SAI-Expsitores 20-10

October 18th, 2021 Daniela Lopez de Luise
 

 

 



pdf icon Flyer_ASAI_Conferencia_20Oct.pdf
Read More »

WACV2022 MAP-A Workshop – Call for papers – extended deadline

October 14th, 2021 Daniela Lopez de Luise

 

EXTENDED SUBMISSION DEADLINE 30th October,2021

 

 

WACV2022 – Workshop On Manipulation, Adversarial and Presentation Attacks In Biometrics (MAP-A) is being organized to report the advancements in creation, evaluation, impact and mitigation measures for adversarial attacks on biometrics systems. The workshop targets submissions addressing the analyses and mitigation measures for function creep attacks. This half-day workshop is a fourth edition of the special session held, previously held in conjunction with BTAS-2018, LA, USA, BTAS-2019, Tampa, FL, and WACV 2020, Snowmass, USA respectively.

 

For more information please visit http://s.ntnu.no/wacv2022-mapa

 

Important Dates

Workshop: January 4, 2022

Full Paper Submission: 11th 30th October, 2021 (23:59 PST) (extended)

Acceptance Notice: 12th November, 2021 (23:59 PST)

Camera-Ready Paper: 15th November, 2021 (23:59 PST)

 

 

Topics Of Interest

The Workshop On Manipulation, Adversarial and Presentation Attacks In Biometrics (MAP-A) welcomes works that focus on biometrics and promote the development of (but not limited to):

•            Physical attacks on biometric systems.

•            Image manipulation attacks in biometrics verification and identification (e.g., PAD).

•            Video manipulation attacks.

•            Morphing attacks and detection

•            Generalizable attack detection algorithms

•            Forensic behavioral biometrics

•            Soft Biometrics cues for authenticity verification of biometric data

•            Multimedia forensics in biometrics

•            Integrity verification and authentication of digital content in biometrics.

•            Combination of multimodal decisions for authenticity verification in biometrics.

•            Function creep attacks effecting the privacy of biometric systems.

•            Human perception and decisions in biometric data authenticity verification

•            Ethical and societal implications of emerging manipulations.

•            Case studies based on the aforementioned topics.

 

 

Read More »

Call for Papers – ICPRAM 2022 (Position/Regular Papers Extension)

October 14th, 2021 Daniela Lopez de Luise

;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px;text-decoration:none;word-wrap:break-word;line-break:after-white-space”>

===================
Gabriella Sanniti di Baja
IAPR Fellow
Foreign Member Royal Society of Sciences at Uppsala, Sweden
Associate Researcher, ICAR-CNR
Via P. Castellino 111, Naples, Italy
email: gabriella.sannitidibaja@icar.cnr.it

Read More »

Master Internship Position: Deep Learning architectures for generating skeleton-based human motion, IRIMAS/UHA

October 14th, 2021 Daniela Lopez de Luise

;text-indent:0px;text-transform:none;white-space:normal;word-spacing:0px;background-color:#ffffff;text-decoration:none”>

Master Internship Position: Deep Learning architectures for generating skeleton-based human motion
Interested in Deep Learning and human motion analysis ? Apply to our Master internship position in deep generative models for skeleton-based human motion.
As part of the ANR DELEGATION project, you will have the opportunity to continue with a funded PhD in our team !
*******************************

Context:
Human motion analysis is crucial for studying people and understanding howthey  behave,  communicate  and  interact  with  real  world  environments.   Dueto the complex nature of body movements as well as the high cost of motioncapture systems, acquisition of human motion is not straightforward and thusconstraints  data  production.   Hopefully,  recent  approaches  estimating  humanposes from videos offer new opportunities to analyze skeleton-based human mo-tion.  While skeleton-based human motion analysis has been extensivelystudied for behavior understanding like action recognition, some efforts are yetto be done for the task of human motion generation.  Particularly, the automaticgeneration of motion sequences is beneficial for rapidly increasing the amountof data and improving Deep Learning-based analysis algorithms.
Since  several  years,  new  image  generation  paradigms  have  been  possiblethanks to the appearance of Generative Adversarial Networks (GAN) which have proved to be extremely efficient for many image generation tasks and hu-man posture estimation. Although these networks are very efficient,  theirexplainability and control still remain challenging tasks.  Differently, other gen-erative models have also emerged by considering the data distribution duringtraining like Variational AutoEncoder (VAE) and Flow-based networks.However, when it comes to human motion, many challenges remain to be solved,in particular when passing from the static case to the dynamic case.  Firstwork addressing deep generative models for human motion have considered mo-tion capture (mocap) data allowing to accurately extract body parts positionsalong the time.  Hence, aforementioned generative architectures have been suc-cessively employed for generating mocap-based human motion sequences. Differently,  we consider noisy skeleton data estimated from videos as it iseasily applicable in real-world scenarios for the general public.

Goal of the project:

The  goal  of  this  internship  is  to  provide  guidelines  in  building  deep  genera-tive models for skeleton-based human motion sequences.  Inspiring from recenteffective Deep Learning-based approaches, the aim is to gener-ate full skeleton-based motion sequences without access to successive poses asprior information as it can be done in prediction tasks.  It is therefore crucialto investigate how deep generative models can handle such noisy and possiblyincomplete  data  in  order  to  generate  novel  motion  sequences  as  natural  andvariable as possible
In particular, the candidate will work on the following tasks:
– Deep Learning architectures for skeleton-based human motion: investigation and assessment of the influence of different deep network ar- chitectures for capturing complex human motion features. Particularly, the goal of this task is to theoretically and empirically analyze the per- formance of existing architectures like CNN, RNN and GCN for modeling skeleton-based human motion.
– Deep generative models adapted to skeleton data: based on stud- ies from the previous task, the goal is to build generative models upon the previously identified meaningful spaces where skeleton sequences are represented. Therefore, the candidate will investigate different generative models, like GAN, VAE and Flow-based models, in order to propose and develop a complete Deep Learning model for generating skeleton-based human motions.
– Evaluation of deep generative models: in order to validate the pro- posed model, experimental evaluation is crucial. In comparison to motion recognition where classification accuracy is a natural way to assess an ap- proach, evaluating the task of motion generation is not as straightforward. Dedicated metrics evaluating both naturalness and diversity of generated sequences as well as the impact of new generated sequences in a classifi- cation task will be considered.
Prerequisites:
The candidate must fit the following requirements:
– Registered in Master 2 or last year of Engineering School (or equivalent) in Computer Science
– Advanced skills in Python programming are mandatory
– Good skills in Machine Learning & Deep Learning using related
libraries (scikit-learn, Tensorflow, Pytorch, etc.) are required
– Knowledge and/or a first experience in human motion analysis will be appreciated
Research environment:
The proposed internship will be carried out within the MSD (Modeling and Data Science) team from the IRIMAS Institute. It will be part of the ANR DELEGATION project starting in 2022 for 4 years. Hence, there is a great opportunity to continue with a PhD in our team on the same topic/project.
Application:

For further information or for applying, candidates should send a CV, academic records, personal projects (e.g. github repo) and a motivation letter to maxime.devanne@uha.fr.

21 Asynchronous Web e-Courses offered on Deep Learning, Computer Vision, Autonomous Systems, Signal/Image/Video Processing, Human-centered Computing, Social Media, Mathematical Foundations, CVML SW tools

October 14th, 2021 Daniela Lopez de Luise

Dear Computer Vision, Machine Learning, Autonomous Systems, DSP/DIP, Social Media Engineers, Scientists and Enthusiasts,

 

you are welcomed to register and attend one or more of the 21 CVML Web e-Course Modules on offer, each consisting of Lecture Series (208 lectures in total).

 

These asynchronous Web e-Course Modules (Lecture Series) provide an overview and in-depth presentation of 21 different domains:

 

  • Deep Learning and Neural Networks: Machine Learning (12 Lectures), Neural Networks/Deep Learning (14 Lectures), Advanced Deep Learning (7 Lectures)
  • Deep Learning and Computer Vision Foundations and Tools:  Mathematical Foundations (9 Lectures), SW Development and Programming Tools (3 Lectures)
  • Computer Vision/Image Processing and 3D Imaging:  Computer Vision  (12 Lectures), 2D Computer Vision/Image Analysis (8 Lectures), Image Processing (21 Lectures), Video Processing and Analysis (17 Lectures), 3D Imaging (9 Lectures), 3D Computer Graphics and Virtual Reality (5 Lectures)
  • Autonomous Systems: Autonomous Systems principles (8 Lectures), Robotics and Automatic Control  (3 Lectures), Autonomous Cars (8 Lectures), Autonomous Drones (15 Lectures), Autonomous Marine Systems (4 Lectures).
  • Human centered computing. Social Networks. Graph Theory: Human Centered Computing (15 Lectures), Network Theory. Social Media Analysis (10 Lectures).
  • Digital Signal Processing and Applications: Signal and Systems (11 Lectures), Digital Signal Processing and Analysis (7 Lectures), Medical Image and Signal Analysis (4 Lectures), Acoustics, Speech, Natural Language Processing and Analysis (4 Lectures), Communications           (2 Lectures).

 

You can combine CVML Web e-Course Modules to create CVML Web e-Courses (typically consisting of 16 lectures) of your own choice that cater your needs.

Each CVML Web e-Course you will create (16 lectures) provides you material that can cover a semester course, but you can master it in approximately 1 month.

Asynchronous tutor support will be provided in case of questions.

 

CVML Web e-Course Module materials typically consist of: a) a lecture pdf/ppt, b) lecture self-assessment understanding questionnaire and lecture video, programming exercises, tutorial exercises (for several modules/lectures)  and overall course module satisfaction questionnaire.

Course materials have been very successfully used in many top conference keynote speeches/tutorials worldwide and in short courses, summer schools, semester courses delivered by AIIA Lab physically or on-line from 2018 onwards, attracting many hundreds of registrants.

 

Course materials are at senior undergraduate/MSc level in a CS, CSE, EE or ECE or related Engineering or Science Department. Their structure, level and offer are completely different from what you can find in either Coursera or Udemy.

 

You can find sample Web e-Course Module material to make up your mind and/or can perform CVML Web e-Course registration in:

http://icarus.csd.auth.gr/cvml-web-lecture-series/

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

 

Academic/Research/Industry offer and arrangements

Special arrangements can be made to offer the material of these CVML Web e-Course Modules at University/Department/Company level:

  • by granting access to the material to University/research/industry lecturers to be used as an aid in their teaching,
  • by enabling class registration in CVML Web e-Courses
  • by delivering such live short courses physically or on-line by Prof. Ioannis Pitas
  • by combinations of the above.

 

The CVML Web e-Course is organized by Prof. I. Pitas, IEEE and EURASIP fellow, Coordinator of International AI Doctoral Academy (AIDA), past Chair of the IEEE SPS Autonomous Systems Initiative,

Director of the Artificial Intelligence and Information analysis Lab (AIIA Lab), Aristotle University of Thessaloniki, Greece, 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 34100+ citations to his work  and h-index 87+.

 

The informatics Department at AUTH ranked 106th internationally in the field of Computer Science for 2019 in the Leiden Ranking list

 

Relevant links:

  1. Prof. I. Pitas: https://scholar.google.gr/citations?user=lWmGADwAAAAJ&hl=el
  2. International AI Doctoral Academy (AIDA): https://www.i-aida.org/
  3. Horizon2020 EU funded R&D project Aerial-Core: https://aerial-core.eu/
  4. Horizon2020 EU funded R&D project Multidrone: https://multidrone.eu/
  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

Read More »
« Older Entries
Newer Entries »
Design by 2b Consult