OBJECTIVES
Computer Vision (CV) is an emerging technology and VC's industry is growing tremendously year after year. The International Master in Computer Vision (IMCV) will enable graduates to acquire general knowledge of CV, as well as to ensure the ability to analyse the needs of a company in the scope of these techniques and to propose and apply the most suitable existing technological tools. IMCV offers the employer a professional profile oriented to computer vision, with theoretical and practical training in a variety of technical solutions that provides a solid and broad knowledge of the area and allows the professional to analyse the needs of a company and provide innovative solutions.
IMCV aims to offer an advanced training in CV, also offering transversal competences: to exercise the profession with an awareness of its human, economic, legal and ethical dimension; ability to work in team, organization and planning.
At IMCV, the student will acquire the capacity to: critically analyse and evaluate technologies and methodologies; analyse the needs of a company in the CV field and develop the best technological solution; identify theoretical results or new technologies with innovative potential and turn them into products and services useful to society; autonomous learning for specialization.
In terms of specific skills, the student is expected to be able to: know and apply the concepts, methodologies and technologies of image and video processing and analysis; to know and apply techniques of automatic learning and pattern recognition applied to CV; communicate and disseminate the results and conclusions of the research.
To achieve its goals, the Master is organized in five Modules:
-Image Processing and Analysis
-Visual Modelling and Recognition
-Machine Learning for Computer Vision
-Machine Vision for Industry and Engineering
-Biomedical Image Analysis and Applications
INTERNATIONAL PROGRAMME
IMCV is an international programme, being jointly offered by the University of Porto, the University of Santiago de Compostela, the University of Vigo, and the University of A Coruna. IMCV is totally offered in English.
DIPLOMA
After completing the 3 semesters of the programme, the graduate has access to a Master's degree in Computer Vision.
CAREER PROSPECTS
The curriculum of the Master in Computer Vision is anchored in real-world problems with a component of project development in the field of Computer Vision. IMCV aims to train highly specialized professionals capable of taking the lead in complex and large-scale Computer Vision projects with high-quality requirements.
STUDY PLAN 2020/2021
https://sigarra.up.pt/feup/en/CUR_GERAL.CUR_VIEW?pv_ano_lectivo=2020&pv_origem=CAND&pv_tipo_cur_sigla=M&pv_curso_id=21561
APPLICATIONS
(at the University of Porto)
https://sigarra.up.pt/feup/en/CAND_ADM.INFORMACAO_RELEVANTE_ESC_VIEW?pv_processo_id=986608
CfP reminder: RSS 2020 Workshop on Self-Supervised Robot Learning
April 21st, 2020 
Daniela Lopez de Luise This is a reminder about the (Virtual) RSS Workshop on
Self-supervised learning is a promising direction that aims to learn representations from the data itself without explicit and potentially even manual supervision. One of the major benefits of self-supervised learning is the ability to scale to large amounts of unlabelled data in a lifelong learning manner and to improve performance by reducing the effect of dataset bias. Recent development in self-supervised learning has resulted in achieving comparable or better performance than fully-supervised models. However, many of these methods are developed in
domain-specific communities such as robotics, computer vision or reinforcement learning. The aim of this workshop is to bring together researchers from different communities to discuss opportunities, challenges and explore new directions.
Topics
======
The focus topics of our workshop include, but are not restricted to:
– Self-supervised learning for robotics, robot vision, reinforcement learning….
– Self-supervised domain adaptation
– Meta-learning of self-supervised tasks
– Large-scale self-supervised learning
– Learning of generalizable pretext-tasks
– Loss functions for self-supervised learning
– Learning from auxiliary/multiple tasks
– Multimodal and cross-modal learning
Submission Instructions
====================
We encourage participants to submit their research in the form of a single PDF. Submissions may be up to 4 pages in length, including figures, excluding references and any supplementary material. Please use the RSS conference template. Accepted papers will be presented in a
poster session and selected awards papers as spotlight talks. All submitted contributions will go through a single blind review process. The contributed papers will be made available on the workshop’s website and selected papers will be invited for a special issue of a major
robotics journal.
Submission Website: https://easychair.org/conferences/?conf=ssrl20
LaTeX Template: https://roboticsconference.org/docs/paper-template-latex.tar.gz
In order to make acceptance decisions early, we request interested researchers to submit a single page extended abstract by 19th April as an expression of interest. The authors would then have time 2nd July to include new results and submit the full 4 page paper. We also welcome submissions that have already been accepted to RSS or other major conferences and journal papers that have not been discussed in a conference.
=============
One page submission deadline: April 19th, 2020 AoE
Notification of acceptance: April 24th, 2020
Full paper submission: July 2nd, 2020 AoE
Virtual Workshop date: July 13th, 2020
Invited Speakers
==============
Pieter Abbeel (UC Berkeley & Covariant.AI)
Dieter Fox (University of Washington & NVIDIA)
Abhinav Gupta (CMU & Facebook AI Research)
Roberto Calandra (Facebook AI Research)
Chelsea Finn (Stanford University)
Pierre Sermanet (Google Brain)
Andy Zeng (Google Brain)
Organizing Committee
==================
Abhinav Valada, University of Freiburg
Anelia Angelova, Google Research/Google Brain
Joschka Boedecker, University of Freiburg
Oier Mees, University of Freiburg
Wolfram Burgard, University of Freiburg
For further information please contact us at <rss20-ssrl@googlegroups.com>.
Best,
Abhinav, Anelia, Joschka, Oier, Wolfram
Call for papers The 3rd workshop on Face and Gesture Analysis for Health Informatics (FGAHI) @ ICMI 2020
April 21st, 2020 Daniela Lopez de Luise There is an ever-growing research interests of the computer vision and machine learning community in modeling human facial and gestural behavior for clinical applications. However, the current state of the art in computer vision and machine learning for face and gesture analysis has not yet achieved the goal of reliable use of behavioral indicators in clinical context. One main challenge to achieve this goal is the lack of available archives of behavioral observations of individuals that have clinically relevant conditions (e.g., pain, depression, autism spectrum). Well-labeled recordings of clinically relevant conditions are necessary to train classifiers. Interdisciplinary efforts to address this necessity are needed. The workshop aims to discuss the strengths and major challenges in using computer vision and machine learning of automatic face and gesture analysis for clinical research and healthcare applications. We invite scientists working in related areas of computer vision and machine learning for face and gesture analysis, affective computing, human behavior sensing, and cognitive behavior to share their expertise and achievements in the emerging field of computer vision and machine learning based face and gesture analysis for health informatics.
Website
Organizers
- Zakia Hammal (Carnegie Mellon University)
- Di Huang (Beihang University)
- Liming Chen (Ecole Centrale De Lyon)
- Mohamed Daoudi (IMT Lille Douai, CRIStAL UMR CNRS)
- Kévin Bailly (Sorbonne University)
RSS 2020 (Virtual) Workshop on Self-Supervised Robot Learning
April 21st, 2020 Daniela Lopez de Luise
Deadline Extension: May 4th, 2020 AoEUPDATE CONCERNING COVID-19
The RSS 2020 SSRL organizing committee hopes that you are safe and well. Due to the pandemic and the uncertainty regarding travel to the US, the RSS 2020 SSRL workshop will take place VIRTUALLY on the original date of July 13th. The submission deadline has been extended to May 4th, 2020 AoE.
Call for Papers
============
RSS 2020 (Virtual) Workshop on Self-Supervised Robot Learning
Robotics: Science and Systems (RSS)
July 13th, 2020
Website: https://www.brainlinks-braintools.uni-freiburg.de/rss20-ssrl
Overview
========
Self-supervised learning is a promising direction that aims to learn representations from the data itself without explicit and potentially even manual supervision. One of the major benefits of self-supervised learning is the ability to scale to large amounts of unlabelled data in a lifelong learning manner and to improve performance by reducing the effect of dataset bias. Recent development in self-supervised learning has resulted in achieving comparable or better performance than fully-supervised models. However, many of these methods are developed in domain-specific communities such as robotics, computer vision or reinforcement learning. The aim of this workshop is to bring together researchers from different communities to discuss opportunities, challenges and explore new directions.
Topics
======
The focus topics of our workshop include, but are not restricted to:
-Self-supervised learning for robotics, robot vision, reinforcement learning….
-Self-supervised domain adaptation
-Meta-learning of self-supervised tasks
-Large-scale self-supervised learning
-Learning of generalizable pretext-tasks
-Loss functions for self-supervised learning
-Learning from auxiliary/multiple tasks
-Multimodal and cross-modal learning
Submission Instructions
====================
We encourage participants to submit their research in the form of a single PDF. Submissions may be up to 4 pages in length, including figures, excluding references and any supplementary material. Please use the RSS conference template. Accepted papers will be presented in a poster session and selected awards papers as spotlight talks. All submitted contributions will go through a single blind review process. The contributed papers will be made available on the workshop’s website and selected papers will be invited for a special issue of a major robotics journal.
Submission Website: https://easychair.org/conferences/?conf=ssrl20
LaTeX Template: https://roboticsconference.org/docs/paper-template-latex.tar.gz
In order to make acceptance decisions early, we request interested researchers to submit a single page extended abstract by 19th April as an expression of interest. The authors would then have time 2nd July to include new results and submit the full 4 page paper. We also welcome submissions that have already been accepted to RSS or other major conferences and journal papers that have not been discussed in a conference.
Important Dates
=============
– One page submission new deadline: May 4th, 2020 AoE
– Notification of acceptance: May 18th, 2020
– Full paper submission: July 2nd, 2020 AoE
– Virtual Workshop date: July 13th, 2020
Invited Speakers
==============
– Pieter Abbeel (UC Berkeley & Covariant.AI)
– Dieter Fox (University of Washington & NVIDIA)
– Abhinav Gupta (CMU & Facebook AI Research)
– Roberto Calandra (Facebook AI Research)
– Chelsea Finn (Stanford University)
– Pierre Sermanet (Google Brain)
– Andy Zeng (Google Brain)
Organizing Committee
==================
– Abhinav Valada, University of Freiburg
– Anelia Angelova, Google Research/Google Brain
– Joschka Boedecker, University of Freiburg
– Oier Mees, University of Freiburg
– Wolfram Burgard, University of Freiburg
For further information please contact us at <rss20-ssrl@googlegroups.com>.
Best,
Abhinav, Anelia, Joschka, Oier, Wolfram
IEEE CAMAD’20: SS on Emerging Data-driven Approches for Network Optimization
April 21st, 2020 Daniela Lopez de Luise announcement]*
* * * * * * * * *
SS on Emerging Data-driven Approches for Network Optimization
IEEE CAMAD 2020
https://camad2020.ieee-camad.org/
* * * * * * * * *
The foundation of 5G and beyond mobile networks lies in the convergence
between networking and computing. The most appealing realization of such
convergence is the application of artificial intelligence (AI) and
machine learning (ML) to optimize network functions. The latter has
generated an increasing interest from academia and industry paving the
path for the transformation from the 5G paradigm "connected things" into
a "connected intelligence" vision for beyond 5G and 6G mobile networks.
To this end, the role of AI/ML is to support zero-touch configuration
and orchestration, thereby enabling self-configuration and
self-optimization of the mobile network. Mobile networks are indeed
becoming increasingly complex, heterogeneous, dynamic and dense, which
makes extremely hard to model correctly their behavior. Model-free
solutions that AI enable can overcome such challenge.
This Special Session seeks contributions from experts in areas such as
network programming, distributed systems, machine learning, data
science, data structures and algorithms, and optimization to discuss the
latest research ideas and results on the application of AI/ML to
networking. Specifically, this Special Session welcomes contributions in
the following major areas (indicative list, other related topics will
also be considered):
– Machine learning (ML) and big data analytics in networking
– Case studies showing (dis)advantages of AI/ML techniques for
networking over traditional ones
– Edge-driven data analytics and applications to smart cities
– AI/ML assisted network optimization
– Resource-efficient machine learning for mobile networks
– Measurements and analysis of network traffic for AI/ML systems
– Efficient ML data structures, algorithms and network protocols to
process network monitoring data
– Approaches for privacy-aware network traffic data collection
– Architectures for federated learning and its applications to
networking
– Energy-efficient federated learning
– Incentive mechanisms of federated learning
– In-network computation for next generation wireless networks
** IMPORTANT DATES **
Submission Deadline: May 20th
Notification Acceptance: July 5th
Camera-Ready due: July 31st
** SUBMISSION INSTRUCTIONS **
Prospective authors are invited to submit a full paper of not more than
six (6) IEEE style pages including results, figures and references.
Papers should be submitted via EDAS. Papers submitted to the conference,
must describe unpublished work that has not been submitted for
publication elsewhere. All submitted papers will be reviewed by at least
three TPC members, while submission implies that at least one of the
authors will register and present the paper at the conference.
Electronic submission will be carried out through the EDAS web site at
the following link: https://edas.info/newPaper.php?c=27371&track=101982
All accepted papers will be included in the conference proceedings and
IEEE digital library (http://ieeexplore.ieee.org/).