Special Issue on “Trust through eXplAInability (XAI), Robustness and Verification of Autonomous Systems”

July 10th, 2024 Daniela Lopez de Luise
We are pleased to announce an extension to the call for papers for the Special Issue entitled “Trust through eXplAInability (XAI), Robustness and Verification of Autonomous Systems” of the IET Radar, Sonar & Navigation journal (IF 1.4, CS 4.1).

Submission deadline: Thursday, 1 August 2024
Expected Publication Month: March 2025
The large success of AI based solutions for autonomous systems applications has strongly impacted people’s minds to get prepared and ready for the use of these systems in our daily life.
Indeed, the booming development of machine learning techniques and their embeddings in suitable, small size computation hardware has made some unrealistic applications of autonomous systems just few years back the reality of today. To effectively adopt those intelligent autonomous systems solutions, the end users need to feel safe in engaging with those machines through the level of trust, under different conditions of operations, they have in the outputs of those solutions.
Interpreting the autonomous systems, and more specifically, autonomous vehicles’ decisions through the explainability of the machine learning techniques composing their solutions is key. The other way to secure the adoption of those techniques onboard autonomous vehicles is to go through rigorous model verification and robustness processes including dealing with anomalies and adversarial attacks.
The focus of this Special Issue is on modern XAI, Robustness and Verification of AI based autonomous vehicles’ decision making in terms of planning, navigation and guidance. Quantum software stacks and libraries facilitate the link from a high-level description of algorithms to a low-level implementation with quantum gates, for solving concrete problems and applications expected to demonstrate quantum advantage.
Topics for this call for papers include but not restricted to:
  • XAI for autonomous vehicle planning and guidance
  • Validation and Verification (V&V) of AI based solution for autonomous vehicle navigation
  • Pruning of deep learning solutions for autonomous vehicles application
  • Embedding of safe deep learning solutions for autonomous vehicles
  • Robustness of the AI based autonomous vehicle’s navigation and guidance through anomaly detection
  • Robustness of the AI based autonomous vehicle’s navigation and guidance through adversarial attacks
Guest Editors:
Nabil Aouf
University of London
United Kingdom
Xiaowei Huang
University of Liverpool
United Kingdom
Abdelhafid Zenati
University of London
United Kingdom
Daniele De Martini
University of Oxford
United Kingdom

Read More »

WYN workshop @ ECCV2024 deadline extension

July 10th, 2024 Daniela Lopez de Luise

1st Workshop on Trustworthiness in Computer Vision “TWYN: Trust What You learN''

ECCV 2024, Sun Sep 29th through Fri Oct 4th, 2024 at MiCo Milano

website: https://www.twyn.unimore.it/

Submission website: https://cmt3.research.microsoft.com/TWYN2024/

Scope:

In an era of rapid advancements in Artificial Intelligence, the imperative to foster Trustworthy AI has never been more critical. The first “Trust What You learN (TWYN)'' workshop seeks to create a dynamic forum for researchers, practitioners, and industry experts to explore and advance the intersection of Trustworthy AI and DeepFake Analysis within the realm of Computer Vision. The workshop aims to delve into the multifaceted dimensions of building AI systems that are not only technically proficient but also ethical, transparent, and accountable. The dual focus on Trustworthy AI and DeepFake Analysis reflects the workshop's commitment to addressing the challenges posed by the proliferation of deep fake technologies while simultaneously promoting responsible AI practices. The workshop will include several talks presented by recognized and important scientists in these 2 fields. Explore the detailed information about our workshop structure, esteemed confirmed speakers, and what to expect on the website of the workshop.

 
Tracks:

Track 1: From Learning to Unlearning: The Role of Privacy in Computer Vision – Dive into privacy-centric topics like differential privacy, privacy attacks, Machine Unlearning and more!

Differential privacy
Statistical and information-theoretic notions of privacy
Privacy-preserving data sharing, anonymization, privacy of synthetic data and distillation
Privacy attacks
Federated and decentralized privacy-preserving algorithms
Privacy and bias correction in generative models
Privacy in autonomous systems
Privacy and private learning in computer vision and natural language processing tasks
Relations of privacy with fairness, transparency and adversarial robustness
Machine unlearning and data-deletion
Privacy-preserving continual learning systems

Track 2: DeepFake Analysis and Detection – Address the challenges of deep-fake technologies with approaches for detection and evaluation.

Approaches for fake image detection, relying on both low-level, hand-crafted features or learnable and semantic approaches
Partially-altered fake image detection
GAN and Diffusion-based techniques with safety reassurance for image and video synthesis and generation
Video Deepfake detection and multimodal approaches to deep-fake detection
Approaches for detecting generated text and fake news, also based on multimodal analysis
Approaches and techniques for explainable deep-fake detection
Evaluation metrics for deep-fake generation and detection systems 

Confirmed Keynote Speakers:

– Dimosthenis Karatzas

– Reza Shokri

– Stefano Soatto

– Rita Cucchiara

– Luisa Verdoliva

 

Paper submissions:

Paper submission instructions are available at https://www.twyn.unimore.it/call-for-papers/. Accepted papers will be presented at the workshop posters session and included in the proceedings. The submission deadline has been postponed from  the 10th to the 19th  2024 of July. Don't miss out on this opportunity to contribute to the discussion!

Dates:

Paper Submission Deadline: July 10 July 19, 2024 AoE
Supplementary Material Deadline: 10 July 19 July, 2024 AoE

Decision to Authors:  August 01 August 10, 2024
Camera ready papers due: August, 20, 2024
Workshop date: 30 September, 2024
Submission Website: https://cmt3.research.microsoft.com/TWYN2024/

Organizers:

– Marco Cotogni
– Luigi Sabetta, Leonardo Spa
– Jacopo Bonato, Leonardo Spa
– Sara Sarto, UniMoRe
– Samuele Poppi, UniMoRe
– Lorenzo Baraldi, UniMoRe

Read More »

Workshop on Neuromorphic Vision @ European Conference on Computer Vision 2024

July 10th, 2024 Daniela Lopez de Luise

ECCV 2024 Advances in Image Manipulation (AIM) workshop and challenges

July 10th, 2024 Daniela Lopez de Luise
CALL FOR PAPERS  & CALL FOR PARTICIPANTS IN 9 CHALLENGES
AIM: 5th Advances in Image Manipulation workshop and challenges on 
video super-resolution, depth upsampling, raw alignment and learned ISP, sparse neural rendering, video saliency prediction, image and video quality assessment,

In conjunction with ECCV 2024, Milano, Italy

Website: https://www.cvlai.net/aim/2024/
Contact: radu.timofte@uni-wuerzburg.de

TOPICS

Papers addressing topics related to image/video manipulation, restoration and enhancement are invited. The topics include, but are not limited to:

● Image-to-image translation
● Video-to-video translation
● Image/video manipulation
● Perceptual manipulation
● Image/video generation and hallucination
● Image/video quality assessment
● Image/video semantic segmentation
● Saliency and gaze estimation
● Perceptual enhancement
● Multimodal translation
● Depth estimation
● Image/video inpainting
● Image/video deblurring
● Image/video denoising
● Image/video upsampling and super-resolution
● Image/video filtering
● Image/video de-hazing, de-raining, de-snowing, etc.
● Demosaicing
● Image/video compression
● Removal of artifacts, shadows, glare and reflections, etc.
● Image/video enhancement: brightening, color adjustment, sharpening, etc.
● Style transfer
● Hyperspectral imaging
● Underwater imaging
● Aerial and satellite imaging
● Methods robust to changing weather conditions / adverse outdoor conditions
● Image/video manipulation on mobile devices
● Image/video restoration and enhancement on mobile devices
● Studies and applications of the above.

SUBMISSION

A paper submission has to be in English, in pdf format, and at most 14 pages (excluding references) in single-column, ECCV style. The paper format must follow the same guidelines as for all ECCV 2024 submissions.
The review process is double blind.
Dual submission is not allowed.
Submission site: https://cmt3.research.microsoft.com/AIMWC2024/

WORKSHOP DATES

● Submission Deadline: July 17, 2024
● Decisions: August 7, 2024
● Camera Ready Deadline: August 14, 2024

AIM 2024 has the following associated challenges (ONGOING!):
● Mobile Real-Time Video Super-Resolution
● Efficient Video Super-Resolution
● Depth Upsampling and Refinement
● RAW Burst Alignment and ISP ongoing
● Sparse Neural Rendering – Track 1 – 3 views
● Sparse Neural Rendering – Track 2 – 9 views
● Video Saliency Prediction
● Video Super-Resolution Quality Assessment
● Compressed Video Quality Assessment
● Pushing the Boundaries of Blind Photo Quality Assessment

PARTICIPATION

To learn more about the challenges and to participate:

CHALLENGES DATES

● Release of train data: May, 2024
● Competitions end: July 19, 2024

Read More »

1st Workshop on Trustworthiness in Computer Vision “TWYN: Trust What You learN”

July 10th, 2024 Daniela Lopez de Luise
1st Workshop on Trustworthiness in Computer Vision “TWYN: Trust What You learN”
ECCV 2024, Sun Sep 29th through Fri Oct 4th, 2024 at MiCo Milano

Scope:
In an era of rapid advancements in Artificial Intelligence, the imperative to foster Trustworthy AI has never been more critical. The first “Trust What You learN (TWYN)'' workshop seeks to create a dynamic forum for researchers, practitioners, and industry experts to explore and advance the intersection of Trustworthy AI and DeepFake Analysis within the realm of Computer Vision. The workshop aims to delve into the multifaceted dimensions of building AI systems that are not only technically proficient but also ethical, transparent, and accountable. The dual focus on Trustworthy AI and DeepFake Analysis reflects the workshop's commitment to addressing the challenges posed by the proliferation of deep fake technologies while simultaneously promoting responsible AI practices. The workshop will include several talks presented by recognized and important scientists in these 2 fields. Explore the detailed information about our workshop structure, esteemed confirmed speakers, and what to expect on the website of the workshop.

 
Tracks:
Track 1: From Learning to Unlearning: The Role of Privacy in Computer Vision – Dive into privacy-centric topics like differential privacy, privacy attacks, Machine Unlearning and more!
Differential privacy
Statistical and information-theoretic notions of privacy
Privacy-preserving data sharing, anonymization, privacy of synthetic data and distillation
Privacy attacks
Federated and decentralized privacy-preserving algorithms
Privacy and bias correction in generative models
Privacy in autonomous systems
Privacy and private learning in computer vision and natural language processing tasks
Relations of privacy with fairness, transparency and adversarial robustness
Machine unlearning and data-deletion
Privacy-preserving continual learning systems

Track 2: DeepFake Analysis and Detection – Address the challenges of deep-fake technologies with approaches for detection and evaluation.
Approaches for fake image detection, relying on both low-level, hand-crafted features or learnable and semantic approaches
Partially-altered fake image detection
GAN and Diffusion-based techniques with safety reassurance for image and video synthesis and generation
Video Deepfake detection and multimodal approaches to deep-fake detection
Approaches for detecting generated text and fake news, also based on multimodal analysis
Approaches and techniques for explainable deep-fake detection
Evaluation metrics for deep-fake generation and detection systems

Confirmed Keynote Speakers:
– Dimosthenis Karatzas
– Reza Shokri
– Stefano Soatto
– Rita Cucchiara
– Luisa Verdoliva
– Cristian Canton Ferrer

Paper submissions:
Paper submission instructions are available at https://www.twyn.unimore.it/call-for-papers/. Accepted papers will be presented at the workshop posters session and included in the proceedings. The submission deadline has been postponed from  the 10th to the 19th  2024 of July. Don't miss out on this opportunity to contribute to the discussion!

Dates:
Paper Submission Deadline: July 10 July 19, 2024 AoE
Supplementary Material Deadline: 10 July 19 July, 2024 AoE

Decision to Authors:  August 01 August 10, 2024
Camera ready papers due: August, 20, 2024
Workshop date: 30 September, 2024
Submission Website: https://cmt3.research.microsoft.com/TWYN2024/

Organizers:
– Marco Cotogni, Leonardo Spa
– Luigi Sabetta, Leonardo Spa
– Jacopo Bonato, Leonardo Spa
– Sara Sarto, UniMoRe
– Samuele Poppi, UniMoRe
– Lorenzo Baraldi, UniMoRe

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