MediaEval 2022
Multimedia Benchmark Workshop

Table of Contents

Memorability

Overview paper:

• Overview of The MediaEval 2022 Predicting Video Memorability Task
  Lorin Sweeney, Mihai Gabriel Constantin, Claire-Hélène Demarty, Camillo Fosco, Alba Garcia Seco de Herrera, Sebastian Halder, Graham Healy, Bogdan Ionescu, Ana Matran-Fernandez, Alan F. Smeaton, Mushfika Sultana

Working notes papers:

• Modelling of Video Memorability using Ensemble Learning and Transformers
  Muhammad Mustafa Ali Usmani, Sumaiyah Zahid, Muhammad Atif Tahir

• AIMultimediaLab at MediaEval 2022: Predicting Media Memorability Using Video Vision Transformers and Augmented Memorable Moments
  Mihai Gabriel Constantin, Bogdan Ionescu

• Video Memorability Prediction using Deep Features and Loss-based Memorability Distribution Estimation
  Safaa Azzakhnini, Olfa Ben-Ahmed, Christine Fernandez-Maloigne

• Predicting Video Memorability Using a Model Pretrained with Natural Language Supervision
  Mirko Agarla, Luigi Celona, Raimondo Schettini

• Understanding Media Memorability From Event-Related Potential Records And Visual Semantics
  Ricardo Kleinlein, Enrique Rodríguez Sebastián, Fernando Fernández-Martínez

• Multi-model Estimators and Ensemble-based Regressors for Predicting Video Memorability
  Gokul Prakash R, Bhuvana Jayaraman, Eeswara Anvesh Chodisetty, Arjun Mukesh, Mirnalinee T T

Quest for insight papers:

• Textual Analysis for Video Memorability Prediction
  Camille Guinaudeau, Andreu Girbau Xalabarder

• Visual Recognition of the Memento10k dataset: A P300 component ERP study
  Rachelle Hamelink

• Quest for Insight: Predicting Memorability based on Frequency of N-Grams
  Muhammad Mustafa Ali Usmani, Sumaiyah Zahid, Muhammad Atif Tahir

• Diffusing Surrogate Dreams of Video Scenes to Predict Video Memorability
  Lorin Sweeney, Graham Healy, Alan Smeaton

FakeNews

Overview paper:

• Combining Tweets and Connections Graph for FakeNews Detection at MediaEval 2022
  Konstantin Pogorelov, Daniel Thilo Schroeder, Stefan Brenner, Asep Maulana, Johannes Langguth

Working notes papers:

• BERT Based Fake News Detection Model
  Yang Zhang, Yi Shao, Wenbo Wan, Jing Li, Jiande Sun, Xuan Zhang

• Identifying Misinformation Spreaders: A Graph-Based Semi-Supervised Learning Approach
  Atta Ullah, Rabeeh Ayaz Abbasi, Akmal Khattak, Anwar Said

• Graph Neural Network for Fake News Detection and Classification of Unlabelled Nodes at MediaEval 2022
  Asep Maulana, Konstantin Pogorelov, Daniel Thilo Schroeder, Johannes Langguth

• Transformers and GNNs for Fake News Detection
  Stefano Bocconi, Alessandro Patruno, Andrey Malakhov

• Representational Learning for the Detection of COVID Related Conspiracy Spreaders in Online Platforms
  Adrian Giron-Jimenez, Angel Panizo Lledot, Javier Torregrosa, David Camacho

• Classifying Text-Based Conspiracy Tweets related to COVID-19 using Contextualized Word Embeddings
  Abdul Rehman, Rabeeh Ayaz Abbasi, Irfan Ul Haq Qureshi, Akmal Khattak

• Evaluating TF-IDF and Transformers-based models for Detecting COVID-19 related Conspiracies
  Rohullah Akbari

• Detection of COVID-19-Related Conspiracy Theories in Tweets using Transformer-Based Models and Node Embedding Techniques
  Youri Peskine, Paolo Papotti, Raphaël Troncy

• Tackling Covid-19 Conspiracies on Twitter using BERT Ensembles, GPT-3 Augmentation, and Graph NNs
  Damir Korenčić, Ivan Grubišić, Gretel Liz De La Peña Sarracén, Alejandro Hector Toselli, Berta Chulvi, Paolo Rosso

NewsImages

Overview paper:

• News Images in MediaEval 2022
  Benjamin Kille, Andreas Lommatzsch, Özlem Özgöbek, Mehdi Elahi, Duc Tien Dang Nguyen

Working notes papers:

• Cross-modal Networks and Dual Softmax Operation for MediaEval NewsImages 2022
  Damianos Galanopoulos, Vasileios Mezaris

• Image-Text Re-Matching with Zero-shot and Finetuning of CLIP
  Yuta Fukatsu, Masaki Aono

• CLIP Pre-trained Models for Cross-modal Retrieval in NewsImages 2022
  Yang Zhang, Yi Shao, Wenbo Wan, Jing Li, Jiande Sun

• Re-matching Images and News Using CLIP Pretrained Model
  Huu-Nghia Vu, Hai-Dang Nguyen, Minh-Triet Tran

• Textual Concept Expansion for Text-Image Matching within Online News Content
  Mingliang Liang, Martha Larson

• An Ensemble Approach Towards Correlating Articles and their Corresponding Images
  Sudhanva Rajesh, Ashwath Krishnan, Bhaskarjyoti Das

DisasterMM

Overview paper:

• DisasterMM: Multimedia Analysis of Disaster-Related Social Media Data Task at MediaEval 2022
  Stelios Andreadis, Aristeidis Bozas, Ilias Gialampoukidis, Anastasia Moumtzidou, Roberto Fiorin, Francesca Lombardo, Thanassis Mavropoulos, Daniele Norbiato, Stefanos Vrochidis, Michele Ferri, Ioannis Kompatsiaris

Working notes papers:

• Model Fusion for Efficient Flood-Related Twitter Posts Detection
  Stelios Kontogiannis, Georgia Christodoulou, Konstantinos Avgerinakis

• Floods Relevancy and Identification of Location from Twitter Posts using NLP Techniques
  Muhammad Suleman, Muhammad Asif, Tayyab Zamir, Ayaz Mehmood, Jebran Khan, Nasir Ahmad, Kashif Ahmad

• Understanding Fine-tuned BERT Models for Flood Location Extraction on Twitter Data
  Jane Arleth Dela Cruz, Iris Hendrickx, Martha Larson

• HFFD: Hybrid Fusion Based Multimodal Flood Relevance Detection
  Yi Shao, Yang Zhang, Ye Jiang, Wenbo Wan, Jing Li, Jiande Sun

• Relevance Classification of Flood-related Twitter Posts via Multiple Transformers
  Wisal Mukhtiar, Waliiya Rizwan, Aneela Habib, Yasir Saleem Afridi, Laiq Hassan, Kashif Ahmad

Urban Air Quality

Overview paper:

• Overview of MediaEval 2022 Urban Air: Urban Life and Air Pollution
  Minh-Son Dao, Thanh-Hai Dang, Tan Loc Nguyen Tai, Thanh Binh Nguyen, Duc Tien Dang Nguyen

Working notes papers:

• HCMUS in MediaEval 2022 - Urban Air - Periodic frequent pattern discovery
  Duc-Huy Tran, Vinh-Thuyen Nguyen-Truong, Xuan-Cuong Le, Minh-Triet Tran, Hai-Dang Nguyen

• Forecasting Long-Term Urban Air Quality Index using Multi-Model
  Khanh-Linh Vo, Gia-Nghi Phuc-Nguyen, Nhat-Hao Pham, Tuong-Nghiem Diep

• Time Series Prediction Of AQI using Facebook Prophet and YOLOV5
  Omer Qureshi, Muhammad Osaid, Muhammad Atif Tahir, Muhammad Nouman Durrani

• Managing Large Dataset Gaps in Urban Air Quality Prediction: DCU-Insight-AQ at MediaEval 2022
  Dinh Viet Cuong, Phuc H. Le-Khac, Adam Stapleton, Elke Eichlemann, Mark Roantree, Alan Smeaton

• CNN-GRU for Air Quality Index Forecasting
  Van-Tien Nguyen, Hai-Dang Nguyen, Minh-Triet Tran

SportsVideo

Overview paper:

• Sport Task: Fine Grained Action Detection and Classification of Table Tennis Strokes from Videos for MediaEval 2022
  Pierre-Etienne Martin, Jordan Calandre, Boris Mansencal, Jenny Benois-Pineau, Renaud Péteri, Laurent Mascarilla, Julien Morlier

Working notes papers:

• Baseline Method for the Sport Task of MediaEval 2022 with 3D CNNs using Attention Mechanism
  Pierre-Etienne Martin

• Fine-Grained Action Detection with RGB and Pose Information using Two Stream Convolutional Networks
  Leonard Hacker, Finn Bartels, Pierre-Etienne Martin

MUSTI

Overview paper:

• MUSTI - Multimodal Understanding of Smells in Texts and Images at MediaEval 2022
  Ali Hürriyetoğlu, Teresa Paccosi, Stefano Menini, Mathias Zinnen, Pasquale Lisena, Kiymet Akdemir, Raphaël Troncy, Marieke van Erp

Working notes papers:

• Multilingual Text-Image Olfactory Object Matching Based on Object Detection
  Yi Shao, Yang Zhang, Wenbo Wan, Jing Li, Jiande Sun

• Multimodal and Multilingual Understanding of Smells using VilBERT and mUNITER
  Kiymet Akdemir, Ali Hürriyetoğlu, Raphaël Troncy, Teresa Paccosi, Stefano Menini, Mathias Zinnen, Vincent Christlein

Medico

Overview paper:

• Medico Multimedia Task at MediaEval 2022: Transparent Tracking of Spermatozoa
  Vajira Thambawita, Steven Hicks, Andrea Storås, Jorunn Andersen, Oliwia Witczak, Trine B. Haugen, Hugo Hammer, Thu Nguyen, Pål Halvorsen, Michael Riegler

Working notes papers:

• Tail-Aware Sperm Analysis for Transparent Tracking of Spermatozoa
  Tuan-Luc Huynh, Huu-Hung Nguyen, Xuan-Nhat Hoang, Thao Thi Phuong Dao, Tien-Phat Nguyen, Viet-Tham Huynh, Hai-Dang Nguyen, Trung-Nghia Le, Minh-Triet Tran

• Tracking of Spermatozoa by YOLOv5 Detection and StrongSORT with OSNet Tracker
  Martin Kosela, Jakub Aszyk, Mateusz Jarek, Jakub Klimek, Tomasz Prokop

Njord

Overview paper:

• NjordVid: A Fishing Trawler Video Analytics Task
  Tor-Arne Nordmo, Aril Ovesen, Håvard Johansen, Dag Johansen, Michael Riegler

Quest for insight papers:

• Addressing Generalization Failure in Deep Detection Models for Fishing Trawler Video Analytics
  Birk Torpmann-Hagen, Pål Halvorsen, Michael Riegler, Dag Johansen

SwimTrack

Overview paper:

• SwimTrack: Swimmers and Stroke Rate Detection in Elite Race Videos
  Nicolas Jacquelin, Jaunet Théo, Romain Vuillemot, Stefan Duffner