytelaars, in ICCV, December 2015. (pdf,3DV14,poster,code)
    • Swap Retrieval: Retrieving Images of Cats When the Query Shows a Dog, Amir Ghodrati, Xu Jia, Marco Pedersoli, Tinne Tuytelaars, in ICMR, June 2015. (pdf)
    • Combining where and what in change detection for unsupervised foreground learning in surveillance, Ivan Huerta, Marco Pedersoli, Jordi Gonzàlez, Alberto Sanfeliu, in Pattern Recognition,Vol.48(3), 709-719, 2015 (pdf)
    • Weakly Supervised Object Detection with Convex Clustering, Hakan Bilen, Marco Pedersoli, Tinne Tuytelaars, in CVPR, June 2015. (pdf)
    • A Coarse-to-fine approach for fast deformable object detection, Marco Pedersoli, Andrea Vedaldi, Jordi Gonzàlez, in Patter Recognition, Vol.48(5), May 2015. (pdf,cvpr11,pptx,code)
    • Face detection without bells and whistles, Markus Mathias, Rodrigo Benenson, Marco Pedersoli, Luc Van Gool, in ECCV, September 2014. (pdf,odp,project)
    • Is 2D information enough for viewpoint estimation?, Amir Ghodrati, Marco Pedersoli, Tinne Tuytelaars, in BMVC, September 2014. (pdf)
    • Weakly Supervised Object Detection with Posterior Regularization, Hakan Binen, Marco Pedersoli, Tinne Tuytelaars, in BMVC, September 2014. (pdf)
    • Using a deformation field model for localizing faces and facial points under weak supervision, Marco Pedersoli, Tinne Tuytelaars, Luc Van Gool, in CVPR, June 2014. (pdf,video1,video2,video3,code)
    • Object Classification with Adaptable Regions, Hakan Bilen, Marco Pedersoli, Vinay P. Namboodiri, Tinne Tuytelaars, Luc Van Gool, in CVPR, June 2014. (pdf)
    • An Elastic Deformation Field Model for Object Detection and Tracking, Marco Pedersoli, Radu Timofte, Tinne Tuytelaars, Luc Van Gool, International Journal of Computer Vision, June 2014, (pdf,report)
    • Toward Real-Time Pedestrian Detection Based on a Deformable Template Model, Marco Pedersoli, Jordi Gonzàlez, Xu Hu, Xavier Roca, IEEE Transactions on Intelligent Transportation Systems, 15(1), September 2013. (pdf)
    • Hierarchical Multiresolution Models for fast Object Detection, Marco Pedersoli, Phd Thesis, September 2012. (pdf,bib)

      • For the complete list of my publications check my google scholar.

    • Roi-Pooling in Lasagne. Porting of R-CNN roi-pooling in Lasagne github.

    • Weakly Supervised Detection. Python (Caffe) Code based on Fast RCNN for weakly supervised detection github.

    • Face detection evaluation code. Python and C source code bitbucket.

    • Fast 3D Object Detection. Python and C source code github.

    • Deformation Field Model. Python and C source code github.

    • Coarse-to-fine Deformable Object Detection. Python and C code of a demo version. A complete version with also the training part github.

    • ETS: "Réseaux de Neurones et Intelligence Artificielle" Autumn 2018
    • ETS: "Apprentissage Machine" Hiver 2018
    • ETS: "Réseaux de Neurones et Intelligence Artificielle" Autumn 2017
    • KU Leuven: Embedded Systems and Multimedia 2014
    • Teachning assiatant in UAB: Computer Science 2009-2012
    • Teachning assiatant in UAB: Bioinformatics 2009-2012
    • Teachning assiatant in UAB: Computational Logic 2008-2009

      PostDoc:

    • Fidel Alejandro Guerrero Peña (with Eric Granger)

      • PhD:

    • Saypraseuth Mounsaveng (with Ismail Ben Ayed)
    • Akhil P M (with Erc Granger)
    • Mehraveh Javan (wtih Matthew Toews)
    • Masih Aminbeidokhti (with Erc Granger)
    • Heitor Rapela Medeiros (with Erc Granger)
    • Jose Fabian Villa
    • Shakeeb Murtaza (with Eric Granger)
    • Nasib Ullah (with Eric Granger)
    • Osama Zeeshan (with Eric Granger)
    • Shakeeb Murtaza (with Eric Granger)

      • MSc:

    • Mirmohammad Saadati (wtih Patrick Cardinal)
    • Lucas Huyghues-Beaufond
    • David Latortue
    • Mishra Shambhavi (with José Dolz)
    • Thomas Dubail (with Erc Granger)

      • PhD Graduated:

    • Jizong Peng (now at Huawei)

      • MSc Graduated:

    • Masih Aminbeidokhti (now PhD)
    • Théo Arial (now PhD)
    • Kristof Boucher Charbonneau (now at Radio Canada)

    • Python for scientific computation (pdf,link)

    News:
  • Two papers accepted in WACV2023!!
  • I was in medical leave for a while, but now I am back ;)
  • Best paper award ICIAR 2019!
  • Presentation at Trento University
  • Interesting talk at CVC Barcelona
  • Presentation of my research at Element AI
  • The code of our EmotiW Attention method is now available here!
  • Our submission to EmotiW ranked 4th and it is published in ICMI'18!
  • Areas of Attention for Image Captioning got accepted in ICCV17!
  • Received the donation of a Titan X Pascal. Thanks NVIDIA!
  • An extension of Deep Proposals have been accepted in IJCV!
  • Looking for motivated Ph.D. students. Check how to apply!
  • I am Tutorials Chair at IPTA17
  • Areas of Attention for Image Captioning
  • Moving to ETS Montreal!!!