My Publications

You can also browse my Google Scholar profile.

Top-Tier Journal Publications

A. Kuznetsova, H. Rom, N. Alldrin, J. Uijlings, I. Krasin, J. Pont-Tuset, S. Kamali, S. Popov, M. Malloci, A. Kolesnikov, T. Duerig, and V. Ferrari
The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale
International Journal on Computer Vision (IJCV), vol. 128, no. 7, pp. 1956-1981, 2020.
[BibTeX] [PDF] [Project Page]

@article{Kuznetsova2020,
  author = {Alina Kuznetsova and Hassan Rom and Neil Alldrin and Jasper Uijlings and Ivan Krasin and Jordi Pont-Tuset and Shahab Kamali and Stefan Popov and Matteo Malloci and Alexander Kolesnikov and Tom Duerig and Vittorio Ferrari},
  title = {The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale},
  year = {2020},
  number = {7},
  volume = {128},
  pages={1956-1981},
  journal = {IJCV}
}

K.K. Maninis, S. Caelles, Y. Chen, J. Pont-Tuset, L. Leal-Taixé, D. Cremers, and L. Van Gool
Video Object Segmentation Without Temporal Information
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 41, no. 6, pp. 1515 - 1530, 2019.
[BibTeX] [PDF] [Project Page]

@Article{Maninis2018c,
  author = {K.K. Maninis and S. Caelles and Y. Chen and J. Pont-Tuset and L. Leal-Taix\'e and D. Cremers and L. {Van Gool},
  title = {Video Object Segmentation Without Temporal Information},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
  year = {2019},
  volume = {41},
  number = {6},
  pages = {1515 - 1530}
}

K.K. Maninis, J. Pont-Tuset, P. Arbeláez and L. Van Gool
Convolutional Oriented Boundaries: From Image Segmentation to High-Level Tasks
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 40, no. 4, pp. 819 - 833, 2018.
[BibTeX] [PDF] [Project Page]

@article{Maninis2018,
  author = {Maninis, Kevis-Kokitsi and Pont-Tuset, Jordi and Arbeláez, Pablo and {Van Gool}, Luc},
  title = {Convolutional Oriented Boundaries: From Image Segmentation to High-Level Tasks},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
  year = {2018},
  volume = {40},
  number = {4},
  pages = {819 - 833}
}

J. Pont-Tuset, P. Arbeláez, J. Barron, F. Marques, and J. Malik
Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 39, no. 1, pp. 128 - 140, 2017.
[BibTeX] [PDF] [Project Page]

@article{Pont-Tuset2017,
  author = {J. Pont-Tuset and P. Arbel\'{a}ez and J. Barron and F.Marques and J. Malik},
  title = {Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
  year = {2017},
  volume = {39},
  number = {1},
  pages = {128 - 140}
}

J. Pont-Tuset and F. Marques
Supervised Evaluation of Image Segmentation and Object Proposal Techniques
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 38, no. 7, pp. 1465-1478, 2016.
[BibTeX] [PDF] [Project Page]

@article{Pont-Tuset2016a,
  author = {Jordi Pont-Tuset and Ferran Marques},
  title = {Supervised Evaluation of Image Segmentation and Object Proposal Techniques},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
  year = {2016},
  volume = {38},
  number = {7},
  pages = {1465--1478}
}

Patents

M. Farré Guiu, M. Junyent, J. Pont-Tuset, P. Beltran, N. Narayan, L. Sigal, A. Smolic, and A. M. Accardo
Metadata extraction and management
US 2017/0109419 A1, 2017.
[BibTeX] [PDF]

@patent{Farre2017,
  author = {M. Farr\'{e} and M. Junyent and J. Pont-Tuset and P. Beltran and N. Narayan and L. Sigal and A. Smolic and A. M. Accardo},
  title = {Metadata extraction and management},
  year = {2017},
  number = {US 2017/0109419 A1}
}

A. Smolic, M. Junyent, J. Pont-Tuset, A. Chapiro and M. Farré Guiu
Systems and Methods for Automatic Key Frame Extraction and Storyboard Interface Generation for Video
US 2017/0011264 A1, 2017.
[BibTeX] [PDF]

@patent{Smolic2017,
  author = {A. Smolic and M. Junyent and J. Pont-Tuset and A. Chapiro and M. Farr\'{e}},
  title = {Systems and methods for automatic key frame extraction and storyboard interface generation for video},
  year = {2017},
  number = {US 2017/0011264 A1}
}

A. Smolic, J. Pont-Tuset, and M. Farré Guiu
Video Object Tagging Using Segmentation Hierarchy
US 2016/0313894 A1, 2016.
[BibTeX][PDF]

@patent{Smolic2016,
  author = {Aljoscha Smolic and Jordi Pont-Tuset and Farre Guiu, Angel},
  title = {Video Object Tagging Using Segmentation Hierarchy},
  year = {2016},
  number = {US 2016/0313894 A1}
}

Top-Tier Vision Conference Publications

J. Pont-Tuset, J. Uijlings, S. Changpinyo, R. Soricut, and V. Ferrari
Connecting Vision and Language with Localized Narratives
European Conference on Computer Vision (ECCV), 2020.
[BibTeX] [PDF] [Project Page]

@inproceedings{PontTuset_eccv2020,
  author  = {Jordi Pont-Tuset and Jasper Uijlings and Soravit Changpinyo and Radu Soricut and Vittorio Ferrari},
  title   = {Connecting Vision and Language with Localized Narratives},
  booktitle = {ECCV},
  year    = {2020}
}

K.K. Maninis, S. Caelles, J. Pont-Tuset, and L. Van Gool
Deep Extreme Cut: From Extreme Points to Object Segmentation
Computer Vision and Pattern Recognition (CVPR), 2018.
[BibTeX] [PDF] [Project Page]

@inproceedings{Maninis2018b,
  author = {K.-K. Maninis and S. Caelles and J. Pont-Tuset and L. {Van Gool}},
  title = {Deep Extreme Cut: From Extreme Points to Object Segmentation},
  booktitle = {Computer Vision and Pattern Recognition (CVPR)},
  year = {2018}
}

Y. Chen, J. Pont-Tuset, A. Montes, and L. Van Gool
Blazingly Fast Video Object Segmentation with Pixel-Wise Metric Learning
Computer Vision and Pattern Recognition (CVPR), 2018.
[BibTeX] [PDF] [Project Page]

@inproceedings{Chen2018,
  author = {Y. Chen and J. Pont-Tuset and A. Montes and L. {Van Gool}},
  title = {Blazingly Fast Video Object Segmentation with Pixel-Wise Metric Learning},
  booktitle = {Computer Vision and Pattern Recognition (CVPR)},
  year = {2018}
}

C. Ventura, J. Pont-Tuset, S. Caelles, K.K. Maninis, and L. Van Gool
Iterative Deep Learning for Road Topology Extraction
British Machine Vision Conference (BMVC), 2018.
[BibTeX] [PDF] [Project Page]

@inproceedings{Ventura2018,
  author = {C. Ventura and J. Pont-Tuset and S. Caelles and K.-K. Maninis and L. {Van Gool}},
  title = {Iterative Deep Learning for Road Topology Extraction},
  booktitle = {British Machine Vision Conference (BMVC)},
  year = {2018}
}

S. Caelles, K.K. Maninis, J. Pont-Tuset, L. Leal-Taixé, D. Cremers, and L. Van Gool
One-Shot Video Object Segmentation
Computer Vision and Pattern Recognition (CVPR), 2017.
[BibTeX] [PDF] [Project Page]

@inproceedings{Caelles2017,
  author = {S. Caelles and K.-K. Maninis and J. Pont-Tuset and L. Leal-Taix\'e and D. Cremers and L. {Van Gool}},
  title = {One-Shot Video Object Segmentation},
  booktitle = {Computer Vision and Pattern Recognition (CVPR)},
  year = {2017}
}

K.K. Maninis, J. Pont-Tuset, P. Arbeláez and L. Van Gool
Convolutional Oriented Boundaries
European Conference on Computer Vision (ECCV), 2016
[BibTeX] [PDF] [Project Page]

@inproceedings{Maninis2016a,
  author = {K.K. Maninis and J. Pont-Tuset and P. Arbel\'{a}ez and L. {Van Gool}},
  title = {Convolutional Oriented Boundaries},
  booktitle = {European Conference on Computer Vision (ECCV)},
  year = {2016}
}

K.K. Maninis, J. Pont-Tuset, P. Arbeláez and L. Van Gool
Deep Retinal Image Understanding
Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2016
[BibTeX] [PDF] [Project Page]

@inproceedings{Maninis2016,
  author = {K.K. Maninis and J. Pont-Tuset and P. Arbel\'{a}ez and L. Van Gool},
  title = {Deep Retinal Image Understanding},
  booktitle = {Medical Image Computing and Computer-Assisted Intervention (MICCAI)},
  year = {2016}
}

F. Perazzi, J. Pont-Tuset, B. McWilliams, L. Van Gool, M. Gross and A. Sorkine-Hornung
A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation
Computer Vision and Pattern Recognition (CVPR), 2016
[BibTeX] [PDF] [Project Page]

@inproceedings{Perazzi2016,
  author = {F. Perazzi and J. Pont-Tuset and B. McWilliams and L. Van Gool and M. Gross and A. Sorkine-Hornung},
  title = {A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation},
  booktitle = {Computer Vision and Pattern Recognition (CVPR)},
  year = {2016}
}

Y. Chen, D. Dai, J. Pont-Tuset and L. Van Gool
Scale-Aware Alignment of Hierarchical Image Segmentation
Computer Vision and Pattern Recognition (CVPR), 2016
[BibTeX] [PDF] [Project Page]

@inproceedings{Chen2016,
  author = {Y. Chen and D. Dai and J. Pont-Tuset and L. Van Gool},
  title = {Scale-Aware Alignment of Hierarchical Image Segmentation},
  booktitle = {Computer Vision and Pattern Recognition (CVPR)},
  year = {2016}
}

J. Pont-Tuset and L. Van Gool
Boosting Object Proposals: From Pascal to COCO
International Conference on Computer Vision (ICCV), 2015
[BibTeX] [PDF] [Project Page]

@inproceedings{Pont-Tuset2015b,
  author = {Jordi Pont-Tuset and Luc Van Gool},
  title = {Boosting Object Proposals: From Pascal to COCO},
  booktitle = {International Conference on Computer Vision (ICCV)},
  year = {2015}
}

P. Arbeláez, J. Pont-Tuset, J. Barron, F. Marques, and J. Malik
Multiscale Combinatorial Grouping
Computer Vision and Pattern Recognition (CVPR), 2014
[BibTeX] [PDF] [Project Page]

@inproceedings{ Arbelaez2014,
    author    = {Arbel\'{a}ez, Pablo and Pont-Tuset, J. and Barron, Jon and Marques, F. and Malik, Jitendra},
    title     = {Multiscale Combinatorial Grouping},
    booktitle = {Computer Vision and Pattern Recognition (CVPR)},
    year      = {2014}
}

J. Pont-Tuset and F. Marques
Measures and Meta-Measures for the Supervised Evaluation of Image Segmentation
Computer Vision and Pattern Recognition (CVPR), 2013
[BibTeX] [PDF] [Project Page]

@inproceedings{ Pont-Tuset2013,
    author    = {Pont-Tuset, J. and Marques, F.},
    title     = {Measures and Meta-Measures for the Supervised Evaluation of Image Segmentation},
    booktitle = {Computer Vision and Pattern Recognition (CVPR)},
    year      = {2013}
}

J. Pont-Tuset and F. Marques
Supervised Assessment of Segmentation Hierarchies
European Conference on Computer Vision (ECCV), 2012
[BibTeX] [PDF] [Project Page]

@inproceedings{ Pont-Tuset2012c,
    author    = {Pont-Tuset, J. and Marques, F.},
    title     = {Supervised Assessment of Segmentation Hierarchies},
    booktitle = {European Conference on Computer Vision (ECCV)},
    year      = {2012}
}

Written Theses

PhD thesis
Image Segmentation Evaluation and Its Application to Object Detection
Universitat Politècnica de Catalunya, UPC BarcelonaTech, 2014
[BibTeX] [PDF]

@phdthesis{Pont-Tuset2014,
    author = {Jordi Pont-Tuset},
    title = {Image Segmentation Evaluation and Its Application to Object Detection},
    school = {Universitat {P}olit\`{e}cnica de {C}atalunya, {UPC} {B}arcelona{T}ech},
    year = {2014}
}

M.Sc. thesis
Automatic extraction of the camera point of view in Football scenes
Universitat Politècnica de Catalunya, UPC BarcelonaTech, 2009
[BibTeX] [PDF]

@MastersThesis{Pont-Tuset2009,
    author = {Jordi Pont-Tuset},
    title = {Automatic extraction of the camera point of view in Football scenes},
    school = {Universitat {P}olit\`{e}cnica de {C}atalunya, {UPC} {B}arcelona{T}ech},
    year = {2009}
}

Other Vision Publications

J. Pont-Tuset, M. Farré Guiu, and A. Smolic
Semi-Automatic Video Object Segmentation by Advanced Manipulation of Segmentation Hierarchies
International Workshop on Content-Based Multimedia Indexing (CBMI), 2015
[BibTeX] [PDF] [Dataset]

@inproceedings{Pont-Tuset2015a,
  author = {Pont-Tuset, J. and Farré, M. and Smolic, A.},
  title = {Semi-Automatic Video Object Segmentation by Advanced Manipulation of Segmentation Hierarchies},
  booktitle = {International Workshop on Content-Based Multimedia Indexing (CBMI)},
  year = {2015}
}

M. Junyent, P. Beltran, M. Farré Guiu, and J. Pont-Tuset, A. Chapiro and A. Smolic
Video content and structure description based on keyframes, clusters and storyboards
Multimedia Signal Processing (MMSP), 2015
[BibTeX] [PDF]

@inproceedings{Junyent2015,
  author = {Junyent, M. and Beltran, P. and Farré, M.A. and Pont-Tuset, J. and Chapiro, A. and Smolic, A.},
  title = {Video content and structure description based on keyframes, clusters and storyboards},
  booktitle = {Multimedia Signal Processing (MMSP)},
  year = {2015}
}

X. Giró-i-Nieto, M. Martos, E. Mohedano, and J. Pont-Tuset
From Global Image Annotation to Interactive Object Segmentation
Multimedia Tools and Applications, 2014.
[BibTeX] [PDF]

@article{ Giro-i-Nieto2014,
      author  = {Gir\'{o}-i-Nieto, X. and Martos, Manel and Mohedano, Eva and Pont-Tuset, J.},
      title   = {From Global Image Annotation to Interactive Object Segmentation},
      journal = {Multimedia Tools and Applications},
      year    = {2014},
      doi     = {http://dx.doi.org/10.1007/s11042-013-1374-3}
}

J. Pont-Tuset and F. Marques
Upper-bound assessment of the spatial accuracy of hierarchical region-based image representations
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2012
[BibTeX] [PDF]

@inproceedings{ Pont-Tuset2012b,
    author    = {Pont-Tuset, J. and Marques, F.},
    title     = {Upper-bound assessment of the spatial accuracy of hierarchical region-based image representations},
    booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    year      = {2012}
}

J. Pont-Tuset and F. Marques
Contour detection using Binary Partition Trees
International Conference on Image Processing (ICIP), 2010
[BibTeX] [PDF]

@inproceedings{ Pont-Tuset2010,
    author    = {Pont-Tuset, J. and Marques, F.},
    title     = {Contour detection using Binary Partition Trees},
    booktitle = {International Conference on Image Processing (ICIP)},
    year      = {2010},
    doi       = {http://dx.doi.org/10.1109/ICIP.2010.5652339}
}

X. Giró-i-Nieto, C. Ventura, J. Pont-Tuset, S. Cortes, and F. Marques
System architecture of a web service for Content-Based Image Retrieval
International Conference on Image and Video Retrieval (CIVR), 2010
[BibTeX] [PDF]

@inproceedings{ Giro-i-Nieto2010a,
    author    = {Giro-i-Nieto, Xavier and Ventura, Carles and Pont-Tuset, Jordi and Cortes, Silvia and Marques, Ferran},
    title     = {System architecture of a web service for Content-Based Image Retrieval},
    booktitle = {International Conference on Image and Video Retrieval (CIVR)},
    year      = {2010},
    doi       = {http://doi.acm.org/10.1145/1816041.1816093}
}