EUVIP 2023 Special session: “AI in the City: Efficient, Scalable and Privacy-Preserving Visual Scene Understanding in Man-Made Environments.”
www.euvip2023.org/index.php/technical-program/special-sessions/

11th European Workshop on Visual Information Processing (EUVIP)
September 11-14, 2023, Gjøvik, Norway.
www.euvip2023.org

Contacts: amine.bourki@viziosense.com and mohib.ullah@ntnu.no

                                                                                                                                                                                                                                        

Dear Colleague,

We are pleased to invite you to submit papers to our special session titled “AI in the City: Efficient, Scalable and Privacy-Preserving Visual Scene Understanding in Man-Made Environments” at the 11th European Workshop on Visual Information Processing (EUVIP). The event will take place on 11th-14th September 2023 in Gjøvik, Norway.

The workshop will bring together leading experts from academia and industry interested in visual information processing, applications and performance assessment for all types of visual modalities. The program will feature lecture, poster and plenary sessions, as well as special sessions and tutorials.

Please find the details of our special session below:

Title: “AI in the City: Efficient, Scalable and Privacy-Preserving Visual Scene Understanding in Man-Made Environments.”

Organizers:
Amine Bourki, VizioSense AI Lab, Paris, France
Mohib Ullah, NTNU, Gjøvik, Norway

Abstract- Man-made environments such as buildings and cities are typically characterized by their large scale, dynamic nature and the dense population of objects and people they contain. With the recent significant advances in Visual AI and the democratization of massive visual information that enable autonomous systems, surveillance applications, and real-time data acquisition from indoor-or outdoor man-made scenes, the processing of such visual information requires a specific attention to several aspects. These include robustness, data- and computation efficiency, scalability, as well as addressing the ethical concerns associated with individual privacy which can be compromised through direct (e.g., facial recognition), or indirect (e.g., vehicle plate recognition) identification methods. This special session aims to encourage novel contributions in the field of visual scene understanding, with an emphasis on addressing the challenges related to robustness, scalability and privacy in the realm of large, dynamic and densely populated scenes such as cities and buildings.

Topics of interest include, but are not limited to:
● Scene understanding:

○ Semantic, instance level and panoptic segmentation,
○ Object detection,
○ Joint geometric-semantic reasoning,
○ 3D from multi-view and sensors,
○ Efficient and scalable vision,
○ Segmentation and shape analysis,
○ Perceptual grouping and counting,
○ Crowd analysis,
○ Behavior analysis,
○ Multi-modality, RGB-D and point clouds,
○ Drones and autonomous vehicles.

● Dynamic environments:

○ Multi-Object Tracking (MOT),
○ Person and object re-IDentification (re-ID),
○ Multi-Camera, Multi-Object Tracking (MC-MOT),
○ Real-time acquisition and processing,
○ Object pose estimation.

● Privacy, Edge AI and social impact:

○ Privacy-by-design in visual processing systems,
○ Embedded and video surveillance systems,
○ Deep Learning for compute-constrained and low-power devices,
○ Power efficient Deep Learning and Green AI,
○ Ethics, fairness and explainability in Visual AI.

● Research reproducibility:

○ Datasets and evaluation.

Important dates:

Both comments and pings are currently closed.