Full Technical Programme

Monday, 11th September

8:30-14:00

Registration Desk Open
Location: Entrance of Ametyst building

Tutorials

09:30

Tutorial 1
Location: Ametyst building, room A154

Hard and soft metrology challenges in Material Appearance
by Davit Gigilashvili and Adity Sole from NTNU, Norway

09:30

Tutorial 2
Location: Kobolt building, room K109

Recent trends in MRI reconstruction
by Joseph Suresh Paul from School of Informatics, Kerala University, India

12:00

Lunch

13:30

Tutorial 3
Location: Beryll building, room B211

Color in computer vision
by Maria Vanrell from Universitat Autònoma de Barcelona, Spain

13:30

Tutorial 4
Location: Gneis building, room G303

From Volumetric Video to Interactive Virtual Humans
by Peter Eisert from Humboldt University Berlin & Fraunhofer HHI, Germany


Tuesday, 12th September

Location: Helvin building, auditorium 1/3 Eureka

8:00

Registration Desk Open
Location: Outside Eureka auditorium

8:45

Welcome Ceremony

09:00

Plenary 1: Mohammed Bennamoun from  University of Western Australia, Perth, Australia

3D Computer Vision for Future Robots

Chair: Faouzi Alaya Cheikh

10:00

Coffee break

Special session 1: AI in the City: Efficient, Scalable and Privacy-Preserving Visual Scene Understanding in Man-Made Environments

Chair: Amine Bourki

10:20

Invited talk: Registration for Urban Modeling Based on Linear and Planar Features
by Pascal Monasse from Ecole des Ponts ParisTech, France

10:50

Mono6D++: Learning Point Cloud Visibility for 3D Prior-based Vehicle 6D Pose Estimation
by Yangxintong Lyu1, Olivier Ducastel1, Remco Royen1, Adrian Munteanu1.
1 Vrije Universiteit Brussel

11:10

Attention-based Network for Image/Video Salient Object Detection
by Omar Elharrouss1, Soukaina ElIdrissi ElKaitouni2, Younes Akbari1, Somaya Al Maadeed1, Ahmed Bouridane3.
1Qatar University, 2SIdi Mohamed Ben Abdellah Univerisity, 3University of Sharjah.

11:30

360-GAN: Cycle-Consistent GAN for Extrapolating 360-Degree Field-of-View
by Jit Chatterjee1, Maria Torres Vega1.
1KU Leuven.

11:50

All Predictions Matter: An Online Video Prediction Approach
by Melan Vijayaratnam1, Marco Cagnazzo1, Giuseppe Valenzise2, Enzo Tartaglione3.
1LTCI, Télécom ParisTech, Institut Polytechnique de Paris, France, 2CNRS, 3Télécom Paris – Institut Polytechnique de Paris.

12:10

Lunch

Oral Session 1: Quality and Performance Assessment

Chair: Ali Amirshahi

13:40

Evaluating the Vulnerability of Deep Learning-based Image Quality Assessment Methods to Adversarial Attacks
by Hanene Fatima Zohra Brachemi Meftah1, Sid Ahmed Fezza2, Wassim Hamidouche1, Olivier Deforges3.
1INSA Rennes, 2National Higher School of Telecommunications and ICT, 3IETR, Rennes

14:00

Blind Video Stabilization Assessment based on convolutional LSTM
by Mohamed Riad Yagoubi1, Seyed Ali Amirshahi1, Steven Y Le Moan1, Azeddine Beghdadi2, Erik Rodner3.
1Norwegian University of Science and Technology, 2L2TI, University Sorbonne Paris Nord, 3University of Applied Sciences, Berlin

14:20

VSTAB-QUAD: A New Video-stablization Quality Assessment Database
by Borhen eddine Dakkar1, Azeddine Beghdadi1, Faouzi Alaya-Chekh2, Amine Bourki3.
1L2TI, University Sorbonne Paris Nord, 2Norwegian University of Science and Technology. 3VizioSense

14:40

Improving Viewer Training in Visual Assessment
by Mathias Wien1 Vittorio Baroncini2.
1RWTH Aachen University, 2VABtech.

15:00

Poster Session: Detection, Classification, Data Protection and Scene Analysis

Chair: Hantao Liu
Location: Outside Eureka auditorium
(Coffee will be available during poster session)

  • MAiVAR-T: Multimodal Audio-image and Video Action Recognizer using Transformers by Muhammad Bilal B Shaikh1, Douglas Chai1, Syed Islam1, Naveed Akhtar2. 1Edith Cowan University, 2The University of Western Australia
  • Semi-Supervised Anomaly Detection in Electronic-Exam Proctoring Based on Skeleton Similarity by Habibollah Agh Atabay1, Hamid Hassanpour1. 1Shahrood University of Technology.
  • CD-COCO: A Versatile Complex Distorted COCO Database for Scene-Context-Aware Computer Vision by Ayman Beghdadi1, Azeddine Beghdadi2, Malik Mallem1, Faouzi Alaya-Chekh 3, Beji Lotfi4 1Paris Saclay University, 2L2TI, University Sorbonne Paris Nord, 3Norwegian University of Science and Technology, 4University of Evry.
  • Skeleton-based Hand Gesture Recognition using Geometric Features and Spatio-Temporal Deep Learning Approach by Abu Saleh Musa Miah1, Jungpil Shin1, Md. Al. Mehedi Hasan2, Yusuke Fujimoto1, Nobuyoshi Asai1. 1The University of Aizu, 2Rajshahi University of Engineering & Technology.
  • CTL-NET: Deep Learning Network for Cattle Teat Length Trait Analysis by Hina Afridi1, Mohib Ullah1, Øyvind Nordbø2, Anne Guro Larsgard3, Faouzi Alaya-Chekh1. 1Norwegian University of Science and Technology, 2Norsvin SA, 3Geno SA.
  • Underwater Object Detection in AUVs using Image Enhancement and Deep Learning Models by Adane N. Tarekegn1, Faouzi Alaya-Chekh1, Mohib Ullah1, Erik Sollesnes2, Cornelia Alexandru3, Saeed Azar4, Erdeniz Erol5, George Suciu3 (1Norwegian University of Science and Technology, 2USEA Ocean Data, 3BEIA consult International, 4OBSS Teknoloji A.Ş, 5Elkon.
  • Wild Animal Species Classification from Camera Traps using Metadata Analysis by Aslak Tøn1, Ali Shariq Imran1, Mohib Ullah1. 1Norwegian University of Science and Technology.
  • A hitchhiker’s guide to white-box neural network watermarking robustness by Carl De Sousa Trias1, Mihai Petru Mitrea1, Enzo Tartaglione1, Attilio Fiandrotti2, Marco Cagnazzo1, Sumanta Chaudhuri1. 1Télécom ParisTech, Institut Polytechnique de Paris, France, 2Università di Torino.
    • Classical approaches and new deep learning trends to assist in accurately and efficiently diagnosing ear disease from otoscopic images by Dhruv C Jobanputra1, Mohammed Bennamoun1, Farid Boussaid1, Lian Xu1, Jafri Kuthubutheen1.1The University of Western Australia.

16:00

End

16:30

Reception and Social Activity
Location: Gjøvik Science Centre, Address: Brennerigata 1, 2815 Gjøvik.


Wednesday, 13th September

Location: Helvin building, auditorium 1/3 Eureka

9:00

Plenary 2 : Quantitative imaging biomarkers in the era of precision medicine

by Habib Zaidi from Geneva University Hospitals, Geneva, Switzerland

Chair: Djamila Aouada

10:00

Coffee break

Oral Session 2 : Medical Image Processing, Analysis and Diagnosis

Chair: Marius Pedersen

10:20

DCAN: DenseNet with Channel Attention Network for Super-resolution of Wireless Capsule Endoscopy
by Hiren Vaghela1, Anjali Sarvaiya1, Pranav Premlani1, Abhishek Agarwal1, Kishor Upla1, Kiran Raja2, Marius Pedersen2.
1Sardar Vallabhbhai National Institute of Technology, Surat, India, 2Norwegian University of Science and Technology

10:40

Enhancement of Color Reproduction for Capsule Endoscopy Images
by Léo Watine1, Pål Anders Floor2, Marius Pedersen1, Peter Nussbaum1, Bilal Ahmad1, Øistein Hovde3.
1Université de Strasbourg, 2Norwegian University of Science and Technology, 3University of Oslo.

11:00

A Quality-Oriented Database for Video Capsule Endoscopy
by Tan-Sy Nguyen1, Marie Luong1, John Chaussard1, Azeddine Beghdadi1, Hatem Zaag1, Thuong Le-Tien2.
1Université Sorbonne Paris Nord, 2HCMUT.

11:20

FEES-IS: Real-time Instance Segmentation of Flexible Endoscopic Evaluation of Swallowing
by Weihao Weng1, Xin Zhu1, Mitsuyoshi Imaizumi2, Shigeyuki Murono2.
1University of Aizu, 2Fukushima Medical University.

11:40

Identification of Children with ADHD from EEG Signals Based on Entropy Measures and Support Vector Machine by Med Maniruzzaman1, Med. Al Mehedi Hasan2, Taro Suzuki1, Jungpil Shin1. 1The University of Aizu, 2Rajshahi University of Engineering & Technology.

12:00

Lunch

Oral Session 3: Visual information display, rendering and compression

Chair: Nuno Rodrigues

13:40

Evaluating the effect of sparse convolutions on point cloud compression
by Davi Lazzarotto1, Touradj Ebrahimi1.
1École Polytechnique Fédérale de Lausanne

14:00

Study on Viewpoint-Dependent Time-Multiplexing for Weighted Optimization of 3D Layered Displays
Armand Losfeld1, Daniele Bonatto1, Gauthier Lafruit1, Mehrdad Teratani1.
1Université Libre de Bruxelles.

14:20

Self-Supervised Super-Resolution Approach for Isotropic Reconstruction of 3D Electron Microscopy Images from Anisotropic Acquisition.
Mohammad Khateri1, Morteza Ghahremani1, Alejandra Sierra1, Jussi Tohka1.
1University of Eastern Finland.

14:40

Using Deep Generative Models for Glossy Appearance Synthesis and Exploration
by Abhinav Reddy Nimma1, Davit Gigilashvili1.
1Norwegian University of Science and Technology.

15:00

ConvNeXt-ChARM: ConvNeXt-based Transform for Efficient Neural Image Compression
by Ahmed Ghorbel1, Wassim Hamidouche2, Luce Morin1.
1INSA Rennes, 2TII.

15:20

Coffee break

15:40

Plenary 3: Model-Based Optimization Meets Deep Learning in Image Analysis

by Aleksandra Pizurica from Ghent University, Belgium

Chair: Stefania Colonnese

16:40

3MT Session

Chairs: Tiziana Cattai

17:40

End

19:00

Conference dinner
Location: Samfundet, Address: Øvre Torvgate 24, 2815 Gjøvik


Thursday, 14th September

Location: Helvin building, auditorium 1/3 Eureka

9:00

Plenary 4: Deep learning for inverse problems in imaging

by Enrico Magli from Politecnico di Torino, Italy

Chair: Anirban Mukhopadhyay

10:00

Coffee break

Special Session 2: Image Quality Assessment and Enhancement in the Context of Medical Imaging and Diagnosis

Chair: Azeddine Beghdadi

10:20

Invited Talk : Predicting Radiologists’ Gaze with Computational Saliency Models in Mammogram Reading.
by Hantao Liu from Cardiff University, UK

10:50

Deep Learning Models for Low Dose CT Simulation
by Lumi XIA 1, Meriem MO OUTTAS1, Lu Zhang1, Eric Frampas2, Olivier Deforges1.
1IETR, INSA Rennes, 2Universitary Hospital
.

11:10

Medical Point Clouds Enhancement at the Network Edge
by Paolo Giannitrapani1, Tiziana Cattai1, Stefania Colonnese1.
1Sapienza Universit di Roma, Italy.

11:30

Enhanced residue prediction for Lossless coding of multimodal image pairs based on image to image translation
by Daniel S Nicolau1, João Oliveira Parracho2, Lucas Thomaz2, Luis MN Tavora1, Sergio M Faria2.
1Instituto Politécnico de Leiria, 2Instituto de Telecomunicacoes.

11:50

Automatic lung nodule classification in CT images using Two-stage CNNs and Soft-voting of Multi-scale Classifiers
by Lipeng Xie (Zhengzhou University), Yubing Tong (University of Pennsylvania), Yuan Wan (Binghamton University).

12:10

Lunch

Special Session 3: Spectral Imaging and its Applications

Chair: Sony George

13:40

Invited talk: Spectral Imaging and its Application to Cultural Heritage
by Giorgio Trumpy from NTNU, Gjovik, Norway

14:10

Bayesian Multispectral Videos Super Resolution
by Hamid Fsian1, Jean Baptiste Thomas1, Pierre Gouton2, Jon Yngve Hardeberg3.
1University of Burgundy, France, 2University of Burgundy, Franche-Comté, 3Norwegian University of Science and Technology.

14:30

Centralized Sample Expansion and Prior Correlation Evaluation for Hyperspectral Image Classification with Fully Convolutional Network
by Ningyang Li1, Zhaohui Wang1.
1Hainan University.

14:30

Coffee break

15:10

Project dissemination session
Chair: Joaquin Olivares

16:10

Panel discussion – Revolutionizing health care with AI-assisted medical imaging analysis
Chair: Jon Yngve Hardeberg

Panel discussion participants:
Habib Zaidi
Øystein Hovde
Anne Solberg
Robert Jenssen

17:10

Closing ceremony