Invitation to “Programming short course and workshop on Deep Learning and Computer Vision for Autonomous Systems 2020”, 19-21th August 2020

Dear Autonomous Systems engineers, scientists, and enthusiasts,


you are welcomed to register in the 2020 'Programming short course and workshop on Deep Learning and Computer Vision for Autonomous Systems', with applications on various autonomous systems, notably drones.  It will take place on 19-21th August 2020 as an e-course hosted by the Aristotle University of Thessaloniki (AUTH), Thessaloniki, Greece, providing a series of lectures and programming workshops delivered through a tele-education platform.

Due to the special COVID-19 circumstances, the course is scheduled to take place primarily as web course (default mode). Remote participation will be available via teleconferencing.

Students will be helped on line for executing the programming workshops while at home.

A physical meeting (second short course mode) is also planned for the same dates, provided that: a) AUTH and national regulations allow it and b) there are sufficient physical attendees. 

 

Greece has had an excellent COVID-19 epidemic record (one of the best worldwide) and our University had no reported COVID-19 cases, whatsoever. We intend to take all appropriate measures to ensure this record in the future as well.

The programming short course consists of a good mix of lectures and programming workshops (hands-on exercises) aiming at developing registrants’ programming skills for
Deep Learning and Computer Vision, with focus on autonomous systems planning/control and imaging/perception. It is organized three parts (one per day):


1) Part A aims at deep neural network programming (Convolutional NN and their use in target/object detection, PyTorch, Tensorflow).
2) Part B aims at computer vision programming (target tracking and localization, GPU architectures and programming, CUDA, OpenCV programming, drone mission simulations).
3) Part C aims at autonomous systems perception and programming (ROS, Gazebo, AIRSIM).

You can use the following link for course registration: http://icarus.csd.auth.gr/autonomous-systems-2020/

For questions, please contact: Ioanna Koroni <koroniioanna@csd.auth.gr&gt;

The short course is sponsored by the European Horizon2020 R&D project Aerial Core. It is organized by Prof. I. Pitas, IEEE and EURASIP fellow, Coordination of the European Horizon2020 R&D project Multidrone, Director of the Artificial Intelligence and Information analysis Lab (AIIA Lab), Aristotle University of Thessaloniki, Greece, Chair of the IEEE SPS Autonomous Systems Initiative. He is ranked 249 top Computer Science and Electronics Scientist internationally by Guide2research (2018).

The lectures and programming sessions will be delivered by very qualified Postdoc/PhD researchers and Professors, with a long R&D record in drone and autonomous systems programming from University of Seville (Robotics, Vision and Control Research Group) and AIIA Lab, Aristotle University of Thessaloniki.

Thessaloniki is a very pleasant city at the end of August, with vibrant night-life, very close to world-class resorts in Chalkidiki peninsula.

Aristotle University of Thessaloniki is the biggest University in Greece and in SE Europe. It is highly ranked internationally and its campus is at the city center.

Course registrants may also want to register (if so desired) in the back2back short course on ‘Short course on Deep Learning and Computer Vision for Autonomous Systems 2020. Application focus on autonomous/self-driving cars', 17-18th August 2020: http://icarus.csd.auth.gr/dl-and-cv-for-autonomous-cars-2020/

Relevant links:

1. H2020 project Aerial-Core: https://aerial-core.eu/

2. AIIA Lab: http://www.aiia.csd.auth.gr/

3. Prof. I. Pitas: https://scholar.google.gr/citations?user=lWmGADwAAAAJ&hl=el

Description of ‘Programming short course and workshop on Deep Learning and Computer Vision for Autonomous Systems’, 19-21th August 2020.

Part A (8 hours), Deep learning sample topic list

  1. Deep neural networks. Convolutional NNs
  2. Deep learning for target detection
  3. PyTorch basics
  4. Target detection with PyTorch
  5. Object oriented Tensorflow in Google Colab

Part B (8 hours), Computer vision sample topic list

  1. 2D target tracking
  2. Parallel GPU and multi-core CPU architectures. GPU programming
  3. CUDA programming
  4. OpenCV programming for object tracking

Part C (8 hours), Drone planning/control sample topic list

  1. Drone mission simulations.
  2. Drone perception and estimation.
  3. ROS UAL Abstraction Layer for drone applications.
  4. Drone perception with ROS.

 

Sincerely yours
Prof. I. Pitas
Director of the Artificial Intelligence and Information analysis Lab (AIIA Lab)

Aristotle University of Thessaloniki, Greece

 

ECCV 2020 Workshop – Beyond mAP: Reassessing the Evaluation of Object Detectors – Call for Papers

Call for Papers: ECCV 2020 Workshop – Beyond mAP: Reassessing the Evaluation of Object Detectors

 

Workshop link

https://nikosuenderhauf.github.io/roboticvisionchallenges/eccv2020

 

Workshop summary

This workshop assesses current evaluation procedures for object detection, highlights their shortcomings and opens discussion for possible improvements.

Through a focus on evaluation using challenges, the object detection community has been able to quickly identify which methods are effective by examining performance metrics. However, as this technological boom progresses, it is important to assess whether our evaluation metrics and procedures adequately align with how object detection will be used in practical applications. Quantitative results should be easily reconciled with a detector’s performance in applied tasks. This workshop provides a forum to discuss these ideas and evaluate whether current standards meet the needs of the object detection community.

 

The workshop also hosts the 3rd iteration of our probabilistic object detection (PrOD) competition. Details to be found at the workshop website and the competition page below

 

(https://competitions.codalab.org/competitions/20597)

 

 

Call for Papers

We invite authors to contribute papers to the workshop. Topics of interest comprise, but are not limited to:

  • New evaluation measures/metrics for object detection
  • New evaluation/visualization tools to analyze object detection systems
  • New evaluation procedures for better understanding object detection performance
  • Examinations of current evaluation procedures
  • New datasets designed to examine specific challenges in object detection
  • New detection methods that provide contributions/insights unrewarded by current evaluation procedures (e.g. improved detector calibration, probabilistic object detection, etc.)

Author Instructions

  • Submissions must follow the ECCV format and be up to 4 pages in length including references
  • It is accepted if this is an abbreviated version of a larger paper published elsewhere if properly referenced
  • Submit your paper through CMT (link)
  • Accepted papers will provide a short video outlining their work which will be part of the ECCV online workshop system (details to come)

If you have any questions don't hesitate to contact.

 

Best regards,

Dr David Hall

Research Fellow

Robotic Vision Benchmarking and Evaluation Project

Australian Centre for Robotic Vision

Queensland University of Technology

e-mail: d20.hall@qut.edu.au

Phone: +61 7 31380656

ORCiD: 0000-0002-5520-0128

Website: https://sites.google.com/view/davidhallcv/home

MobiHealth 2020 is going virtual! Submit your paper and get more citations & extra exposure by presenting online to a global audience (Springer, Scopus, ISI, more) November 19-20, 2020

Web version

November 19 – 20, 2020 | Saint Andrews, Great Britain Cyberspace
Submission Deadline: July 1, 2020

EAI is proud to announce that MobiHealth is going virtual and beyond borders.

Get the same full publication and indexing, enjoy EAI’s fair evaluation and recognition, present your paper to a global audience, and experience virtual meetings live as well as on-demand from the safety and comfort of your home.

MobiHealth 2020 will take place online due to safety concerns and travel restrictions caused by COVID-19. Although we will miss having everyone meet and connect in person, we feel strongly that knowledge exchange must continue, if not more so. That is why we have equipped our online conferences with live viewing with chat, virtual Q&A, and a multitude of other measures to provide you with a great experience. All of this while making the registration for co-authors and non-authors completely free to give you the biggest possible audience. You can learn more about EAI’s online conferences here.

sCOPE

The objectives of MobiHealth 2020 conference are to advance personal healthcare, medical diagnosis, treatment, patient care and patient safety through application of sensing technologies (e.g. Internet of Things IoT), mobile computing and effective data management methodologies. Contributions will be solicited regarding the interdisciplinary design and application of relevant technologies to help provide advanced mobile health care applications and infrastructures.

We are pleased to invite you to submit your paper to EAI MobiHealth 2020. Submissions should be in English, following the Springer formatting guidelines (see Submission). 

Submit Paper

Read More: Call for Papers

MobiHealth authors have enjoyed over 284.000+ downloads

Publication

All registered papers will be submitted for publishing by Springer and made available through SpringerLink Digital Library.

Proceedings will be submitted for inclusion in leading indexing services, Ei Compendex, ISI Web of Science, Scopus, CrossRef, Google Scholar, DBLP, as well as EAI’s own EU Digital Library (EUDL).

Authors of selected papers will be invited to submit an extended version to:
All accepted authors are eligible to submit an extended version in a fast track of:
Additional publication opportunities:
Important dates

Full Paper Submission Deadline: July 1, 2020

Notification Deadline: August 20, 2020

Camera-ready deadline: September 20, 2020 

Conference dates: November 19 – 20, 2020

Call for Workshop Proposals

MobiHealth 2020 is open to proposals for workshops to be held in conjunction with the main conference. MobiHealth workshops should focus on cutting-edge research areas. Innovative, high-risk frontier research ideas are particularly welcome as a main topic of a workshop. Workshop proposal submission deadline: June 15, 2020.

Read more: Call for Workshop Proposals

EAI COMMUNITY BENEFITS
Granting you visibility and fair review through
Community Review.
Credits counting towards your EAI Index, membership ranks and global recognition.
Receive invaluable real-time feedback on your presentation on-site via EAI Compass.
Follow us!

facebook    You Tube   twitter  

SI on Resource Management for Edge Intelligence in Journal of Systems Architecture

Dear Colleagues, 

You are cordially invited to submit your latest research findings to the Journal of Systems Architecture (CCF B) special issue on: 

 

Resource Management for Edge Intelligence


Due to rapid growth of Internet of Things (IoT) applications that demand large amounts of computing power, resource-constrained IoT devices typically do not have enough computing capability to satisfy the computational requirements. For example, inference or training of large machine learning models, e.g., Deep Neural Networks (DNNs), are typically quite resource-intensive. Computational offloading for edge intelligence can help overcome resource constraints of IoT devices, reduce computing load and improve task processing efficiency. Edge Computing and Fog Computing aim to harness computing resources in the proximity of the IoT devices to provide services in a timely manner with reduced accesses to the cloud, which may be time-consuming. For example, a DNN can be partitioned and processed collaboratively between the device, edge server and the cloud to optimize objectives such as performance and power consumption, based on factors such as workload, hardware platform capabilities and wireless bandwidth. This special issue addresses recent developments in algorithms and techniques for computational offloading for edge intelligence. Topics of interest include, but are not limited to:
Topics of interest include but are not limited to:
  • Techniques for profiling and modeling of latency and power consumption on device/edge/cloud
  • Algorithms for dynamic and adaptive resource management for both computation and communication objectives
  • Intelligent decision making for computational offloading with Machine Learning, esp. Reinforcement Learning.
  • Security, and privacy issues
  • Application case studies
General information for submitting papers to JSA can be found at https://www.journals.elsevier.com/journal-of-systems-architecture. Submissions should be made online at https://www.editorialmanager.com/jsa/. Please select the “VSI: RMEI20” option as the type of the paper during the submission process. 

 Submission Deadline:   June 30th, 2020

Prof. Shaohua Wan, Zhongnan University of Economics and Law, China
Prof. Huaming Wu, Tianjin University, China
Prof. Joarder Kamruzzaman, Professor of Information Technology, Federation University Australia
Prof. Sotirios Goudos, Aristotle University of Thessaloniki, Greece

ECCV 2020 workshop: VISART V “Where Computer Vision Meets Art” – Deadline Extension

VISART V “Where Computer Vision Meets Art“
http://visarts.eu

****************************************************************

5th Workshop on Computer VISion for ART Analysis
In conjunction with the 2020 European Conference on Computer Vision (ECCV),
Glasgow, UK

****************************************************************

IMPORTANT DATES
Full & Extended Abstract Paper Submission (EXTENDED): 12th June 2020
Notification of Acceptance: 10th July 2020
Camera-Ready Paper Due:  15th July 2020
Workshop: Morning of 23th August 2020

****************************************************************

CALL FOR PAPERS

Following the success of the previous editions of the Workshop on Computer VISion for ART Analysis held in 2012, `14, `16, and `18 we present the VISART V workshop, in conjunction with the 2020 European Conference on Computer Vision (ECCV 2020). VISART will continue its role as a forum for the presentation, discussion and publication of Computer Vision (CV) techniques for the analysis of art. As with the previous edition, VISART V offers two tracks:

  1.  Computer Vision for Art – technical work (standard ECCV submission, 14 pages excluding references)
  2.  Uses and Reflection of Computer Vision for Art (Extended abstract, 4 pages, excluding references)

The recent explosion in the digitisation of artworks highlights the concrete importance of application in the overlap between CV and art; such as the automatic indexing of databases of paintings and drawings, or automatic tools for the analysis of cultural heritage. Such an encounter, however, also opens the door both to a wider computational understanding of the image beyond photo-geometry, and to a deeper critical engagement with how images are mediated, understood or produced by CV techniques in the `Age of Image-Machines' (T. J. Clark). Submissions to our first track should primarily consist of technical papers; our second track, therefore, encourages critical essays or extended abstracts from art historians, artists, cultural historians, media theorists and computer scientists.

The purpose of this workshop is to bring together leading researchers in the fields of computer vision and the digital humanities with art and cultural historians and artists, to promote interdisciplinary collaborations, and to expose the hybrid community to cutting-edge techniques and open problems on both sides of this fascinating area of study.

This half-day workshop, in conjunction with ECCV 2020, calls for high-quality, previously unpublished, works related to Computer Vision and Cultural History. Submissions for both tracks should conform to the ECCV 2020 proceedings style and will be double-blind peer-reviewed by at least three reviewers. However, extended abstracts will not appear in the conference proceedings. Papers must be submitted online through the CMT submission system at:

https://cmt3.research.microsoft.com/VISART2020/

TOPICS include but are not limited to:

– Art History and Computer Vision
– Cultural Heritage and Computer Vision
– Image and visual representation in art
– 3D reconstruction from visual art or historical sites
– 2D and 3D human pose and gesture estimation in art
– Multi-modal multimedia computing systems and human-machine interaction
– Multimedia databases and digital libraries for artistic and art-historical research
– Visual Question & Answering (VQA) or Captioning for Art
– Interactive 3D media and immersive AR/VR environments for cultural heritage
– Authentication Forensics and dating
– Big-data analysis of art
– Media content analysis and search
– Security and legal issues in the digital presentation and distribution of cultural information
– Surveillance and Behaviour analysis in Galleries, Libraries, Archives and Museums

INVITED SPEAKERS

To be confirmed.

INTERNATIONAL PROGRAM COMMITTEE

To be confirmed

ORGANIZERS:
Alessio Del Bue, Istituto Italiano di Tecnologia (IIT)
Sebastiano Vascon, Ca' Foscari University of Venice
Leonardo Impett, EPFL & Biblioteca Hertziana, Max Planck for Art History
Peter Bell, Friedrich-Alexander University Nüremberg
Stuart James, Istituto Italiano di Tecnologia (IIT) & UCL DH

Design by 2b Consult