Program Schedule

Wednesday – 20/09/2023

  • Welcome

    –

    Reception and registration

  • Keynote 1 – Towards AI-powered personal shoppers of trendy clothes

    –

    Pr. Alberto Del Bimbo

  • Coffee Break

    –

  • Session 1 – Visual Processing

    –

    Regular

  • Lunch

    –

  • Special Session – Cultural Heritage and Multimedia Content

    –

    Special Sesssion

  • Session 2 – Applications

    –

    Regular

  • Coffee Break

    –

  • Music meets Science

    –

    Social Event

  • Guided Tour

    –

  • Dinner

    –

Thursday – 21/09/2023

  • Keynote 2 – Research activities at INA ( French National Audiovisual Archive)

    –

    Nicolas Hervé, Head Researcher

  • Session 3 – Multimodal Analysis

    –

    Regular

  • Coffee Break

    –

  • Special Session – Explainability in Multimedia Analysis (ExMA)

    –

    Special Session

  • Lunch

    –

  • Special Session – Physical Models and AI in Image and in Multi-modality 

    –

    Special Session

  • Poster session + Coffee

    –

    Regular

  • Special session – Interactive Video Retrieval for Beginners (IVR4B)

    –

    Special Session

  • Dinner

    –

Friday – 22/09/2023

  • Special Session – Computational Memorability of Imagery

    –

    Special Session

  • Session 4 – Multimodal Analysis

    –

    Regular

  • Coffee Break

    –

  • Special session – Cross-modal multimedia analysis and retrieval for well-being insights

    –

  • Closing & Award

    –

  • Lunch

    –

Detailed Program

September 20th, 2023

9h00 Welcome

9h30 Keynote 1: Pr. Alberto Del Bimbo, Department of Information Engineering of
the University of Firenze.

Towards AI-powered personal shoppers of trendy clothes

10h30 Coffee Break

11h00 Regular Session 1: Visual Processing

  • Sami Barchid (University of Lille); Benjamin Allaert (IMT Nord Europe); Amel Aissaoui (IMT Nord Europe ); José Mennesson (IMT Nord-Europe); Chaabane C Djeraba (University of Lille) Spiking-Fer: Spiking Neural Network for Facial Expression Recognition With Event Cameras
  • Alexandre Heuillet (Université Paris-Saclay); Hedi Tabia (Université Paris-Saclay);Hichem Arioui (Université d’Evry Val d’Essonne) Automated Siamese Network Design for Image Similarity Computation
  • Nathalie Neptune (IRIT); Josiane Mothe (Institut de Recherche en Informatique de Toulouse) Annotating Satellite Images of Forests with Keywords from a Specialized Corpus in the Context of Change Detection
  • Meghna P Ayyar (University of Bordeaux/LaBRI); Jenny Benois-Pineau (University of Bordeaux/LABRI); Akka Zemmari (Univ. Bordeaux); Hélène Amieva (Inserm BPH, Université de Bordeaux); Laura Middleton (University of Waterloo) Entropy-based Sampling for Streaming learning with Move-to-Data approach on Video

12h20 Lunch

13h40 Special Session CH: Cultural Heritage and Multimedia Content

  • Liliana Cecere (University of Salerno); Francesco Colace (University of Salerno); Marco Lombardi (University of Salerno); Angelo Dr. Lorusso (University of Salerno); Domenico Santaniello (University of Salerno); Carmine Valentino (University of Salerno) Cultural Heritage Enhancement through Digital Storytelling and Context-Aware Recommender System
  • Helmut Neuschmied (JOANNEUM RESEARCH)*; Georg Thallinger (JOANNEUM
    RESEARCH, Austria); Werner Bailer (JOANNEUM RESEARCH); Gabriele Fröschl
    (Austrian Mediathek) ÖWF-OD: A Dataset for Object Detection in Archival Film Content
  • Emile Blettery (LASTIG/IGN-UGE)*; Valérie Gouet-Brunet (LASTIG/IGN-UGE) Re-ranking Image Retrieval in Challenging Geographical Iconographic Heritage Collections

14h40 Regular Session 2: Applications

  • Julie Fournier (Université de Rennes 1); Elise Etchamendy (Université de Rennes 2); Myriam Chérel (Université de Rennes 2); Meriem MO OUTTAS (IETR INSA); Lu Zhang (INSA Rennes) The impact of the affinity on ASD people visual engagement
  • QIONG WANG (Zhejiang University of Technology); Lu Zhang (INSA Rennes) Predicting personalized saliency map for people with autism spectrum disorder
  • Aymen Sekhri (INTTIC); Mohamed A KERKOURI (Université d’Orléans); Aladine Chetouani (Université d’Orléans, France); Marouane Tliba (University of Orleans); Yassine Nasser (University of Orleans); Rachid Jennane (University of Orleans); Alessandro Bruno (IULM university ) Automatic diagnosis of knee osteoarthritis severity using Swin transformer
  • Djamila Romaissa Beddiar (Center for machine vision and signal analysis, university of Oulu); Mourad Oussalah (University of Oulu); Tapio Seppanen (Center for machine vision and signal analysis, university of Oulu) Retrieved Generative Captioning for Medical Images

16h00 Coffee Break

16h20 Music Meets Science (1 hour)

18h30 Guided Tour (1 hour)

19h30 Diner (La Taverne) Map

September 21st, 2023

9h00 Keynote 2: Prof. Nicolas Hervé, Ina

Research activities at INA ( French National Audiovisual Archive)

10h00 Regular Session 3: Multimodal Analysis

  • Perla Doubinsky (CNAM); Nicolas Audebert (Cnam); Michel Crucianu (CEDRIC LAB, CNAM); Herve Le Borgne (CEA LIST) Wasserstein loss for Semantic Editing in the Latent Space of GANs
  • Théo Gigant (Laboratoire des Signaux et Systèmes); Frederic Dufaux (CNRS); Camille Guinaudeau (University Paris Sud / LIMSI); Marc Decombas (Télécom ParisTech) TIB: A Dataset for Abstractive Summarization of Long Multimodal Videoconference Records

10h40 Coffee Break

11h10 Special Session ExMA: Explainability in Multimedia Analysis

  • Helmut Neuschmied (JOANNEUM RESEARCH); Martin Winter (JOANNEUM RESEARCH) Explainable face verification for video archive documentation
  • Luc-Etienne Pommé (University of Bordeaux); Romain Giot (Univ. Bordeaux); Romain Bourqui (Univ. Bordeaux) H²O: Heatmap by Hierarchical Occlusion
    Romain XU-DARME (CEA-LIST/LIG); Jenny Benois-Pineau (University of Bordeaux/LABRI); Romain Giot (Univ. Bordeaux); Georges Quénot (Laboratoire d’Informatique de Grenoble, CNRS); Zakaria Chihani (CEA LIST); Marie-Christine Rousset (University Grenoble-Alpes); Alexey Zhukov (LaBRI UMR CNRS 5800, University of Bordeaux) On the stability, correctness and plausibility of visual explanation methods based on feature importance
  • Annika Frommholz (Fraunhofer HHI); Fabian Seipel (Technische Universitaet Berlin); Sebastian Lapuschkin (Fraunhofer Heinrich Hertz Institute); Wojciech Samek (Fraunhofer HHI); Johanna Vielhaben (Fraunhofer HHI) XAI-based Comparison of Audio Event Classifiers with different Input
    Representations

12h30 Lunch

14h00 Special Session Phy: Physical Models and AI in Image and in Multi-modality

  • Michaël Dell’aiera (LAPP); Thomas Vuillaume (Univ. Grenoble Alpes, Univ. Savoie Mont-Blanc, CNRS/IN2P3/LAPP); Mikael Jacquemont (LAPP); Alexandre Benoit (Listic-Université Savoie Mont Blanc) Deep unsupervised domain adaptation applied to the Cherenkov Telescope Array Large-Sized Telescope
  • Lorenzo Lopez Uroz (LISTIC); Alexandre Benoit (Listic-Université Savoie Mont
    Blanc); Yajing Yan (Listic-Université Savoie Mont Blanc); Christophe Lin-Kwong-
    Chon (LISTIC); Sophie Giffard-Roisin (ISTerre-Université Grenoble Alpes); Antoine
    Rabatel (IGE-Université Grenoble Alpes) Deep learning multimodal methods for geophysical inversion: application to glacier ice thickness estimation
  • Muhammad Amjad Iqbal (CEOSpaceTech (LAB), Research Center for Spatial Information, University Politehnica of Bucharest)*; Reza Mohammadi Asiyabi (University POLITEHNICA of Bucharest); Omid Ghozatlou (CEOSpaceTech (LAB), Research Center for Spatial Information, University Politehnica of Bucharest); Andrei Anghel (University Politehnica of Bucharest); Mihai Datcu (CEOSpaceTech (LAB),
    Research Center for Spatial Information, University Politehnica of Bucharest)
    Towards Complex-Valued Deep Architectures with Data Model Preservation for
    Sea Surface Current Estimation from SAR Data

15h00 Posters & Coffee Break

  • Sharmistha Sawant (Dublin City University); Saloni Thakare (Dublin City University); Derek Greene (University College Dublin); Gerardine Meaney (University College Dublin); Alan Smeaton (Insight Centre for Data Analytics, Dublin City University), Handwriting Analysis on the Diaries of Rosamond Jacob
  • Klaus Schoeffmann (Klagenfurt University) diveXB: An Interactive Video Retrieval System for Beginners
  • salima bourbia (LRIT, Mohammed V University, | L@bISEN, Vision-AD, ISEN Yncréa Ouest/Nantes|Prisme, Orleans University)*; Ayoub KARNE (ISEN Yncréa Ouest, Nantes); Aladine Chetouani (Université d’Orléans, France); Mohammed El Hassouni (LRIT URAC 29, Mohammed V University in Rabat); maher JRIDI (ISEN Yncréa Ouest, Nantes), Multi-stream Point-based model for Blind Geometric Point Cloud Quality Assessment
  • Giuseppe Amato (CNR-ISTI); Paolo Bolettieri (CNR-ISTI); Fabio Carrara (CNR-ISTI); Fabrizio Falchi (CNR-ISTI); Claudio Gennaro (CNR-ISTI); Nicola Messina (CNR); Lucia Vadicamo (CNR – ISTI)*; Claudio Vairo (CNR-ISTI), VISIONE for newbies: an easier-to-use video retrieval system
  • Loris Sauter (University of Basel)*; Heiko Schuldt (University of Basel); Raphael Waltenspül (University of Basel); Luca Rossetto (University of Zurich), Novice-Friendly Text-based Video Search with vitrivr
  • Josiane Mothe (Institut de Recherche en Informatique de Toulouse)*; Oshri Even-Zohar (Motek Entertainment ), Trad’Europe – From Aquisition to Transmission of Traditional Dances
  • Matthieu François (Université de Pau et des Pays de l’Adour)*; paul gay (uppa), Active Learning with few shot learning for crisis management
  • LAM PHAM (Austrian Institute of Technology)*; Trang Le (JVN Institute-VNU); Cam Le (HCM University of Technology); Dat Ngo (University of Essex); Axel Weissenfeld (AIT Austrian Institute of Technology GmbH); Alexander Schindler (Austrian Institute of Technology), Deep Learning Based Multimodal with Two-phase Training Strategy for Daily Life Video Classification
  • Sylvain Marchand (La Rochelle University)*; Petra Gomez-Krämer (La Rochelle University); Florian Lardeux (La Rochelle University), Energy and Orientation Maps for Interactive Visualization and Retrieval of Ancient Coins
  • Varsha Devi ( Laboratoire d’Informatique de Grenoble); Philippe Mulhem (Laboratoire d’Informatique de Grenoble, CNRS); Georges Quénot (Laboratoire d’Informatique de Grenoble, CNRS)* Improving Causality in Interpretable Video Retrieval
  • An Thi Nguyen (Norwegian University of Science and Technology) Adapting Video Instance Segmentation for Instance Search
  • Zhe Wang (University of Orleans); Aladine Chetouani (Université d’Orléans, France)*; Rachid Jennane (IDP – université d’Orléans), Transformer with Selective Shuffled Position Embedding for Early Detection of Knee Osteoarthritis
  • Thao-Nhu Nguyen (Dublin City University)*; Bunyarit Puangthamawathanakun (Dublin City University); Chonlameth Arpnikanondt (King Mongkut’s University of Technology Thonburi); Cathal Gurrin (Dublin City University); Annalina Caputo (Dublin City University); Graham Healy (Dublin City University), Efficient Search with an Interactive Video Retrieval System for Novice Users in IVR4B
  • Omar Shahbaz Khan (Reykjavik University)*; Björn Þ Jónsson (Reykjavik University), User Relevance Feedback and Novices: Anecdotes from Exquisitor’s Participation in Interactive Retrieval Competitions

16h20 Special Session IVR4B – Interactive Video Retrieval for Beginners

  • Klaus Schoeffmann (Klagenfurt University) diveXB: An Interactive Video Retrieval System for Beginners
  • Giuseppe Amato (CNR-ISTI); Paolo Bolettieri (CNR-ISTI); Fabio Carrara (CNR-ISTI); Fabrizio Falchi (CNR-ISTI); Claudio Gennaro (CNR-ISTI); Nicola Messina (CNR); Lucia Vadicamo (CNR – ISTI); Claudio Vairo (CNR-ISTI), VISIONE for newbies: an easier-to-use video retrieval system
  • Loris Sauter (University of Basel); Heiko Schuldt (University of Basel); Raphael Waltenspül (University of Basel); Luca Rossetto (University of Zurich), Novice-Friendly Text-based Video Search with vitrivr
  • Thao-Nhu Nguyen (Dublin City University)*; Bunyarit Puangthamawathanakun (Dublin City University); Chonlameth Arpnikanondt (King Mongkut’s University of Technology Thonburi); Cathal Gurrin (Dublin City University); Annalina Caputo (Dublin City University); Graham Healy (Dublin City University), Efficient Search with an Interactive Video Retrieval System for Novice Users in IVR4B
  • Omar Shahbaz Khan (Reykjavik University)*; Björn Þ Jónsson (Reykjavik University), User Relevance Feedback and Novices: Anecdotes from Exquisitor’s Participation in Interactive Retrieval Competitions

19h30 Diner (Le Martroi) Map

September 22nd, 2023

9h00 Special Session MM: Computational Memorability of Imagery

  • Iván Martín-Fernández (Universidad Politécnica de Madrid); Ricardo Kleinlein (Universidad Politécnica de Madrid); Cristina Luna-Jiménez (Universidad Politécnica de Madrid); Manuel Gil-Martín (Universidad Politécnica de Madrid); Fernando Fernández-Martínez (Universidad Politécnica de Madrid) Video Memorability Prediction From Jointly-learnt Semantic and Visual Features
  • Lorin Sweeney (Dublin City University); Alan Smeaton (Insight Centre for Data Analytics, Dublin City University); Graham Healy (Dublin City University) Memories in the Making: Predicting Video Memorability with Encoding Phase EEG
  • Mihai Gabriel Constantin (University Politehnica of Bucharest)*; Mihai Dogariu (University Politehnica of Bucharest); Andrei C Jitaru (University Politehnica of Bucharest); Bogdan Ionescu (University Politehnica of Bucharest, Romania) Assessing the difficulty of predicting media memorability

10h00 Regular Session 4: Multimodal Analysis

  • Elise Lincker (CNAM)*; Camille Guinaudeau (JFLI CNRS, Université Paris-Saclay); olivier pons (CNAM); Jérôme Dupire (CNAM); Céline Hudelot (CentraleSupélec); Vincent Mousseau (CentraleSupélec); Isabelle Barbet (CNAM); Caroline Huron (Université Paris Cité, INSERM) Noisy and Unbalanced Multimodal Document Classification: Textbook Exercises as a Use Case
  • Danfeng Zhuang (Jiangnan University); Min Jiang (Jiangnan Universiy)*; Hichem Arioui (Université d’Evry Val d’Essonne); Hedi Tabia (Université Paris-Saclay) Action Text Diffusion Prior Network for Action Segmentation

10h40 Coffee Break

11h10 Special Session Wel: Cross-modal multimedia analysis and retrieval for well-being insights

  • Georgia Pantalona (Information Technology Institute, CERTH); Anna Barachanou (Information Technology Institute, CERTH ); Nikolaos Loukas (Information Technology Institute, CERTH); Lazaros Apostolidis (Information Technology Institute, CERTH ); Filareti Tsalakanidou (Information Technology Institute, CERT ); Symeon Papadopoulos (Information Technologies Institute / Centre for Research & Technology – Hellas, GR)* Online Behaviour Indicator Extraction for Enhanced Cancer Patient Management using Real-World Data
  • Chi Cuong Nguyen (University of Science and Technology of Hanoi)*; Gang Son Tran (University of Science and Technology of Hanoi); Vincent NGUYEN (University of Orleans) False Positive Reduction of Pulmonary Nodule on CT image using Attention-based Multiple Instance Learning
  • Eivind Moholdt (University of Bergen); Sohail Ahmed Khan (MediaFutures,University of Bergen); Duc-Tien Dang-Nguyen (University of Bergen)* Detecting Out-of-Context Image-Caption Pair in News: A Counter-Intuitive
  • Bunyarit Puangthamawathanakun (Dublin City University)*; Chonlameth Arpnikanondt (King Mongkut’s University of Technology Thonburi); Worarat Krathu (King Mongkut’s University of Technology Thonburi); Graham Healy (Dublin City University); Cathal Gurrin (Dublin City University) Towards Face De-identification for Wearable Cameras Method

12h30 Closing