Opendata, web and dolomites

SEED SIGNED

Learning to See in a Dynamic World

Total Cost €

0

EC-Contrib. €

0

Partnership

0

Views

0

 SEED project word cloud

Explore the words cloud of the SEED project. It provides you a very rough idea of what is the project "SEED" about.

automatic    learning    localize    adaptively    techniques    dynamic    people    compositional    first    extract    animate    spaces    geometrical    methodology    horizons    reasoning    outdoor    scene    indexing    spatial    acquire    layout    accurate    time    human    fundamentally    integrating    perspective    indoor    propagating    environments    chairs    phones    inverse    minimal    categories    precise    tractable    interact    move    supervision    continuous    seed    descriptions    segmentation    animals    world    diverse    objects    semantic    automatically    robotics    boundaries    sense    supervised    manufacturing    personal    interactions    forecast    office    augmented    actions    cars    ground    urban    purpose    manner    forecasting    consolidating    interaction    visual    envisaged    computer    vision    acquired    data    bicycles    physical    editing    components    qualitative    observers    video    models    scenes    computers    ended    environmental    temporal    contextual    demonstrators    assistance    figure    training    recover    corresponding    machine   

Project "SEED" data sheet

The following table provides information about the project.

Coordinator
LUNDS UNIVERSITET 

Organization address
address: Paradisgatan 5c
city: LUND
postcode: 22100
website: n.a.

contact info
title: n.a.
name: n.a.
surname: n.a.
function: n.a.
email: n.a.
telephone: n.a.
fax: n.a.

 Coordinator Country Sweden [SE]
 Project website http://www.maths.lth.se/sminchisescu/
 Total cost 1˙999˙412 €
 EC max contribution 1˙999˙412 € (100%)
 Programme 1. H2020-EU.1.1. (EXCELLENT SCIENCE - European Research Council (ERC))
 Code Call ERC-2014-CoG
 Funding Scheme ERC-COG
 Starting year 2016
 Duration (year-month-day) from 2016-01-01   to  2020-12-31

 Partnership

Take a look of project's partnership.

# participants  country  role  EC contrib. [€] 
1    LUNDS UNIVERSITET SE (LUND) coordinator 1˙999˙412.00

Map

 Project objective

The goal of SEED is to fundamentally advance the methodology of computer vision by exploiting a dynamic analysis perspective in order to acquire accurate, yet tractable models, that can automatically learn to sense our visual world, localize still and animate objects (e.g. chairs, phones, computers, bicycles or cars, people and animals), actions and interactions, as well as qualitative geometrical and physical scene properties, by propagating and consolidating temporal information, with minimal system training and supervision. SEED will extract descriptions that identify the precise boundaries and spatial layout of the different scene components, and the manner they move, interact, and change over time. For this purpose, SEED will develop novel high-order compositional methodologies for the semantic segmentation of video data acquired by observers of dynamic scenes, by adaptively integrating figure-ground reasoning based on bottom-up and top-down information, and by using weakly supervised machine learning techniques that support continuous learning towards an open-ended number of visual categories. The system will be able not only to recover detailed models of dynamic scenes, but also forecast future actions and interactions in those scenes, over long time horizons, by contextual reasoning and inverse reinforcement learning. Two demonstrators are envisaged, the first corresponding to scene understanding and forecasting in indoor office spaces, and the second for urban outdoor environments. The methodology emerging from this research has the potential to impact fields as diverse as automatic personal assistance for people, video editing and indexing, robotics, environmental awareness, augmented reality, human-computer interaction, or manufacturing.

 Publications

year authors and title journal last update
List of publications.
2018 A. Zanfir, C. Sminchisescu
Deep Learning of Graph Matching
published pages: , ISSN: , DOI:
IEEE International Conference on Computer Vision and Pattern Recognition 2019-06-06
2018 H. Petzka and C. Sminchisescu
Non-attracting regions of local minima in deep and wide neural networks
published pages: , ISSN: , DOI:
2019-06-06
2018 M. Zanfir, A.I. Popa, A. Zanfir, C. Sminchisescu
Human Appearance Transfer
published pages: , ISSN: , DOI:
IEEE International Conference on Computer Vision and Pattern Recognition 2019-06-06
2018 A. Pirinen, C. Sminchisescu
Deep Reinforcement Learning of Region Proposal Networks for Object Detection
published pages: , ISSN: , DOI:
IEEE International Conference on Computer Vision and Pattern Rewcognition 2019-06-06
2018 E. Marinoiu, M. Zanfir, V. Olaru, C. Sminchisescu
3D Human Sensing, Action and Emotion Recognition in Robot Assisted Therapy of Children With Autism
published pages: , ISSN: , DOI:
IEEE International Conference on Computer Vision and Pattern Recognition 2019-06-06
2016 D. Nilsson, C. Sminchisescu
Semantic Video Segmentation by Gated Recurrent Flow Propagation
published pages: , ISSN: , DOI:
IEEE International Conference on Computer Vision and Pattern Recognition 2019-06-06
2016 S. Mathe, A. Pirinen, C. Sminchisescu.
Reinforcement Learning for Visual Object Detection
published pages: , ISSN: , DOI:
IEEE International Conference on Computer Vision and Pattern Recognition 2019-06-06
2017 A. Popa, M. Zanfir, C. Sminchisescu
Deep Multitask Architecture for Integrated 2D and 3D Human Sensing
published pages: , ISSN: , DOI:
IEEE International Conference on Computer Vision and Pattern Recognition 2019-06-06
2017 C. Ionescu, A. Popa, C. Sminchisescu
Large-Scale Data Driven Kernel Approximation
published pages: , ISSN: , DOI:
Artificial Intelligence and Statistics 2019-06-06

Are you the coordinator (or a participant) of this project? Plaese send me more information about the "SEED" project.

For instance: the website url (it has not provided by EU-opendata yet), the logo, a more detailed description of the project (in plain text as a rtf file or a word file), some pictures (as picture files, not embedded into any word file), twitter account, linkedin page, etc.

Send me an  email (fabio@fabiodisconzi.com) and I put them in your project's page as son as possible.

Thanks. And then put a link of this page into your project's website.

The information about "SEED" are provided by the European Opendata Portal: CORDIS opendata.

More projects from the same programme (H2020-EU.1.1.)

InsideChromatin (2019)

Towards Realistic Modelling of Nucleosome Organization Inside Functional Chromatin Domains

Read More  

SUExp (2018)

Strategic Uncertainty: An Experimental Investigation

Read More  

ECOLBEH (2020)

The Ecology of Collective Behaviour

Read More