Full Technical Program

Download Full Technical Program

Sunday, 11th September

9:30

Tutorial 1 (Part 1)

“Signal Processing Methods for Light Field Displays“
by Erdem Sahin (Tampere University, Finland), Robert Bregovic (Tampere University, Finland), Atanas Gotchev (Tampere University, Finland)

11:00

Coffee Break

11:20

Tutorial 1 (Part 2)

“Signal Processing Methods for Light Field Displays“
by Erdem Sahin (Tampere University, Finland), Robert Bregovic (Tampere University, Finland), Atanas Gotchev (Tampere University, Finland)

12:50

Lunch

14:30

Tutorial 2 (Part 1)

“Deep Learning for Image and Video Compression“
by Murat Tekalp (Koç University, Turkey)

16:00

Coffee Break

16:20

Tutorial 2 (Part 2)

“Deep Learning for Image and Video Compression“
by Murat Tekalp (Koç University, Turkey)

17:50

End of the Tutorial Day

Monday, 12th September

8:45

Opening Session
Fernando Pereira (Instituto Superior Técnico – Instituto de Telecomunicações, Portugal), EUVIP 2022 General Chair

9:00

Keynote Talk 1

Chair: Elena Alshina (Huawei, Germany)

“Image Denoising – Not What You Think“
by Michael Elad (Technion – Israel Institute of Technology, Israel)

10:00

Special Session 1 (Oral)

Chair: Ruxandra Tapu (Institute Mines-Telecom, Telecom SudParis / University Politehnica of Bucharest)

Current Standardization Activities on Dynamic Mesh Compression

  1. Award candidate: Compression of Time-Varying Textured Meshes using Patch Tiling and Image-based Tracking, Jean-Eudes Marvie (InterDigital)*; Maja Krivokuca (InterDigital); Celine Guede (InterDigital); Julien Ricard (InterDigital); Olivier Mocquard (InterDigital); Francois-Louis Tariolle (InterDigital)
  2. V3C-based Coding of Dynamic Meshes, Patrice Rondao Alface (Nokia Technologies)*; Aleksei Martemianov (Nokia Technologies); Lauri Ilola (Nokia Technologies); Lukasz Kondrad (Nokia Technologies); Christoph Bachhuber (Nokia Technologies); Sebastian Schwarz (Nokia Technologies)
  3. Award candidate: Video and Subdivision based Mesh Coding, Khaled Mammou (Apple, Inc.)*; Jungsun Kim (Apple, Inc.); Alexis Tourapis (“Apple, Inc.”); Dimitri Podborski (Apple, Inc.); David Flynn (Apple, Inc.)
  4. Award candidate: Formal Visual Evaluation and Study of Objective Metrics for MPEG Dynamic Mesh Coding, Mathias Wien (RWTH Aachen University)*; Joel Jung (Tencent Media Lab); Vittorio Baroncini (GBTech)

11:20

Coffee Break

11:40

Oral Session 1

Chair: Mathias Wien (RWTH Aachen University)

Image and Video Coding

  1. Award candidate: Ensemble Learning for Efficient VVC Bitrate Ladder Prediction, Fatemeh NASIRI (INSA Rennes)*; Luce Morin (INSA Rennes); Wassim Hamidouche (INSA Rennes); Nicolas Dhollande (Aviwest); Jean-Yves Aubié (IRT b-com)
  2. Features Denoising for Learned Image Coding, Daniele Mari (University of Padova)*; Simone Milani (University of Padova)
  3. Overfitting Multiplier Parameters for Content-Adaptive Post-Filtering in Video Coding, Maria Santamaria (Nokia Technologies)*; Ruiying Yang (Nokia Technologies); Francesco Cricri (Nokia Technologies); Honglei Zhang (Nokia Technologies); Jani Lainema (Nokia Technologies); Ramin Ghaznavi Youvalari (Nokia Technologies); Hamed Rezazadegan Tavakoli (Nokia Technologies); Miska Hannuksela (Nokia Technologies)
  4. Lossless Coding of Multimodal Image Pairs Based on Image-to-Image Translation, João Oliveira Parracho (Instituto de Telecomunicações)*; Lucas Thomaz (Instituto de Telecomunicações); Luis Tavora (Instituto de Telecomunicações); Pedro Amado Assuncao (Instituto de Telecomunicações, Politécnico de Leiria); Sergio Faria (Instituto de Telecomunicações)

13:00

Lunch
Lunch box provided

14:00

Project Dissemination Session

Chairs: Nuno Rodrigues (Polytechnic of Leiria, Portugal) and Azeddine Beghdadi (USPN, France)

  1. ATLANTIS – Indoor Planning with Augmented and Diminished Reality, Werner Bailer, Georg Thallinger (DIGITAL, JOANNEUM RESEARCH); Vasileios Gkitsas, Petros Drakoulis, Antonis Karakottas, Dimitrios Pattas, Dimitris Zarpalas (ITI, Centre for Research and Technology Hellas); Brita Piovesan, Robert Huemer (Roomle GmbH); Richard Whitehand, Per Ström (Usability Partners)
  2. TailoredMedia – Automated Metadata Creation for Searching Audiovisual Content, Werner Bailer, Georg Thallinger (DIGITAL, JOANNEUM RESEARCH); Gernot Rottermanner (St. Pölten University of Applied Sciences); Thomas Kurz, Jakob Frank (Redlink GmbH); Christoph Bauer (Austrian Broadcasting Corporation); Gabriele Fröschl, Michael Batlogg (Austrian Mediathek)
  3. XAIface: Measuring and Improving Explainability for AI-based Face Recognition, Chiara Galdi* (EURECOM); Paulo Lobato Correia* (Instituto Superior Técnico – Instituto de Telecomunicações); Yuhang Lu* (EPFL); Jonas Pfister* (University of Vienna); Martin Winter* (JOANNEUM RESEARCH)
  4. Towards JPEG AIC Part 3: Call for Contributions on Subjective Image Quality Assessment, Michela Testolina (EPFL); Evgeniy Upenik (Audiovisual Technology Laboratory); Jon Sneyers (Media Technology Research Cloudinary); Touradj Ebrahimi (EPFL)

15:20

Coffee Break

15:40

Special Session 2 (Oral)

Chairs: Hadi Amirpour (Alpen-Adria-Universität Klagenfurt)

Machine Learning for Immersive Content Processing

  1. Award candidate: Computational Hyperspectral Imaging with Diffractive Optics and Deep Residual Learning, Ayoung Kim (Tampere University)*; Ugur Akpinar (Tampere University); Erdem Sahin (Tampere University); Atanas Gotchev (Tampere University)
  2. Deep 3D Model Optimization for Immersive and Interactive Applications, Elena Camuffo (University of Padova)*; Federica Battisti (University of Padova); Francesco Pham (University of Padova); Simone Milani (University of Padova)
  3. FuRA: Fully Random Access Light Field Image Compression, Hadi Amirpour (Alpen-Adria-Universität Klagenfurt)*; Christine Guillemot (INRIA); Christian Timmerer (Alpen-Adria-Universität Klagenfurt)
  4. Double Deep Learning-Based Point Cloud Geometry Coding with Adaptive Super-Resolution, Manuel Ruivo (Instituto Superior Técnico – Instituto de Telecomunicações)*; André F. R. Guarda (Instituto de Telecomunicações); Fernando Pereira (Instituto Superior Técnico – Instituto de Telecomunicações)

17:00

Oral Session 2

Chair: Marco Carli (Università degli Studi Roma Tre)

Image and Video Segmentation

  1. Award candidate: Opto-UNet: Optimized UNet for Segmentation of Varicose Veins in Optical Coherence Tomography, Maryam Viqar (Institute of Optical Materials and Technologies – Bulgarian Academy of Sciences)*; Violeta Madjarova (Institute of Optical Materials and Technologies – Bulgarian Academy of Sciences); Vipul Baghel (Dept. of Electronics Engineering, Aligarh Muslim University); Elena Stoykova (Institute of Optical Materials and Technologies – Bulgarian Academy of Sciences)
  2. Semantic-SRF: Sparse Multi-view Indoor Semantic Segmentation with Stereo Neural Radiance Fields, Cem Eteke (Technical University of Munich)*; Jinpeng Zhang (Technical University of Munich); Eckehard Steinbach (Technical University of Munich)
  3. Change Detection in Moving-Camera Videos Using a Shift-Invariant Dissimilarity Metric, Thadeu L Barbosa Dias (Federal University of Rio de Janeiro)*; Lucas Thomaz (Instituto de Telecomunicações); Sergio Netto (Federal University of Rio de Janeiro); Eduardo A. B. da Silva (Federal University of Rio de Janeiro)
  4. Transfer Learning Based Retinal Layer and Fluid Segmentation using Fully Convolutional Networks, Esther M Parra-Mora (University of Coimbra)*; Alex Cazañas-Gordon (University of Coimbra); Luis A da Silva Cruz (University of Coimbra)

18:20

End of the First Day

18:30

EUVIP 2022 Welcome Reception
Sea the Future, Parque das Nações

Tuesday, 13th September

9:00

Keynote Talk 2

Chair: João Ascenso (Instituto Superior Técnico – Instituto de Telecomunicações, Portugal)

“Volumetric Video Content Creation for Immersive XR Experiences“
by Aljosa Smolic (Hochschule Luzern, Switzerland)

10:00

Special Session 3 (Oral)

Chair: Paulo L. Correia (Instituto Superior Técnico – Instituto de Telecomunicações, Portugal)

Biometric Recognition Explainability

  1. Award candidate: Demystifying Face-Recognition with Locally Interpretable Boosted Features (LIBF), Martin Winter (JOANNEUM RESEARCH)*; Werner Bailer (JOANNEUM RESEARCH); Georg Thallinger (JOANNEUM RESEARCH)
  2. Impact of Digital Face Beautification in Biometrics, Nélida Mirabet-Herranz (Eurecom)*; Chiara Galdi (Eurecom); Jean-Luc Dugelay (Eurecom)
  3. A Novel Framework for Assessment of Deep Face Recognition Systems in Realistic Conditions, Yuhang Lu (EPFL)*; Luca Barras (EPFL); Touradj Ebrahimi (EPFL)
  4. Impact of Conventional and AI-based Image Coding on AI-based Face Recognition Performance, Naima Bousnina (Instituto de Telecomunicações)*; Joao Ascenso (Instituto Superior Técnico – Instituto de Telecomunicações); Paulo L Correia (Instituto Superior Técnico – Instituto de Telecomunicações); Fernando Pereira (Instituto Superior Técnico – Instituto de Telecomunicações)

11:20

Coffee Break

11:40

Oral Session 3

Chair: Lina Karam (Arizona State University, USA)

Image and Video Processing

  1. Award candidate: EGAIN: Extended GAn Inversion, Wassim Kabbani (Technical University of Denmark)*
  2. Multilayer Perceptron to Boost Colorimetric Capacities of 2D RGB and Hyperspectral Snapshot Cameras, Eric Lopez-Lopez (AIMEN)*; Roi Mendez-Rial (AIMEN)
  3. Residual Swin Transformer Channel Attention Network for Image Demosaicing, Wenzhu Xing (Tampere University)*; Karen Egiazarian (Tampere University)
  4. CNN-based Euler’s Elastica Inpainting with Deep Energy and Deep Image Prior, Karl Schrader (Saarland University)*; Tobias Alt (Saarland University); Joachim Weickert (Saarland University); Michael Ertel (Saarland University)

13:00

Lunch
Lunch box provided

14:00

Keynote Talk 3

Chair: Fernando Pereira (Instituto Superior Técnico – Instituto de Telecomunicações, Portugal)

“The Revolution of Neural Rendering“
by Matthias Nießner (Technical University of Munich, Germany)

15:00

Oral Session 4

Chair: Touradj Ebrahimi (EPFL, Switzerland)

3D Image Processing

  1. Visually Relevant Point Clouds Features Extraction by Radial Angular Point Cloud Filtering, Tiziana Cattai (Sapienza Universita di Roma); Azeddine Beghdadi (L2TI, University Sorbonne Paris Nord); Gaetano Scarano (Sapienza Universita di Roma); Stefania Colonnese (Sapienza Universita di Roma)*
  2. Incorporating Spatio-Temporal Information in Frustum-ConvNet for Improved 3D Object Detection in Instrumented Vehicles, Venkatesh G M (Insight Centre for Data Analytics)*; Suzanne Little (Dublin City University); Noel O Connor (Home)
  3. Enhanced Local Optimization Framework for Light Field Disparity Estimation, Rui Lourenco (Instituto de Telecomunicações)*; Lucas Thomaz (Instituto de Telecomunicações); Eduardo A. B. da Silva (Federal University of Rio de Janeiro); Sergio Faria (Instituto de Telecomunicações)
  4. 3D Object Detection On Synthetic Point Clouds For Railway Applications, Michael Neri (Università degli Studi Roma Tre)*; Federica Battisti (University of Padova)

16:20

Coffee Break

16:40

Oral Session 5

Chair: Hugo Proença (University of Beira Interior- Instituto de Telecomunicações)

Biometrics and Medical Imaging

  1. Fusion of Deep Features for Differential Face Morphing Attack Detection at Automatic Border Control Gates, Jag Mohan Singh (Norwegian University of Science and Technology Gjøvik)*; Raghavendra Ramachandra (Norwegian University of Science and Technology Gjøvik)
  2. HEROES: a Video-Based Human Emotion Recognition Database, Ilaria Mannocchi (Università degli Studi Roma Tre); Kamal Lamichhane (Università degli Studi Roma Tre)*; Federica Battisti (University of Padova); Marco Carli (Università degli Studi Roma Tre)
  3. Real-time Style Transfer for Videos to Enhance the Realism of Simulation of Laparoscopic Surgeries, Marine Y Shao (UWE)*; James Clark (Royal Cornwall Hospital NHS Trust); David A Huson (UWE); Jon Yngve Hardeberg (Norwegian University of Science and Technology Gjøvik)
  4. Hybrid Attention Mechanism for Liver Tumor Segmentation in CT Images, Ming Gong (University of Strathclyde)*; Baixaing Zhao (University of Strathclyde); John Soraghan (University of Strathclyde); Gaetano Di-Caterina (University of Strathclyde); Derek Grose (Beatson West of Scotland Cancer Centre)

18:00

End of the Second Day

20:00

EUVIP 2022 Dinner
Tacho do Pescador restaurant, Parque das Nações

Wednesday, 14th September

9:00

Keynote Talk 4

Chair: Moncef Gabbouj (Tampere University, Finland)

“Visual Processing and Data Science for Physiological Forensics“
by Min Wu (University of Maryland, USA)

10:00

Special Session 4 (Oral)

Chair: António Pinheiro (University of Beira Interior – Instituto de Telecomunicações)

Challenges in Point Cloud Technology

  1. Subjective and Objective Testing in Support of the JPEG Pleno Point Cloud Compression Activity, Stuart Perry (University of Technology Sydney)*; Antonio Pinheiro (University of Beira Interior – Instituto de Telecomunicações); Davi Lazzarotto (EPFL); Luis A da Silva Cruz (University of Coimbra); João P.C Prazeres (University of Beira Interior); Touradj Ebrahimi (EPFL); Emil Dumic (University North, Varazdin)
  2. Influence of Spatial Rendering on the Performance of Point Cloud Objective Quality Metrics, Davi Lazzarotto (EPFL)*; Michela Testolina (EPFL); Touradj Ebrahimi (EPFL)
  3. Explorations on 3D Point Clouds Coding Using Transformers and Patches, Luis A da Silva Cruz (University of Coimbra)*; Miguel Marques (University of Coimbra)
  4. On The Stability of Point Cloud Machine Learning Based Coding, João P.C Prazeres (University of Beira Interior)*; Rafael Rodrigues (University of Beira Interior – Instituto de Telecomunicações); Manuela Pereira (University of Beira Interior); Antonio Pinheiro (University of Beira Interior – Instituto de Telecomunicações)

11:20

Coffee Break

11:40

Poster Session

Chair: Paulo Nunes (ISCTE-IUL-IT, Portugal)

  1. Deep Learning based Aerial Image Segmentation for Computing Green Area Factor, G M Atiqur Rahaman (Örebro University)*; Martin Längkvist (Örebro University); Amy Loufti (Örebro University)
  2. Active Speaker Recognition using Cross Attention Audio-Video Fusion, Ruxandra G TAPU (Institute Mines-Telecom, Telecom SudParis / University Politehnica of Bucharest)*; Bogdan Cosmin Mocanu (University Politehnica of Bucharest)
  3. ParalMGC Multiple Audio Representations for Synthetic Human Speech Attribution, Michael Neri (Università degli Studi Roma Tre)*; Anna Ferrarotti (Università degli Studi Roma Tre); Luca De Luisa (Università degli Studi Roma Tre); Andrea Salimbeni (Università degli Studi Roma Tre); Marco Carli (Università degli Studi Roma Tre)
  4. Invertebrates Detection With YOLOv5: Towards Study of Soil Organisms Using Deep Learning, Ghulam Sakhi Shokouh (IMT Mines Ales)*; Emma Pruvost (IMT Mines Ales); Etienne Delort (IMT Mines Ales); hadrien tulet (IMT Mines Ales); Philippe Montesinos (EMA); Baptiste Magnier (IMT Mines Ales CERIS); Mickael Hedde (IMT Mines Ales); Emma BELAUD (IMT Mines Ales); Jourdan Christophe (IMT Mines Ales)
  5. ITER-Tag: An Adaptable Framework for Robust Uncoded Fiducial Marker Detection and Identification, Laura Goncalves Ribeiro (Tampere University)*; Olli J Suominen (Tampere University); Sari Peltonen (Tampere University); Emilio Ruiz Morales (F4E); Atanas Gotchev (Tampere University)
  6. Stabilised Inverse Flowline Evolution for Anisotropic Image Sharpening, Kristina Schaefer (Saarland University)*; Joachim Weickert (Saarland University)
  7. Exploring Temporal Consistency in Image-Based Rendering for Immersive Video Transmission, Smitha Lingadahalli Ravi (Orange Labs)*; Félix Henry (Orange Labs); Luce Morin (INSA Rennes); Matthieu Gendrin (Orange Labs)
  8. Watermarking for Large-Scale Video Distribution through Out-of-the-Loop Frame Replacement, Hannes Mareen (Ghent University)*; Francis Valcke (Ghent University); Aaron Hallaert (Ghent University); Glenn Van Wallendael (Ghent University); Peter Lambert (Ghent University)
  9. A Light Weight Convolution Neural Network for Automatic Disasters Recognition, Muhammad Munsif (Islamia college Peshawar); Hina Afridi (Norwegian University of Science and Technology Gjøvik); Mohib Ullah (Norwegian University of Science and Technology Gjøvik)*; Sultan Daud Khan (National University of Technology); Faouzi Alaya-Chekh (Norwegian University of Science and Technology Gjøvik); Muhammad Sajjad (Norwegian University of Science and Technology Gjøvik)
  10. Computing Particle Size Distribution of Mineral Rocks using Deep Learning-based Instance Segmentation, Andrei Cristian Baraian (VTT Technical Research Center of Finland)*; Vili Kellokumpu (VTT Technical Research Center of Finland)
  11. IDALib: a Python Library for Efficient Image Data Augmentation, Nicolás Vila-Blanco (Universidade de Santiago de Compostela)*; Raquel Rodríguez-Vilas (Universidade de Santiago de Compostela); María José Carreira (Universidade de Santiago de Compostela)
  12. Autoencoder Model Exploration for Multi-Layer Video Compression, Luiz Henrique Cancellier (Federal University of Santa Catarina)*; Mateus Grellert (Federal University of Santa Catarina); José Luís Güntzel (Federal University of Santa Catarina); Luis A da Silva Cruz (University of Coimbra)

13:00

Lunch
Lunch box provided

14:00

Oral Session 6

Chair: Paula Queluz (Instituto Superior Técnico – Instituto de Telecomunicações, Portugal)

Quality Assessment

  1. Holography Challenges on Coding and Quality Assessment, Manuela Pereira (University of Beira Interior)*; Raquel Guerra (University of Beira Interior); Elsa Fonseca (University of Beira Interior); Antonio Pinheiro (University of Beira Interior – Instituto de Telecomunicações)
  2. Does Personal Interests Affect Visual Attention? – An Eye Tracking Study, Julie Fournier (Université de Rennes)*
  3. Parametric Quality Models for Multiscreen Video Systems, Yuriy Reznik (Brightcove, Inc.)*; Nabajeet Barman (Brightcove UK, Ltd.); Rahul Vanam (Brightcove, Inc.)
  4. Visual Quality Assessment of Adversarially Attacked Images, Ali Mezher (Lebanese American University); Yingpeng Deng (Arizona State University); Lina Karam (Arizona State University)*

15:20

Coffee Break

15:40

Industry Session

Chair: Nuno Couto (Worten, Portugal)

“Present and Future of TV Services & Video Streaming“

Keynote: “Engineering and operating a large-scale OTT service – a view from the Streaming Industry”
by Pedro Geada (Senior Engineering Leader)

Panel speakers:

  • Pedro Geada (Senior Engineering Leader)
  • João Miguel Ferreira (Innovation Services Director @ NOS Inovação, Portugal)
  • Miguel Jardim (Head of MEO TV Services Engineering & Operations @ Altice, Portugal)
  • Pedro Neto (Head of TV Product Development @ Vodafone, Portugal)

18:00

End of the Third Day