Pablo Mesejo Santiago
7
Documents
Présentation
My name is Pablo Mesejo Santiago and I currently hold a Marie Curie Experienced Researcher position at the University of Granada (Spain), one of the [top institutions in computer science and engineering](http://www.shanghairanking.com/Shanghairanking-Subject-Rankings/computer-science-engineering.html).
My principal research areas of interest are computer vision, machine learning and computational intelligence methods applied to image analysis problems (mainly in the biomedical domain). Typical tools I use in my research are stochastic optimization algorithms, deep and shallow neural networks, and ensemble classifiers. During my career I have tackled numerous challenging problems, e.g. the automatic segmentation of anatomical structures in biomedical images (PhD at University of Parma, performed as a Marie Curie Early Stage Researcher, 2010-13), the classification of gastrointestinal lesions from endoscopic videos (postdoc at University of Auvergne Clermont-Ferrand I, 2013-14), the estimation of biophysical parameters from fMRI signals (postdoc at Inria, 2014-16), and the integration of deep learning into probabilistic generative models for visual and audio recognition in human-robot interaction (starting researcher position at Inria, 2016-18).
More information about me and my publications can be found in the following links: [Google Scholar](https://scholar.google.com/citations?user=dUlIWxcAAAAJ), [ORCID](http://orcid.org/0000-0001-9955-2101), [Linkedin](https://fr.linkedin.com/pub/pablo-mesejo-santiago/54/348/71b/en), [DBLP](http://dblp.uni-trier.de/pers/hd/m/Mesejo:Pablo), [ResearchGate](https://www.researchgate.net/profile/Pablo_Mesejo) and [ResearcherID](http://www.researcherid.com/ProfileView.action?SID=V24kpAPPEKmBvYjOeqa&returnCode=ROUTER.Success&queryString=KG0UuZjN5WkwsNoH4O%252BEmmn%252FPULU3%252FDZxELZtBub7fk%253D&SrcApp=CR&Init=Yes).
My name is Pablo Mesejo Santiago and I currently hold a Marie Curie Experienced Researcher position at the University of Granada (Spain), one of the [top institutions in computer science and engineering](http://www.shanghairanking.com/Shanghairanking-Subject-Rankings/computer-science-engineering.html).
My principal research areas of interest are computer vision, machine learning and computational intelligence methods applied to image analysis problems (mainly in the biomedical domain). Typical tools I use in my research are stochastic optimization algorithms, deep and shallow neural networks, and ensemble classifiers. During my career I have tackled numerous challenging problems, e.g. the automatic segmentation of anatomical structures in biomedical images (PhD at University of Parma, performed as a Marie Curie Early Stage Researcher, 2010-13), the classification of gastrointestinal lesions from endoscopic videos (postdoc at University of Auvergne Clermont-Ferrand I, 2013-14), the estimation of biophysical parameters from fMRI signals (postdoc at Inria, 2014-16), and the integration of deep learning into probabilistic generative models for visual and audio recognition in human-robot interaction (starting researcher position at Inria, 2016-18).
More information about me and my publications can be found in the following links: [Google Scholar](https://scholar.google.com/citations?user=dUlIWxcAAAAJ), [ORCID](http://orcid.org/0000-0001-9955-2101), [Linkedin](https://fr.linkedin.com/pub/pablo-mesejo-santiago/54/348/71b/en), [DBLP](http://dblp.uni-trier.de/pers/hd/m/Mesejo:Pablo), [ResearchGate](https://www.researchgate.net/profile/Pablo_Mesejo) and [ResearcherID](http://www.researcherid.com/ProfileView.action?SID=V24kpAPPEKmBvYjOeqa&returnCode=ROUTER.Success&queryString=KG0UuZjN5WkwsNoH4O%252BEmmn%252FPULU3%252FDZxELZtBub7fk%253D&SrcApp=CR&Init=Yes).
Publications
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 7
- 7
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 2
- 2
- 1
|
A Comprehensive Analysis of Deep RegressionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42 (9), pp.2065-2081. ⟨10.1109/TPAMI.2019.2910523⟩
Article dans une revue
hal-01754839v1
|
|
Neural Network Based Reinforcement Learning for Audio-Visual Gaze Control in Human-Robot InteractionPattern Recognition Letters, 2019, 118, pp.61-71. ⟨10.1016/j.patrec.2018.05.023⟩
Article dans une revue
hal-01643775v2
|
|
Learning Visual Voice Activity Detection with an Automatically Annotated DatasetICPR 2020 - 25th International Conference on Pattern Recognition, Jan 2021, Milano, Italy. pp.4851-4856, ⟨10.1109/ICPR48806.2021.9412884⟩
Communication dans un congrès
hal-02882229v4
|
|
Extended Gaze Following: Detecting Objects in Videos Beyond the Camera Field of ViewFG 2019 - 14th IEEE International Conference on Automatic Face and Gesture Recognition, May 2019, Lille, France. pp.1-8, ⟨10.1109/FG.2019.8756555⟩
Communication dans un congrès
hal-02054236v1
|
|
DeepGUM: Learning Deep Robust Regression with a Gaussian-Uniform Mixture ModelECCV 2018 - European Conference on Computer Vision, Sep 2018, Munich, Germany. pp.205-221, ⟨10.1007/978-3-030-01228-1_13⟩
Communication dans un congrès
hal-01851511v1
|
|
Deep Reinforcement Learning for Audio-Visual Gaze ControlIROS 2018 - IEEE/RSJ International Conference on Intelligent Robots and Systems, Oct 2018, Madrid, Spain. pp.1555-1562, ⟨10.1109/IROS.2018.8594327⟩
Communication dans un congrès
hal-01851738v1
|
|
Deep Mixture of Linear Inverse Regressions Applied to Head-Pose EstimationIEEE Conference on Computer Vision and Pattern Recognition, Jul 2017, Honolulu, Hawaii, United States. pp.7149-7157, ⟨10.1109/CVPR.2017.756⟩
Communication dans un congrès
hal-01504847v1
|