Marco Pedersoli

Marco Pedersoli
Professeur
Formation B. Eng. (Universita degli studi di Brescia, Italie), M.Sc., Ph.D. (Universitat Autonoma de Barcelona & Computer Vision Center, Espagne)
Bureau A-3480
Téléphone 514 396-8742
Présentation

Département de génie des systèmes

Axes de recherche :

  • Technologies de l’information et des communications

Expertises :

  • Réseaux de neurones artificiels
  • Apprentissage machine
  • Vision artificielle
  • Reconnaissance de formes
  • Réseaux à convolution
  • Réseaux récurrents
  • Apprentissage faiblement supervisé
  • Apprentissage non supervisé
  • Réduction de coût de calcul dans l'apprentissage
  • Apprentissage sur systèmes embarqués
Publications: article

Publications: conference_item
Image Analysis and Recognition : 16th International Conference, ICIAR : Proceedings
Publications: conference_item
27th IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Publications: conference_item
IEEE Conference on Computer Vision and Pattern Recognition, (CVPR)
Publications: conference_item
Proceedings British Machine Vision Conference
Publications: book_section
Multimodal interaction in image and video applications
Publications: conference_item
5th International Conference on Articulated Motion and Deformable Objects (AMDO) 2008, July 9, 2008 - July 11, 2008
Publications: conference_item
15th IEEE International Conference on Computer Vision ( ICCV)
Publications: article

Publications: conference_item
5th ACM International Conference on Multimedia Retrieval (ICMR)
Publications: conference_item
2014 IEEE Winter Conference on Applications of Computer Vision (WACV)
Publications: conference_item
Proceedings British Machine Vision Conference
Publications: conference_itemau

Publications: conference_itemau

Publications: article

Publications: conference_item
20th ACM International Conference on Multimodal Interaction (ICIM '18)
Publications: article

Publications: conference_item
Proceedings of the British Machine Vision Conference
Publications: conference_item
Computer Vision - ECCV 2014 : 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part IV
Publications: conference_itemau

Publications: thesis

Publications: conference_item
Computer Vision - ECCV 2010 : 11th European Conference on Computer Vision, Heraklion, Crete, Greece, September 5-11, 2010, Proceedings, Part VI
Publications: book_section
Computer Recognition Systems 2
Publications: article

Publications: conference_item
Pattern Recognition and Image Analysis : 4th Iberian Conference, IbPRIA 2009 Póvoa de Varzim, Portugal, June 10-12, 2009 Proceedings
Publications: conference_itemau

Publications: article

Publications: conference_item
2017 IEEE International Conference on Computer Vision (ICCV)
Publications: monograph

Publications: article

Publications: conference_item
2nd International Conference on 3D Vision (3DV)
Publications: conference_item
15th IEEE International Conference on Computer Vision (ICCV)
Publications: conference_item
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Publications: conference_item
2011 IEEE Conference on Computer Vision and Pattern Recognition
Publications: conference_itemau

Publications: article

Publications: conference_item
32nd Conference on Neural Information Processing Systems (NIPS 2018) - Medical Imaging Meets NIPS Workshop (MED-NEURIPS 2018)
Publications: article

Publications: conference_item
Pattern Recognition and Image Analysis : 5th Iberian Conference, IbPRIA 2011, Las Palmas de Gran Canaria, Spain, June 8-10, 2011 : Proceedings
Cours et encadrements

Cours

GPA759 Réseaux de neurones et intelligence artificielle (Automne 2019)
SYS866 Sujets spéciaux II : génie de la production automatisée (Hiver 2019)

Encadrements

Thèse de doctorat (recherche appliquée)

    En codirection avec : Ben Ayed, Ismail
    Training visual recognition models in a low data regime, par Mounsaveng,Saypraseuth.
    Hiver 2020

Publications
Article publié dans une revue, révisé par les pairs (9)

Sherif Abuelwafa, Marco Pedersoli, Mohamed Cheriet. 2019. « Unsupervised exemplar-based learning for improved document image classification ». IEEE Access. vol. 7 p. 133738-133748.

Amir Ghodrati, Ali Diba, Marco Pedersoli, Tinne Tuytelaars, Luc Van Gool. 2017. « DeepProposals: Hunting objects and actions by cascading deep convolutional layers ». International Journal of Computer Vision. vol. 124 , nº 2. 17 p. p. 115-131.

Josep M. Gonfaus, Marco Pedersoli, Jordi Gonzàlez, Andrea Vedaldi, F. Xavier Roca. 2015. « Factorized appearances for object detection ». Computer Vision and Image Understanding. vol. 138 p. 92-101.

Ivan Huerta, Marco Pedersoli, Jordi Gonzàlez, Albert Sanfeliu. 2015. « Combining where and what in change detection for unsupervised foreground learning in surveillance ». Pattern Recognition. vol. 48 , nº 3. p. 709-719.

Marco Pedersoli, Radu Timofte, Tinne Tuytelaars, Luc Van Gool. 2015. « An elastic deformation field model for object detection and tracking ». International Journal of Computer Vision. vol. 111 , nº 2. p. 137-152.

Marco Pedersoli, Andrea Vedaldi, Jordi Gonzàlez, Xavier Roca. 2015. « A coarse-to-fine approach for fast deformable object detection ». Pattern Recognition. vol. 48 , nº 5. p. 1844-1853.

Marco Pedersoli, Jordi Gonzalez, Xu Hu, Xavier Roca. 2014. « Toward real-time pedestrian detection based on a deformable template model ». IEEE Transactions on Intelligent Transportation Systems. vol. 15 , nº 1. p. 355-364.

Marco Pedersoli, Jordi Gonzlez, Andrew D. Bagdanov, Xavier Roca. 2011. « Efficient discriminative multiresolution cascade for real-time human detection applications ». Pattern Recognition Letters. vol. 32 , nº 13. p. 1581-1587.

D. Rowe, J. Gonzalez, M. Pedersoli, J. J. Villanueva. 2010. « On tracking inside groups ». Machine Vision and Applications. vol. 21 , nº 2. p. 113-127.

Compte rendu de conférence (21)

Masih Aminbeidokhti, Marco Pedersoli, Patrick Cardinal, Eric Granger. 2019. « Emotion recognition with spatial attention and temporal softmax pooling ». Image Analysis and Recognition : 16th International Conference, ICIAR : Proceedings (Waterloo, ON, Canada, Aug. 27-29, 2019) p. 323-331. Cham, Switzerland : Springer International Publishing.

Aarush Gupta, Dakshit Agrawal, Hardik Chauhan, Jose Dolz, Marco Pedersoli. 2018. « An attention model for group-level emotion recognition ». 20th ACM International Conference on Multimodal Interaction (ICIM '18) (Boulder, CO, USA, Oct. 16-20, 2018) p. 611-615. ACM.

Jizong Peng, Christian Desrosiers, Marco Pedersoli. 2018. « DC-SegNet: a discretely constrained deep network for weakly supervised segmentation ». 32nd Conference on Neural Information Processing Systems (NIPS 2018) - Medical Imaging Meets NIPS Workshop (MED-NEURIPS 2018) (Montreal, QC, Canada, Dec. 08, 2018)

Marco Pedersoli, Thomas Lucas, Cordelia Schmid, Jakob Verbeek. 2017. « Areas of attention for image captioning ». 2017 IEEE International Conference on Computer Vision (ICCV) (Venice, Italy, Oct. 22-29, 2017) p. 1251-1259. IEEE.

Xu Jia, Amir Ghodrati, Marco Pedersoli, Tinne Tuytelaars. 2016. « Towards automatic image editing: learning to see another you ». Proceedings of the British Machine Vision Conference (York County, United kingdom, Sept. 19-22, 2016) BMVA Press.

Hakan Bilen, Marco Pedersoli, Tinne Tuytelaars. 2015. « Weakly supervised object detection with convex clustering ». IEEE Conference on Computer Vision and Pattern Recognition, (CVPR) (Boston, MA, USA, June 07-12, 2015) p. 1081-1089. IEEE Computer Society.

Amir Ghodrati, Ali Diba, Marco Pedersoli, Tinne Tuytelaars, Luc Van Gool. 2015. « Deepproposal: Hunting objects by cascading deep convolutional layers ». 15th IEEE International Conference on Computer Vision ( ICCV) (Santiago, Chile, Dec. 11-18, 2015) p. 2578-2586. IEEE.

Amir Ghodrati, Xu Jia, Marco Pedersoli, Tinne Tuytelaars. 2015. « Swap retrieval: Retrieving images of cats when the query shows a dog ». 5th ACM International Conference on Multimedia Retrieval (ICMR) (Shanghai, China, June 23-26, 2015) p. 395-402. Association for Computing Machinery.

Marco Pedersoli, Tinne Tuytelaars. 2015. « Learning where to position parts in 3D ». 15th IEEE International Conference on Computer Vision (ICCV) (Santiago, Chile, Dec. 11-15, 2015) p. 136-144. IEEE.

Hakan Bilen, Marco Pedersoli, Vinay P. Namboodiri, Tinne Tuytelaars, Luc Van Gool. 2014. « Object classification with adaptable regions ». 27th IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (Columbus, OH, USA, June 23-28, 2014) p. 3662-3669. IEEE Computer Society.

Hakan Bilen, Marco Pedersoli, Tinne Tuytelaars. 2014. « Weakly supervised object detection with posterior regularization ». Proceedings British Machine Vision Conference (Nottingham, United Kingdom, Sept. 01-05, 2014) BMVA Press.

Amir Ghodrati, Marco Pedersoli, Tinne Tuytelaars. 2014. « Coupling video segmentation and action recognition ». 2014 IEEE Winter Conference on Applications of Computer Vision (WACV) (Steamboat Springs, CO, USA, Mar. 24-26, 2014) p. 618-625. IEEE Computer Society.

Amir Ghodrati, Marco Pedersoli, Tinne Tuytelaars. 2014. « Is 2D information enough for viewpoint estimation? ». Proceedings British Machine Vision Conference (Nottingham, United kingdom, Sept. 01-05, 2014) BMVA Press.

Markus Mathias, Marco Pedersoli, Luc Van Gool, Rodrigo Benenson, Luc Van Gool. 2014. « Face detection without bells and whistles ». Computer Vision - ECCV 2014 : 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part IV (Zurich, Switzerland, Sept. 6-12, 2014) p. 720-735. Springer International Publishing.

Marco Pedersoli, Tinne Tuytelaars. 2014. « A scalable 3D HOG model for fast object detection and viewpoint estimation ». 2nd International Conference on 3D Vision (3DV) (Tokyo, Japan, Dec. 08-11, 2014) p. 163-170. IEEE.

Marco Pedersoli, Tinne Tuytelaars, Luc Van Gool. 2014. « Using a deformation field model for localizing faces and facial points under weak supervision ». IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (Columbus, OH, United states, June 23-28, 2014) p. 3694-3701. IEEE Computer Society.

Marco Pedersoli, Andrea Vedaldi, Jordi Gonzàlez. 2011. « A coarse-to-fine approach for fast deformable object detection ». 2011 IEEE Conference on Computer Vision and Pattern Recognition (Colorado Springs, CO, USA, June 20-25, 2011) p. 1353-1360. IEEE Computer Society.

Nataliya Shapovalova, Wenjuan Gong, Marco Pedersoli, Francesc Xavier Roca, Jordi Gonzàlez. 2011. « On importance of interactions and context in human action recognition ». Pattern Recognition and Image Analysis : 5th Iberian Conference, IbPRIA 2011, Las Palmas de Gran Canaria, Spain, June 8-10, 2011 : Proceedings (Las Palmas de Gran Canaria, Spain, June 08-10, 2011) p. 58-66. Springer Verlag.

Marco Pedersoli, Jordi Gonzàlez, Andrew D. Bagdanov, Juan J. Villanueva. 2010. « Recursive coarse-to-fine localization for fast object detection ». Computer Vision - ECCV 2010 : 11th European Conference on Computer Vision, Heraklion, Crete, Greece, September 5-11, 2010, Proceedings, Part VI (Heraklion, Crete, Greece, Sept. 05-11, 2010) p. 280-293. Springer Verlag.

Marco Pedersoli, Jordi Gonzalez, Juan Jose Villanueva. 2009. « High-speed human detection using a multiresolution cascade of histograms of oriented gradients ». Pattern Recognition and Image Analysis : 4th Iberian Conference, IbPRIA 2009 Póvoa de Varzim, Portugal, June 10-12, 2009 Proceedings (Povoa de Varzim, Portugal, June 10-12, 2009) p. 48-55. Springer Verlag.

Bhaskar Chakraborty, Marco Pedersoli, Jordi Gonzalez. 2008. « View-invariant human action detection using component-wise HMM of body parts ». 5th International Conference on Articulated Motion and Deformable Objects (AMDO) 2008, July 9, 2008 - July 11, 2008 (Port d'Andratx, Mallorca, Spain, July 09-11, 2008) p. 208-217. Springer Verlag.

Communication (5)

Amir Ghodrati, Marco Pedersoli, Tinne Tuytelaars. 2014. « Is 2D information enough for viewpoint estimation? ». Communication lors de la conférence : 25th British Machine Vision Conference (BMVC) ( Nottingham, United kingdom, Sept. 01-05, 2014 )

Markus Mathias, Marco Pedersoli, Luc Van Gool, Rodrigo Benenson, Luc Van Gool. 2014. « Face detection without bells and whistles ». Communication lors de la conférence : 13th European Conference on Cuomputer Vision (ECCV) ( Zurich, Switzerland, Sept. 6-12, 2014 )

Marco Pedersoli, Andrea Vedaldi, Jordi Gonzàlez. 2011. « A coarse-to-fine approach for fast deformable object detection ». Communication lors de la conférence : 2011 IEEE Conference on Computer Vision and Pattern Recognition ( Colorado Springs, CO, USA, June 20-25, 2011 )

Josep M. Gonfaus, Xavier Boix, Fahad S. Khan, Joost van de Weijer, Andrew D. Bagdanov, Marco Pedersoli, Joan Serrat, Xavier Roca, Jordi Gonzàlez. 2010. « Harmony potentials : Fusing global and local scale for semantic image segmentation ». Communication lors de la conférence : The PASCAL Visual Object Classes Challenge Workshop 2010 ( Crete, Greece, Sept. 11, 2010 )

Marco Pedersoli, Jordi Gonzalez, Juan Jose Villanueva. 2009. « High-speed human detection using a multiresolution cascade of histograms of oriented gradients ». Communication lors de la conférence : 4th Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA) ( Povoa de Varzim, Portugal, June 10-12, 2009 )

Rapport technique (1)

Marco Pedersoli, Radu Timofte, Tinne Tuytelaars, Luc Van Gool. 2014. « An Elastic Deformation Field Model for Object Detection and Tracking ». «KU Leuven technical report» KU leuven. 19 p.

Chapitre de livre (2)

Marc Castelló, Jordi Gonzàlez, Ariel Amato, Pau Baiget, Carles Fernández, Josep M. Gonfaus, Ramón A. Mollineda, Marco Pedersoli, Nicolás Pérez de la Blanca, F. Xavier Roca. 2013. « Exploiting multimodal interaction techniques for video-surveillance ». In Multimodal interaction in image and video applications Coll. «Intelligent systems reference library», . p. 135-151. Springer Berlin Heidelberg.

Marco Pedersoli, Jordi Gonzàlez, Bhaskar Chakraborty, Juan J. Villanueva. 2007. « Enhancing real-time human detection based on histograms of oriented gradients ». In Computer Recognition Systems 2 Coll. «Advances in Soft Computing», . p. 739-746. Springer.

Mémoire ou thèse (1)

Marco Pedersoli. 2012. « Hierarchical multiresolution models for fast object detection ». Thèse de doctorat. Barcelona , Universitat Autònoma de Barcelona

Prix et distinctions