Compression, Deep learning, Machine learning

[:fr]Nouveau groupe de travail sur apprentissage par ordinateur et compression[:en]Working group on machine learning for compression [:it]Gruppo di studio su machine learning e compressione[:]

[:fr]Nous avons lancé un nouveau groupe de travail sur l’utilisation des techniques d’intelligence artificielle (apprentissage par ordinateur, apprentissage profond) dans le domaine de la compression d’images et vidéo.

Ici le site: https://mlcompr.wp.imt.fr/[:en]We started a working group about using machine learning and deep learning techniques for compression problem, check it out here!

 

 [:it]Abbiamo cominciato le riunioni di un nuovo gruppo di studio e ricerca sulle applicazioni di machine learning e deep learning in compression, qui il sito del gruppo.

 

 [:]

Publication

[:fr]Article accepté ICASSP[:en]ICASSP article accepted[:it]Articolo accettato a ICASSP[:]

[:fr]L’article sur l’allocation de puissance pour la transmission linéaire de la vidéo à été accepté dans le programme de la conférence IEEE ICASSP 2018. Félicitations au premier auteur, notre doctorant Shuo Zheng![:en]The paper on power allocation for LVC systems has been accepted into ICASSP’18. Congratulations to the first author Shuo Zheng![:it]L’articolo sull’allocazione di potenza per sistemi LVC è stato accettato. Complimenti a Shuo![:]

Séminaire

[:fr]Seminar: Virtual Reality: from Neuroscience to Media Streaming[:en]Invited talk: « Virtual Reality: from Neuroscience to Media Streaming »[:]

[:fr]Nous avons le plaisir d’accueillir Joan Llobera (i2CAT, Barcelona) pour un séminaire sur la réalité virtuelle.

Date : Vendredi 2 février
Heure : 13h30
Salle : C48
Titre : Virtual Reality: from Neuroscience to Media Streaming
Abstract:
Immersive Virtual Reality is transitioning, at a remarkable pace, from a tool for fundamental research in cognitive neuroscience, therapy and rehabilitation to a consumer product for training, education and entertainment.
In this talk I will review some highlights of this remarkable transition. The talk will have three parts.
1) Review some of the known principles and well estabhised mechanisms of Virtual Reality science, as they can be found in the relevant litterature,
2) Introduce some of the ongoing initiatives in terms of capture technologies, encoding mechanisms, and delivery infrastructure fostered by the transformation of VR into a consumer product
3) Discuss, hopefully in interaction with the audience, where we are heading, what might happen in the near future, and what we can do to address the challenges and oportunities associated with this medium.

Speaker:
Dr. Joan Llobera (male) is an electrical engineer and an academic researcher working at the conjunction of cognitive sciences and virtual reality. He obtained a double diploma in Electrical Engineering (Universitat Politècnica de Catalunya and Télécom Paris), holds 2 Masters, one in cognitive sciences (EHESS) and another in software (UPC), and in 2012 obtained a PhD at the Universitat de Barcelona on the topic of Stories in Virtual Reality, which received a Cum Laude qualification. He also worked as a postdoc researcher at the Ecole Polytechnique Fédérale de Lausanne. Since September 2015 he is a senior researcher at the i2CAT foundation.[:en]Our next seminar!

Date : Friday Feb 2nd 2018
Hour : 13h30
Room : C48
Title : Virtual Reality: from Neuroscience to Media Streaming
Abstract:
Immersive Virtual Reality is transitioning, at a remarkable pace, from a tool for fundamental research in cognitive neuroscience, therapy and rehabilitation to a consumer product for training, education and entertainment.
In this talk I will review some highlights of this remarkable transition. The talk will have three parts.
1) Review some of the known principles and well estabhised mechanisms of Virtual Reality science, as they can be found in the relevant litterature,
2) Introduce some of the ongoing initiatives in terms of capture technologies, encoding mechanisms, and delivery infrastructure fostered by the transformation of VR into a consumer product
3) Discuss, hopefully in interaction with the audience, where we are heading, what might happen in the near future, and what we can do to address the challenges and oportunities associated with this medium.

Speaker:
Dr. Joan Llobera (male) is an electrical engineer and an academic researcher working at the conjunction of cognitive sciences and virtual reality. He obtained a double diploma in Electrical Engineering (Universitat Politècnica de Catalunya and Télécom Paris), holds 2 Masters, one in cognitive sciences (EHESS) and another in software (UPC), and in 2012 obtained a PhD at the Universitat de Barcelona on the topic of Stories in Virtual Reality, which received a Cum Laude qualification. He also worked as a postdoc researcher at the Ecole Polytechnique Fédérale de Lausanne. Since September 2015 he is a senior researcher at the i2CAT foundation.[:it]Il prossimo seminario del gruppo Multimedia sarà centrato sulla realtà virtuale

Data : Venerdì  2 febbraio 2018
Orario : 13h30
Luogo : C48
Titolo : Virtual Reality: from Neuroscience to Media Streaming
Abstract:
Immersive Virtual Reality is transitioning, at a remarkable pace, from a tool for fundamental research in cognitive neuroscience, therapy and rehabilitation to a consumer product for training, education and entertainment.
In this talk I will review some highlights of this remarkable transition. The talk will have three parts.
1) Review some of the known principles and well estabhised mechanisms of Virtual Reality science, as they can be found in the relevant litterature,
2) Introduce some of the ongoing initiatives in terms of capture technologies, encoding mechanisms, and delivery infrastructure fostered by the transformation of VR into a consumer product
3) Discuss, hopefully in interaction with the audience, where we are heading, what might happen in the near future, and what we can do to address the challenges and oportunities associated with this medium.

Speaker:
Dr. Joan Llobera (male) is an electrical engineer and an academic researcher working at the conjunction of cognitive sciences and virtual reality. He obtained a double diploma in Electrical Engineering (Universitat Politècnica de Catalunya and Télécom Paris), holds 2 Masters, one in cognitive sciences (EHESS) and another in software (UPC), and in 2012 obtained a PhD at the Universitat de Barcelona on the topic of Stories in Virtual Reality, which received a Cum Laude qualification. He also worked as a postdoc researcher at the Ecole Polytechnique Fédérale de Lausanne. Since September 2015 he is a senior researcher at the i2CAT foundation.[:]

Séminaire

[:fr]Séminaires du groupe MM[:]

[:fr]Les prochaines séminaires du groupe MM se tiendront mardi 19 décembre 2017 en salle B567 autour de la thématique de la vidéo immersive.

Quatre orateurs invités nous introduiront leur projets de recherche dans 2 sessions : matin 10h-12h30 et après-midi 13h30-16h.[:]

Enseignement, PACT

[:fr]PACT : introduction à la détection de mouvement et aux descripteurs[:]

[:fr]Mouvement :

Descripteurs :

  • Tutoriel OpenCV-Python
  • Transparents
  • Images pour le TP
  • Scripts Python
  • Problèmes d’installation opencv :
    1) Assurez-vous d’avoir les versions 64 bits de python et numpy.
    2) Téléchargez ici la version 2.14 d’opencv : https://sourceforge.net/projects/opencvlibrary/files/opencv-win/2.4.13/opencv-2.4.13.4-vc14.exe/download
    3) Installez opencv , allez dans : \opencv\build\python\2.7\x64 et copiez le fichier cv2.pyd (attention, ça doit bien être dans un répertoire nommé ‘x64’)
    5) (!) Copiez-le dans votre environnement Python : typiquement C:/Python27/lib/site-packeges ou si c’est Anaconda, Anaconda2/Lib/site-packages/
    6) Là, vous devriez pouvoir importer le module cv2. Si ça marche pas, essayez ça :
    import imp
    imp.find_module(‘cv2’)Cela vous dira où le module cv2 est cherché. Ca doit correspondre à l’adresse du point 5) Si ce n’est pas le cas, copiez le fichier cv2.pyd à l’adresse donnée par imp.find_module
    7) Vérifiez la bonne installation d’opencv par les commandes :
    import.cv2; print cv2.__version__

[:]

Poste

[:fr]Ouverture de poste : Maître de conférences en Vidéo Immersive[:en]Open position: Associate professor in Immersive Video[:]

[:fr]

Télécom ParisTech recrute un(e)
Enseignant-chercheur en vidéo immersive à 46 rue Barrault- 75013 PARIS
Date limite de candidature : 10/11/2017

Type de contrat / Catégorie(s) pouvant postuler
CDI / II-C
Éléments à envoyer pour postuler
Modalités de candidature :
Envoyer
– un curriculum vitae complet et détaillé
– une lettre de motivation
– une notice de travaux exposant les activités passées du candidat en enseignement (formation initiale et formation continue) et en recherche : les deux types d’activités doivent être décrits avec le même souci de rigueur et de précision et témoigner des réflexions qui les ont accompagnées
– le texte des principales publications
– les noms et adresses de deux personnalités qualifiées pouvant donner un avis éclairé sur la candidature
– un projet succinct d’enseignement et un projet succinct de recherche (maximum 3 pages)
Nom et adresse d’envoi du dossier de candidature
Par mail à : recrutement@telecom-paristech.fr
ou par courrier à : Télécom ParisTech – DRH – B659 – 46 rue Barrault – 75634 Paris Cedex 13
Contact(s)
Marco Cagnazzo, second contact
Position description
Cliquer pour télécharger la fiche de poste

[:en]

Télécom ParisTech recruits
An associate professor in Immersive Video
46 rue Barrault- 75013 PARIS
Candidature deadline : 10 nov. 2017

See also here (French).

Please send:
– a detailed curriculum vitae
– a cover letter
– a description of the past activities of the candidate in teaching (initial and continuing training) and research
– the main publications
– the names and addresses of two qualified persons who can give an informed opinion on the applicant
– a succinct teaching  and research project (maximum 3 pages)
Send to
E-mail : recrutement@telecom-paristech.fr
OR
Mail : Télécom ParisTech – DRH – B659 – 46 rue Barrault – 75634 Paris Cedex 13
Contact(s)
Marco Cagnazzo, second contact
Position description (in French)
Clik here
Extract of the position description in English:
Required degrees:
  • PhD; or
  • Master Degree (or equivalent) and 5+ years of experience ; or
  • Professional with 8+ years of experience
Required knowledge:
  • Video compression; and
  • Immersive video
Required skills:
  • University-level teaching experience; and
  • Good level of English; and
  • Good level of French, or engagement to reach a good level as soon as possible
Desirable skills (one or more among)
  • Statistical model of multi-dimensional signals;
  • Video streaming;
  • Video quality
  • Digital holography
  • Programming languages
  • Teaching by projects and problems

 

[:]

Nouveau, Poste

[:fr]Poste de Maître de conférences en Vidéo immersive[:en]Open position: Associate professor in Immersive Video[:]

[:fr]Un poste de Maître de conférences en Vidéo immersive sera prochainement ouvert dans notre équipe. Nous cherchons des docteurs avec au moins un an d’expérience. Des candidats avec une expérience plus longue sont également souhaitables.

Domaines de recherches : vidéo immersive, codage vidéo, transmission vidéo, qualité.

Expertise : traitement du signal, réseaux, mathématiques appliqués.

Le descriptif du poste sera publié bientôt. Entre temps, les candidats intéressés peuvent me contacter directement par e-mail : cagnazzo@telecom-paristech.fr

 [:en]Very soon we will open a position of Associate Professor (specialty: immersive video) in our team at Telecom-ParisTech. We are looking for brilliant PhD, preferably with 1y+ of post-doctoral experience. More experienced candidates are also welcome. The detailed call will follow soon.

Research domains: immersive video, video coding, video transmission, video quality.

Background: signal processing, networking, applied maths.

Potential candidate can contact me at cagnazzo@telecom-paristech.fr[:]

Séminaire

[:fr]Journée séminaires équipe Multimédia [:en]Multimedia group seminar’s day[:]

[:fr]La dernière journée séminaires de l’équipe Multimédia aura lieu le mardi 12 juin en B500. Trois présentations sont au programme :

  1. Iulia Mitrica : « Aircraft screen content compression »
  2. Belén Luque Lopez : « Super resolution on 3D point cloud using CNNs »
  3. Theodoros Karagkioules : « A Comparative Case Study of HTTP Adaptive Streaming Algorithms in Mobile Networks »

 

 [:en]Three talks are in program for our last group seminar’s day (June 12th 2017) :

  1. Iulia Mitrica : « Aircraft screen content compression »
  2. Belén Luque Lopez : « Super resolution on 3D point cloud using CNNs »
  3. Theodoros Karagkioules : « A Comparative Case Study of HTTP Adaptive Streaming Algorithms in Mobile Networks »

 

 [:]