We are really happy to announce the 8th International Workshop on Multimedia Assisted Dietary Management (MADiMa2023) in conjunction with the 31st ACM International Conference in Multimedia (ACMM2023).
The workshop will take place between October 29th-November 3rd, 2023, in Ottawa, Canada. Below, you can find the 1st call for papers. More details are available at our website (www.madima.org).
We are truly looking forward to your participation.
Best regards and see you in Ottawa,
Stavroula Mougiakakou
Keiji Yanai
Dario Allegra
===================================================
===================================================
Call For Papers (apologies for multiple copies)
===================================================
The 8th International Workshop on Multimedia Assisted Dietary Management (MADiMa2023) is organized in conjunction with the 31st ACM International Conference in Multimedia (ACMM2023).
Website: www.madima.org
Place: Ottawa, Canada
Date: October 29th-November 3rd, 2023
Submission Deadline: 21st July 2023
RATIONALE
=========
The prevention of onset and progression of diet-related acute and chronic diseases requires reliable and intuitive dietary management. The need for accurate, automatic, real-time, and personalized dietary advice has been recently complemented by the advances in AI, computer vision, wearable, and smartphone technologies, permitting the development of the first mobile food multimedia content analysis applications. The proposed solutions rely on the analysis of multimedia content captured by wearable sensors, smartphone cameras, barcode scanners, RFID readers and IR sensors, along with already established nutritional and recipe databases and often require some user input. In the field of nutritional management, multimedia not only bridges diverse information and communication technologies, but also computer science with medicine, nutrition, and dietetics. This confluence brings new challenges and opportunities on dietary monitoring, assessment, and management.
SCOPE
=====
The main scope of MADiMa2023 is to bring together researchers from the diverse fields of engineering, computer science and nutrition who investigate the use of information and communication technologies for better monitoring, assessment, and management of food intake. The combined use of multimedia, machine learning algorithms, ubiquitous computing and mobile technologies permits the development of applications and systems able to monitor the dietary behavior, analyze food intake, identify eating patterns, and provide feedback to the user towards healthier nutrition. The researchers will present and demonstrate their latest progress and discuss novel ideas in the field. Besides the technologies used, emphasis will be given to the precise problem definition, the available nutritional databases, the need for benchmarking multimedia databases of packed and unpacked food and the evaluation protocols.
TOPICS
======
Topics of interest include (but are not limited to) the following:
– Ubiquitous and mobile computing for dietary assessment
– Computer vision for food detection, segmentation, and recognition
– Deep learning for food analysis
– 3D reconstruction for food portion estimation
– Augmented reality for food portion estimation
– Wearable sensors for food intake detection
– Computerized food composition (nutrients, allergens) analysis
– Multimedia technologies for eating monitoring
– Food image analysis and social media
– Smartphone technologies for dietary behavioral patterns
– Food multimedia databases
– Evaluation protocols of dietary management systems
– Multimedia assisted self-management of health and disease
– ICT technologies for tackling mal- and undernutrition
– Dietary monitoring systems for Low- and Middle-Income Country (LMIC) settings
– Vision techniques for food quality check
– ICT for personalization of dietary advice
– Personalized dietary recommendation systems
IMPORTANT DATES
================
– Paper submission deadline: July 21st, 2023
– Notification of acceptance: July 8th, 2023
– Camera ready deadline: August 12th, 2023
WORKSHOP CHAIRS
=================
– Stavroula Mougiakakou, University of Bern, Switzerland
– Keiji Yanai, The University of Electro-Communications, Tokyo, Japan
– Dario Allegra, University of Catania, Italy
PROGRAMME COMMITTEE
=====================================
– Lorenzo Brigato, University of Bern, Switzerland
– Lorenzo Catania, University of Catania, Italy
– Jingjing Chen, Fudan University, Shanghai
– Christos Diou, Harokopio University of Athens, Greece
– Ichiro Ide, Nagoya University, Japan
– Ioannis Papathanail, University of Bern, Switzerland
– Raimondo Schettini, University of Milan-Bicocca, Italy
– Yoko Yamakata, University of Tokyo, Japan
For more information, please visit the workshop's website at www.madima.org.
The workshop chairs,
Stavroula Mougiakakou
Keiji Yanai
Dario Allegra
QCAV’2023 – 16th International Conference on Quality Control by Artificial Vision
May 4th, 2023 
Daniela Lopez de Luise Dear colleagues,
Preliminary program of the QCAV'2023 – 16th International Conference on Quality Control by Artificial Vision (Albi, France, 6-8 June 2023) has been published on the conference website:
https://qcav2023.sciencesconf.org/resource/page/id/14
Registration is open until the 22nd of May.
Kind regards,
ICCV 2023: Event Detection for Situation Awareness in Autonomous Driving
May 4th, 2023 Daniela Lopez de Luise https://lnkd.in/ehg3nP5C
The #workshop aims to bring together researchers and practitioners in the field of #autonomousdriving to present and discuss recent advances in event detection for #situationalawareness.
The focus of the event is a ground-breaking competition centered on the detection of road events (triplets formed by #agent, action and location) in a challenging domain adaptation environment.
The challenge will leverage our new ROAD++ benchmark which scales up the road event annotation originally developed for the ROAD #dataset (https://lnkd.in/gsBU5wU) to the Waymo dataset (https://waymo.com/open/), with prizes for the top three entries.
For the paper track we welcome papers reporting original research, case studies, or work-in-progress papers related to the theme of the workshop.
We will award a best paper and a best student paper prize, host spotlight presentations and hold poster sessions for all accepted papers.
Topics of interest include, but are not limited to:
– Detection and modelling of 'atomic' road events.
– Detection and modelling of complex road activities, involving several agents over an extended period of time.
– Agent intention #prediction .
– Prediction of the trajectory of pedestrians and vehicles.
– Forecast of future road events.
– Multi-agent modelling of road scenes.
– Realistic simulation for training of perceptual models.
– Generative #AI for situation awareness.
– Fusion of multi-sensor data for situation awareness.
– Machine theory of mind.
– Continual learning from video streams.
– Domain adaptation.
– Datasets and evaluation metrics and datasets for situation awareness in #autonomousvehicles.
Papers are to be submitted using the ICCV template via CMT. The Workshop will allow for the submission of papers concurrently submitted elsewhere, with the aim of aggregating all relevant efforts in this area.
The workshop will host invited speakers of the calibre of Marco Pavone (Stanford), Holger Caesar (TU Delft), Bernard Ghanem (KAUST), Xinshuo Weng (NVIDIA), Raim Al-Rfou and Yin Zhou (Waymo).
Workshop timeframe:
· Submission site open: May 2
· Paper Submission: July 2
· Acceptance: Aug 7
· Camera-ready: Aug 17
Challenge timeframe:
· Registration open: April 24
· Training and validation data: May 2
· Test data: July 15
· Submission deadline: Aug 5
· Results: Aug 10
Organisers:
Fabio Cuzzolin, Andrew Bradley, Salman Khan, Izzeddin Teeti (Oxford Brookes University)
Gurkirt singh (ETH Zurich)
Eleonora Giunchiglia (TU Wien)
Mihaela Catalina Stoian (University of Oxford)
Reza Javanmard Alitappeh (Mazandaran University)
XR&AI 2023 – 2nd International Summer School on eXtended Reality and Artificial Intelligence, July 17-22, 2023 – Matera, Italy
May 4th, 2023 Daniela Lopez de Luise XR&AI – eXtended Reality and Artificial Intelligence – 2nd International Summer School – call for application
Matera, Italy, 17-22 July 2023
LOCATION:
Casa delle Tecnologie Emergenti, Via S. Rocco, 1 Matera
MOTIVATION AND DESCRIPTION:
eXtended Reality (XR) is an emerging umbrella term for all the immersive technologies (Virtual Reality, Augmented Reality, and Mixed Reality) able to extend the user senses by blending the virtual and real worlds and creating a fully immersive experience.
Artificial Intelligence (AI) is a broad area of computer science that makes machines seem like they have human intelligence. The goal of AI is to mimic the human brain and create systems that can function intelligently and independently.
AI can enhance XR applications significantly in several ways and the XR&AI Summer School is focused on the synergy of these technologies for applications in cultural and territorial heritage, medicine and industry.
This summer school is suitable for PhD students, post-docs, Masters students, and academic staff, as well as participants from industry who wish to improve their skills in these fields.
PROGRAMME:
The programme of this second edition of the school includes theoretical and practical lectures. Both types of lectures are aimed at the development of a project by groups of participants, with the results presented on the last day, and whose main objective is the use of AI tools to improve the development of XR applications in order to reduce the time and effort required to create resources while maintaining a high quality of output. For example, participants will use machine learning algorithms, including deep learning and convolutional neural networks, to generate high-quality assets such as 3D models, textures, animations and sound effects based on user input.
In addition, on the morning of the first day, participants can participate in a 4-hour introductory and levelling tutorial on the tools and technologies used during the school.
SPEAKERS OF THEORETICAL LECTURES (confirmed):
Rita Cucchiara, University of Modena and Reggio Emilia, Italy:
Generative AI: from image to text and return
Joaquim Jorge, University of Lisboa, Portugal:
Challenges and Opportunities for AI&XR in Health Applications
Andrea Bottino, Dipartimento di Automatica e Informatica, Politecnico di Torino, Italy:
AI for procedure learning in XR
Joseph L. Gabbard, Virginia Tech, USA:
Implications of AI for next-generation AR user interfaces
REGISTRATION:
The registration deadline for XR&AI 2023 is 1 July 2023, with the following fee options:
Early bird registration: € 550,00 (until 31 May 2023)
Regular registration: € 600,00 (from 1 June 2023)
The XR&AI Summer School 2023 registration fee includes lectures, WiFi internet connection, daily lunches and coffee breaks as well as the pizza party and the guided visit of the town. The registration fee does not include the accommodation costs.
MORE INFORMATION:
Registration is open (registration)
For additional information regarding the detailed program of theoretical and practical lectures, venue, recommended accommodations and travels, etc., please visit the school's website or send us an e-mail.
***************************************
Prof. Primo Zingaretti
Full Professor of Computer Engineering
Università Politecnica delle Marche
Dipartimento di Ingegneria dell'Informazione
Via brecce bianche, 60131 Ancona Italy
Tel. +39 071 220 4899
e-mail p.zingaretti@staff.univpm.it
***************************************
CALL FOR PAPERS,,16th International Symposium on Multimedia Applications and Processing (MMAP’23); May 23 deadline; Web of Science; IEEE: #57573
May 4th, 2023 Daniela Lopez de Luise (MMAP’23)
Warsaw, Poland, 17–20 September, 2023
https://fedcsis.org/sessions/css/mmap
Organized within FedCSIS 2023 (IEEE: #57573)
Strict submission deadline: May 23, 2023, 23:59:59 AOE (no extensions)
KEY FACTS: Proceedings: submitted to IEEE Digital Library; indexing:
DBLP, Scopus and Web of Science; 70 punktów parametrycznych MEiN
Please feel free to forward this announcement to your colleagues and
associates who could be interested in it.
********************* Statement concerning LLMs *********************
Recognizing developing issue that affects all academic disciplines, we
would like to state that, in principle, papers that include text
generated from a large-scale language model (LLM) are prohibited, unless
the produced text is used within the experimental part of the work.
*********************************************************************
Background and goals
Multimedia, computer vision, graphics, and machine learning have become
ubiquitous in modern information systems, creating new challenges for
detection, recognition, indexing, access, search, retrieval, automated
understanding, and processing, resulting in many applications based on
image and signal processing, machine learning and various multimedia
technologies.
Recent advances in pervasive computers, networks, telecommunications,
and information technology, along with the proliferation of multimedia
mobile devices, have stimulated the rapid development of intelligent
applications. These key technologies, using virtual reality, augmented
reality, and computational intelligence, are creating a recent
multimedia revolution that will significantly impact a broad spectrum of
consumer, business, healthcare, educational and governmental domains.
Advancements in artificial intelligence resulted in the rapid growth of
both methods and applications of machine learning approaches in computer
vision, image processing, and analysis. The development of parallel
computing capabilities in the first decade of the 21st century that
boosted the development of deep neural networks became a real
game-changer in machine vision. The workshop covers a range of AI-based
theories, methods, algorithms, technologies, and systems for diversified
and heterogeneous digital multimedia, imaging, computer graphics and
machine learning areas.
The Multimedia Applications and Processing (MMAP) will provide an
opportunity for researchers and professionals to discuss present and
future challenges and potential collaboration for future progress in
these fields. The MMAP Symposium welcomes submissions of original papers
concerning all aspects of multimedia, vision, and graphics, ranging from
concepts and theoretical developments to advanced technologies and
innovative applications. MMAP invites original, previously unpublished
contributions that are not submitted concurrently to a journal or
another conference. We welcome papers covering innovative applications,
practical usage, and theoretical aspects of the abovementioned trends.
Papers acceptance and publication will be judged based on their
relevance to the symposium theme, clarity of presentation, originality,
and accuracy of results and proposed solutions.
Topics
Topics of interest are related (but are not limited) to the following areas:
– multimedia processing:
+ audio, image and video joint processing,
+ cloud computing and multimedia applications,
+ multimedia file systems and databases: indexing,
recognition and retrieval,
+ multimedia in internet and web-based systems,
+ human computer interaction, interfaces and multimedia,
+ distributed multimedia systems,
+ network and operating system support for multimedia,
+ machine learning for mobile network architectures,
+ trends in multimedia information processing,
+ multimedia ontology and perception for multimedia users,
– machine vision, image processing and analysis:
+ image enhancement,
+ linear and non-linear filtering,
+ object detection and segmentation,
+ shape analysis,
+ scene understanding, analysis and modeling
+ image acquisition,
+ stereo and multispectral imaging,
+ embedded vision,
+ robotic vision,
+ image models and transforms,
+ modeling of human visual perception,
+ visual knowledge representation and reasoning,
– visualization and computer graphics:
+ computational geometry,
+ data-driven image synthesis,
+ graphical data presentation,
+ computer-aided graphic arts and animation,
+ virtual and augmented reality,
+ entertainment, personalized systems and games,
– machine learning for multimedia, vision and graphics:
+ pattern recognition,
+ deep neural models,
+ convolutional networks,
+ recurrent networks,
+ graph networks,
+ generative adversarial networks,
+ neural style transfer,
+ deep reinforcement learning,
+ big data and multimedia systems,
+ machine learning and computational intelligence for
information retrieval in multimedia sustems,
+ data mining, warehousing and knowledge extraction,
– applications:
+ innovative uses of graphic and vision systems,
+ image retrieval,
+ autonomous driving systems,
+ remote sensing,
+ digital microscopy,
+ security and surveyance systems,
+ document analysis,
+ OCR systems,
+ medical applications and computational biology,
+ security in multimedia applications: authentication and
watermarking,
+ e-learning, e-commerce and e-society applications,
+ intelligent multimedia network applications,
+ future trends in multimedia systems technologies and
applications.
Best Paper Award
A best paper award will be made for work of high quality presented at
the MMAP Symposium. Award comprises a certificate for the authors and
will be announced on time of conference. Selected papers will be invited
to high IF journals organized for the participants of MMAP.
Submission rules:
– Authors should submit their papers as Postscript, PDF or MSWord files.
– The total length of a paper should not exceed 10 pages IEEE style
(including tables, figures and references). IEEE style templates are
available here.
– Papers will be refereed and accepted on the basis of their
scientific merit and relevance to the workshop.
– Preprints containing accepted papers will be published on a USB
memory stick provided to the FedCSIS participants.
– Only papers presented at the conference will be published in
Conference Proceedings and submitted for inclusion in the IEEE Xplore®
database.
– Conference proceedings will be published in a volume with ISBN,
ISSN and DOI numbers and posted at the conference WWW site.
– Conference proceedings will be submitted for indexation according
to information here.
– Organizers reserve right to move accepted papers between FedCSIS
technical sessions.
Important dates:
+ Paper submission (strict deadline): May 23, 2023, 23:59:59 (AoE; there
will be no extension)
+ Position paper submission: June 7, 2023
+ Author notification: July 11, 2023
+ Final paper submission and registration: July 31, 2023
+ Payment (early fee deadline): July 26, 2023
MMAP Committee: https://fedcsis.org/sessions/css/mmap/committee