Invitation to join 2021 Summer ‘Programming short course and workshop on Deep Learning and Computer Vision’, 25-27th August 2021

 

you are welcomed to register in the  CVML e-course on ‘Programming short course and workshop on Deep Learning and Computer Vision’,  25–27th August 2021:

http://icarus.csd.auth.gr/cvml-programming-short-course-and-workshop-on-deep-learning-and-computer-vision-for-autonomous-systems-2021/

 

It will take place as a three-day e-course (due to COVID-19 circumstances), hosted by the Aristotle University of Thessaloniki (AUTH), Thessaloniki, Greece, providing a series of live lectures and workshops delivered through a tele-education platform (Zoom). They will be complemented with on-line video recorded lectures and lecture pdfs, to facilitate international participants having time difference issues and to enable you to study at own pace.  You can also self-assess your knowledge, by filling appropriate questionnaires (one per lecture). You will be provided programming to improve your programming skills. You will also have accesses to tutorial exercises to better your theoretical understanding of selected CVML topics.

This course is part of the very successful CVML programming short course and workshop series that took place in the last four years.

 

Course description ‘Programming short course and workshop on Deep Learning and Computer Vision’

The programming short course and workshop e-course consists of 16 1-hour live lectures & workshops organized in two Parts (1 Part per day):

Part A will focus on Deep Learning and GPU programming.

Part B lectures will focus on deep learning algorithms for computer vision, namely on 2D object/face detection and 2D object tracking.

Part C lectures will focus on autonomous UAV cinematography. Before mission execution, it is best simulated, using drone mission simulation tools.

 

Course lectures

Part A (8 hours),

Deep Learning and GPU programming

Deep neural networks. Convolutional NNs.

Deep learning for target detection.

Image classification with CNNs.

Target detection with PyTorch.

Part B (8 hours), Deep Learning for Computer Vision

Deep learning for object/face detection.

2D object tracking.

PyTorch: Understand the core functionalities of an object detector. Training and deployment.

OpenCV programming for object tracking.

Part C (8 hours), Autonomous UAV cinematography

Video summarization.

UAV cinematography.

Video summarization with Pytorch.

Drone cinematography with Airsim.

 

You can use the following link for course registration:

http://icarus.csd.auth.gr/cvml-programming-short-course-and-workshop-on-deep-learning-and-computer-vision-for-autonomous-systems-2021/

 

Lecture topics, sample lecture ppts and videos, self-assessment questionnaires, programming exercises and tutorial exercises can be found therein.

For questions, please contact: Ioanna Koroni <koroniioanna@csd.auth.gr>

 

The short course is organized by Prof. I. Pitas, IEEE and EURASIP fellow and IEEE distinguished speaker.  He is the coordinator of the EC funded International AI Doctoral Academy (AIDA), that is co-sponsored by all 5 European AI R&D flagship projects (H2020 ICT48). He was initiator and first Chair of the IEEE SPS Autonomous Systems Initiative. He is Director of the Artificial Intelligence and Information analysis Lab (AIIA Lab), Aristotle University of Thessaloniki, Greece. He was Coordinator of the European Horizon2020 R&D project Multidrone. He is ranked 249-top Computer Science and Electronics scientist internationally by Guide2research (2018). He has 33800+ citations to his work and h-index 86+.

 

AUTH is ranked 153/182 internationally in Computer Science/Engineering, respectively, in USNews ranking.

 

Relevant links:

1) Prof. I. Pitas:

https://scholar.google.gr/citations?user=lWmGADwAAAAJ&hl=el

2) Horizon2020 EU funded R&D project Aerial-Core: https://aerial-core.eu/

3) Horizon2020 EU funded R&D project Multidrone: https://multidrone.eu/

4) International AI Doctoral Academy (AIDA): http://www.i-aida.org/

5) Horizon2020 EU funded R&D project AI4Media: https://ai4media.eu/

6) AIIA Lab: https://aiia.csd.auth.gr/

 

Sincerely yours

Prof. I. Pitas

Director of the Artificial Intelligence and Information analysis Lab (AIIA Lab)

Aristotle University of Thessaloniki, Greece

 

PETS’21 challenge and workshop

CFP: PETS2021 Int’l Workshop on Performance Evaluation of Tracking and Surveillance
www.pets2021.net
 
In Cooperation with AVSS2021 (17th IEEE Int’l Conference on Advanced Video and Signal-based Surveillance)
November 16-19, 2021
Virtual
 
The 2021 International Workshop on Performance Evaluation of Tracking and Surveillance (PETS'21) continues the series of highly successful PETS workshops held for over twenty years (AVSS'12, WVM'13, AVSS'14, AVSS'15, CVPR'16, CVPR'17, to name some of the most recent). The goal of the PETS workshop has been to foster the emergence of methodology for performance evaluation of tracking and surveillance.  This includes development of performance evaluation metrics as well as a quantitative evaluation of tracking and surveillance results based on a common dataset. PETS 2021 is sponsored by the EU Project FOLDOUT.

PETS 2021 introduces a new and exciting surveillance challenge, through-foliage detection and tracking. Such an application is important for (green) border surveillance. The specific tasks addressed are (1) through-foliage detection and fragmented occlusion, and (2) long-term tracking in natural environments, both of which have been received relatively limited attention in the computer vision community. Solutions to solve these tasks are currently unavailable. The aim of this challenge is to raise awareness to these tasks in the vision community and to foster appropriate solutions. The overall border surveillance challenge has significant impact for border authorities worldwide for enhancing border security operations. A corresponding dataset is provided for this challenge which covers the two tasks described above. 

Ultimately, the workshop challenge comes down first, to accurately detecting and/or tracking person(s) present in the surveillance scene. To this end, a range of methods could be applied from change detectors to object detectors to trackers. Understanding of the temporal history of the movement of the person(s) may help in accurate localisation and tracking, especially in partially or heavily occluded scenes. Secondly, the challenge recognises that simple bounding boxes may not always be appropriate for annotating the visual extent of the detected object (person). Hence this challenge also considers alternate object representational schemes.
 
Important Dates
 
August 31, 2021
Deadline for submission of results and methods' description
September 10, 2021
Notification of acceptance
November 2021 (TBC: between 16-19)
Challenge event (online)
 
Organisers
 
Organising Committee
 
James Ferryman (University of Reading) 
Roman Pflugfelder (Austrian Institute of Technology)
Georg Melzer-Venturi (EUTEMA)
Email: j.m.ferryman@reading.ac.uk
 
Technical Committee
Luis Patino (University of Reading)
Julian Pegoraro (Austrian Institute of Technology)
David Scheiber (Austrian Institute of Technology)
 
Submission Information
 
The workshop invites submissions which:
Process (i.e. apply one or more change/object detectors and/or trackers) on one or more of the provided video sequences and report results in a standardised format. The submission should include a short description of the methodology used and results submitted in XML format.
 
Please visit the workshop webpage at www.pets2021.net and click on the Authors Instructions to know the detailed description of the challenges set in PETS 2021 and click on the Datasets link to see a detailed description of the datasets and how to download them.

Submit a Paper by 30 August for LATINCOM 2021 (Santo Domingo, Dominican Republic November 17-19)

FYI, machine learning is one of the highlighted topics

 

 

 

LATINCOM 2021

 

 

 

CALL FOR PAPERS

 

 

 

The IEEE Latin-American Conference on Communications (LATINCOM) is an international conference organized by the IEEE Communications Society (ComSoc) Latin America Region. This year, the 13th edition of the conference, LATINCOM 2021, will be held virtually and in person in Santo Domingo, Dominican Republic 17-19 November 2021.

We are seeking submissions of original, unpublished, high-quality research papers focused on (but not limited to) the following areas of interest:

  • Mobile and Wireless Networking
  • Communication Services, Software and Multimedia Applications
  • Communication QoS, Reliability and Performance Modeling
  • Optical Networks
  • Communications Theory & Signal Processing
  • Next-Generation Networking and Internet
  • AI, Big Data and ML for Networking 
  • Selected Areas in Communications

Submissions Deadline Extended to 30 August 2021

 

 

 

 

 

 

 

Keynote Speakers

 

 

 

 

 

 

 

 

 

 

 

© 2021 IEEE– All rights reserved.

 

 

IEEE • 445 Hoes Lane, Piscataway, NJ 08854 USA

 

              

 

ICETCI 2021

The International Conference on Emerging Techniques in Computational Intelligence, ICETCI 2021 will be held  virtually from August 25 to 27, 2021. The conference will consist of one day of tutorial sessions followed by two days of keynote lectures by invited experts and paper presentations by practitioners.

The attendance is free but registration is mandatory. kindly access this link: http://ietcint.com/user/AttendeesRegistration  
Best Regards,
The Conference Chairs

ROAD @ ICCV 2021: Final Call for Papers

ROAD @ ICCV 2021: Final Call for Papers

 

The deadline for submitting papers to the ICCV 2021 workshop

“The ROAD challenge: Event detection for situation awareness in autonomous driving”,

has been extended to ***September 5 2021***

https://lnkd.in/gsBU5wU

 

Decisions will be made public on September 14. Publication of the proceedings will be pursued separately.

 

The deadline for submitting entries to the Challenge has also been extended to ***September 30 2021***

 

https://sites.google.com/view/roadchallangeiccv2021/challenge

The goal of this Workshop/Challenge is to put to the forefront of the research in autonomous driving “situation awareness”, intended as the ability to create semantically useful representations of dynamic road scenes in terms of the notion of ‘road event’, leveraging our recently released ROad event Awareness Dataset for autonomous driving (ROAD):

https://lnkd.in/gjr9M5Z

 

The Challenge proposes three video-level detection tasks: (1) agent detection, (2) action detection and (3) road event detection, intended as a triplet (agent, action, location).

All tasks consist in regressing ‘tubes’ of temporally linked bounding boxes and the associated label(s). Researchers active in object detection or action detection are especially encouraged to participate!

 

The dataset is composed by 22 long duration (8-minute-long) videos in diverse weather conditions, making the above detection tasks extremely challenging.

 

As for the papers, we invite contributions on the following topics:

Detecting and modelling ‘atomic’ events.

Detecting and modelling complex activities.

Predicting agent intentions.
Dynamic scene understanding from streaming videos.
Predicting the trajectory of pedestrians, vehicles and other road users.
Forecasting future road events (both atomic and complex).
Decision making, both via reinforcement/imitation learning and via intermediate representations, and a critical/empirical comparison between the two approaches.
Explicability of both perception and decision making components of autonomous driving.
Modelling road scenarios in a multi-agent framework.
Modelling the reasoning processes of road agents in terms of goals or mental states.
Machine theory of mind for autonomous vehicles.
The role of incremental, life-long and continual learning in autonomous driving, with a focus on situation awareness.
The use of realistic simulations to generate training data for semantic scene understanding.
Testing and certification of AI algorithms for autonomous driving.
The ethical implications of situation awareness and automated decision making.

 

Papers will be published as posters in two sessions. The winners of a Best Paper and a Best Student Paper award will instead give an oral presentation, as will the authors of the top entry in each Challenge task.

Papers must follow the ICCV 2021 template and be submitted via CMT:

https://lnkd.in/gweCKpU

The Workshop will allow for the submission of papers concurrently submitted elsewhere to aggregate all relevant efforts in this area.

We have secured an array of prestigious Invited Speakers:

Raquel Urtasun (Toronto)
Adrien Gaidon (TRI)
Daniela Rus (MIT)
Deva Ramanan (CMU)
Paul Newman (Oxford  University)

 

The workshop will also host a panel discussion on the future and ethical implications of autonomous driving.

Organisers

Fabio Cuzzolin, Andrew Bradley (Oxford Brookes University)
Gurkirt singh (ETH)
Reza Javanmard Alitappeh (Mazandaran University)
Stanislao Grazioso, Giuseppe Di Gironimo, Valentina Fontana (Federico II  University, Naples)
Valentina Mușat (Oxford  University)

Design by 2b Consult