Special Sessions

Recent Advances in Immersive Imaging Technologies

Handling the sheer amount of data in all processing steps of light field imaging, 360-video and volumetric video from capture to display is a major challenge. Especially, the streaming of the data to the audiences in high quality is still an unsolved problem. Furthermore, technical limitations of the capture devices, like incorrect 3D-to-2D mapping and optical distortions in omnidirectional image acquisition, optical distortions or low spatial and angular resolution of light field images as well as segmentation or time-consistent 3D reconstruction in dynamic volumetric video reduce the quality of experience on the consumer side. On the other hand, the interest of the industry in AR/VR applications and immersive imaging solutions for consumers is growing. Together with the growing interest, immersive imaging technologies have become a hot research topic for the scientific community.

The special session is dedicated to recent advances in immersive imaging technologies, in particular in (but not limited to):

  • Capturing, processing and rendering of light fields, 360° content and/or volumetric video
  • Coding and streaming of light fields, 360° content and/or volumetric video
  • Visual attention / saliency in light fields, 360° content and/or volumetric video
  • Quality metrics in light fields, 360° content and/or volumetric video

Organizers: Martin Alain (alainm@tcd.ie), Cagri Ozcinar (cagriozcinar@gmail.com), Emin Zerman (zermane@tcd.ie), Sebastian Knorr (sebastian.knorr@eah-jena.de).

Deepfake Video Generation and Detection

The word deepfake comes from “deep learning” and “fake”. Roughly, it refers to a video, an image or an audio recording in which the protagonist’s identity or lyrics have been modified to mimic the protagonist’s identity or lyrics from a source video, or even completely generated from scratch. Recent advances in deep learning, including variational auto-encoders and generative adversarial networks (GAN), have enabled the generation of high-quality fake videos and audio. This situation raises many security issues in society, especially when celebrities and politicians are targeted, and their fake videos are widely shared on social networks. Many deepfake detection solutions relying on both handcrafted and deep learning techniques have been proposed in the literature. For instance, some deepfake detection methods rely on visual artifacts, physiological inconsistencies of features space where fake and real videos are well characterized. The race between deepfake generation and detection is still in play to develop more efficient generation and detection solutions. The aim of this cross-disciplinary special session is to bring together industry researchers as well as academics working on deepfake generation and detection from different communities including machine learning, computer vision, image processing, multimedia security and biometric.

Topics of interest in this special session include the following topics (but are not limited to):

  • Generation of DeepFakes and face manipulation
  • Generation of synthetic faces including GAN based solutions
  • Detection of DeepFakes with hand-crafted solutions and deep learning-based solutions
  • Construction methodology of Deepfake datasets and detection benchmark
  • Resilience of Deepfake detection solution against adversarial attacks

Organizers: Wassim Hamidouche (whamidou@insa-rennes.fr), Sid Ahmed Fezza (sfezza@inttic.dz), Abdenour Hadid (abdenour.hadid@ieee.org).

Conducting multimedia users studies during COVID-19 pandemic

The Covid-19 pandemic has affected the world and society severely. Several restrictions are imposed on businesses, private life and social behavior in order to minimize the spread of the disease. It has also affected particularly research communities that perform experimental evaluations with humans. The most common approach has involved laboratory experiments with people coming to a controlled laboratory. The pandemic has made this approach considerably more challenging if the experiments are to be carried out safely considering researchers and participants. Alternative approaches to bringing people to a dedicated lab do exist e.g. crowdsourcing. Research communities have had to quickly adapt their approaches, and the scope of this special session is to solicit submissions of research works which have conducted user studies during the COVID-19 pandemic.

This special session therefore aims to raise this issue by inviting in particular work, empirical studies and contributions:

  • Novel approaches to addressing the difficulty of doing (in lab) experiments safely considering the risks of a contagious virus. Such works could include guidelines for safe experimental executions in such conditions for example
  • Works that have validated or compared experimental results from in lab experiments with “in the wild” experiments
  • Alternate and innovative methodologies to traditional experimental approaches
  • Hybrid experimental approaches in scenarios where there are partial population vaccinations
  • Works that have employed novel methods to deal with special hardware needs (big /special displays, VR headsets, eye-tracking, electrophysiology, etc.)
  • Ethical considerations for executing tests in context of user tests during a pandemic

The range of papers submitted to this special session can include full experimental results, to position papers or new protocols or platforms.

Organizers: Niall Murray (nmurray@research.ait.ie), Kjell Brunnström (kjell.brunnstrom@ri.se), Matthieu Perreira Da Silva (matthieu.perreiradasilva@univ-nantes.fr).