MediaEval 2025
Multimedia Benchmark Workshop

Table of Contents

NewsImages

Overview paper:

• NewsImages in MediaEval 2025 - Comparing Image Retrieval and Generation for News Articles
  Lucien Heitz, Luca Rossetto, Benjamin Kille, Andreas Lommatzsch, Mehdi Elahi, Duc-Tien Dang-Nguyen

Working notes papers:

• Comparing CLIP-Based Image Retrieval and Stable Diffusion Turbo for News Article Thumbnails
  Sakthi Mukesh Thanga Mariappan, Muthulakshmi Ramasamy, Beulah Arul

• Cross-Modal Image Recommendation for News Articles by Multimodal Foundation Models-Based Retrieval-Reranking
  Damianos Galanopoulos, Andreas Goulas, Vasileios Mezaris

• NewsImages: FAISS-Based Image Retrieval and Stable Diffusion Generation for Diverse News Articles
  Mirunalini P, Yuvashree P H, Harini J, Kawvya M K

• Improving Text-to-image Retrieval of News Articles, Class-aware Fine-tuning of CLIP and the Use of Lead Text
  Bram Bakker, Xiaomeng Wang

• Diffusion-Based Approaches for NewsImage Generation: A Comparative Study of SDXL Variants
  Xiaomeng Wang, Bram Bakker

• Beyond Similarity: Two-Stage Retrieval for News Image Search
  Bulat Khaertdinov, Aashutosh Ganesh, Mirela Popa, Nava Tintarev

• CLIP-Based News Image Retrieval with Keyword-Enriched Prompts for MediaEval 2025 NewsImages Task
  Ramcharan Swaminathan, Sakthivel Thangapandiyan, Mirunalini P, Saravanan Esakki

• Dual-Pipeline Multimedia Enrichment for News Articles via Image Generation and Retrieval
  Dhannya S M, Lakshmi Priya S, Kavinsoorya Ks, Jeeva G, Arivuchezhiyan E, Ashwath Ram T

• Balancing Relevance and Compliance: Text-to-Image Methods for News Articles Visualization
  Alishba Subhani, Mahrukh Khan, Muhammad Rafi, Muhammad Atif Tahir

• Less is More: A Dual-Filtering Perspective on Prompt Design for News Thumbnail Generation
  Nguyen Thanh Khoi

• A Systematic Evaluation of Vision-Language Models for News Image Retrieval: A Two-Stage Retrieve-and-Rerank Pipeline Analysis
  Lakshmi Priya Swaminatha Rao, Dhannya Santhakumari Madhavan, Shrika Thota, Thirumurugan Ravialagappan, Vishal Muralidharan, Shanmugam Karthikeyen Shivaanee

• NewsImages: Retrieval and Generative AI for News Thumbnails
  Sanghamithra Namboodiri, Sadhana J, Samyuktha V

• A Comparative Study of Vision-Language Models for News Image-Headline Matching
  Hemnath Dillibabu, Naren Karthik Kandasamy, Aadhithya Srinivasan Rajashree

Quest for insight papers:

• NewsImages: CLIP-FAISS Retrieval and Diffusion-Based Generation for Editorial News Thumbnails
  Prabavathy Balasundaram, Harshavarthan S, Bharathi A, Swedha S

Medico

Overview paper:

• Medico 2025: Visual Question Answering for Gastrointestinal Imaging
  Sushant Gautam, Vajira Lasantha Thambawita, Michael A. Riegler, Pål Halvorsen, Steven Hicks

Working notes papers:

• A Novel Approach to Medical Visual Question Answering: Integrating Disease Classification, Co-Attention Fusion, and Answer Generation
  Zeshan Khan

• BLIP-2-based Visual Question Answering with Multimodal Explanations for Gastrointestinal Imaging
  Lakshmi Priya S, Dhannya S M, Moogambigai A, Nikhil Karthik S, Pandiarajan D

• From Answers to Explanations: Self-Probing Efficiently Fine-Tuned Vision-Language Models for Medical VQA at Medico 2025
  Sujata Gaihre, Amir Thapa Magar

• Curriculum-Guided Fine-Tuning for Multimodal VQA in GI Endoscopy (Team Lama4Vision)
  Mahdi Azmoodeh-Kalati, Mohammad Sadegh Maghareh, Saba Alavi, Reza Lashgari

• Exploring Vision-Language Models for Medical VQA on Gastrointestinal Images: A LoRA Fine-Tuning Study
  Vishal S, Rajalakshmi Sivanaiah, Angel Deborah Suseelan

• Multi-Task Learning for Visually Grounded Reasoning in Gastrointestinal VQA
  Itbaan Safwan, Muhammad Annas Shaikh, Muhammad Haaris, Ramail Khan, Muhammad Atif Tahir

• X-VQA for GI Diagnostics: Multimodal VQA with Confidence-Aware Explanations
  Krishna Tewari, Sukomal Pal

• LoRA-Enhanced PaliGemma for Efficient Visual Question Answering in Gastrointestinal Imaging
  Prabhash Jha, Firoj Paudel, Debesh Jha

• Enhancing encoder-decoder architecture to visual question answering task for gastrointestinal images
  Minh-Triet Bui, Nam-Tran Nguyen-Thuy, Hai-Dang Nguyen, Minh-Triet Tran

• Medico 2025: Visual Question Answering (with multimodal explanations) for Gastrointestinal Imaging
  Sarath Chandran K R, Sivasriraman P, Vishnu Murugesh V, Vishwajith L K

• Visual Question Answering (with Multimodal Explanations) for Gastrointestinal Imaging
  Prabavathy Balasundaram, Suguneswari K, Ganga B, Pradeep M

Quest for insight papers:

• Towards Reliable VQA Evaluation: Addressing Image and Q\&A Leakage in Kvasir-VQA-x1 (Team Lama4Vision)
  Mohammad Sadegh Maghareh, Mahdi Azmoodeh-Kalati, Saba Alavi, Reza Lashgari

Synthetic Images

Overview paper:

• Synthetic Images at MediaEval 2025: Advancing detection of generative AI in real-world online images
  Olga Papadopoulou, Manos Schinas, Riccardo Corvi, Dimitrios Karageorgiou, Christos Koutlis, Fabrizio Guillaro, Efstratios Gavves, Hannes Mareen, Luisa Verdoliva, Symeon Papadopoulos

Working notes papers:

• Deep Learning-Based Detection and Localization of Generative AI Manipulations in Real-World Images
  Konda Nitish, Jayasree R, Mirunalini P, Ponsubash Raj R

• A CLIP-based Approach for Synthetic Image Detection under Distribution Shift
  Qiushi Li, Andrea Ciamarra, Roberto Caldelli, Stefano Berretti

• An EfficientNet Framework : Methods and Results for Synthetic Image Detection and Manipulation Localization
  Sakthi Mukesh Thanga Mariappan, Muthulakshmi Ramasamy, Beulah Arul

• A three-way Decision-based Synthetic Image Detection
  Zeshan Khan, Zunaira Zainab

• Synthetic vs Real Image Detection using Vision Transformers and CNN-based Architectures
  Noor Ul Huda, Ayesha Fayyaz, Uswa Asad, Yasir Saleem Afridi

• Synthetic Images: Advancing detection of generative AI used in real-world online images
  Avantikaa R, Sangeetha S K, Madhuri B, Vijaya Lakshmi A

• A resolution-agnostic three-stage framework for Image Forgery Detection and Localization
  Minh-Hoang Le, Minh-Khoa Le-Phan, Khanh-Ngoc Vu-Nguyen, Minh-Triet Tran, Trong-Le Do

• Examining Difficulties with CNNs and Segmentation Models for Real-vs. Synthetic Image Detection
  Amrit Gopinath, Amudhan A, Adithya Sivakumar, Vijaya Lakshmi A

• Mattaru Net: Lightweight synthetic image detection using contrastive distilled learning
  Ngoc-Tuan Nguyen, Phuc-Nguyen Lam-Gia, Nhat-Khai Hoang, Duc-Nghi Hoang, Hai-Dang Nguyen

• Detection of generative AI used in real-world online images
  J Bhuvana, S Siddharth Chandrasekar, Ramanan Mahendran, J Pragatheesh

• Real Vs Synthetic Classification using ResNet
  Hafiz Muhammad Owais Raza, Muhammad Atif Tahir, Rizwan Ahmed Khan

Memorability

Overview paper:

• Overview of The MediaEval 2025 Predicting Movie and Commercial Memorability Task
  Iván Martín-Fernández, Mihai Gabriel Constantin, Claire-Hélène Demarty, Manuel Gil-Martín, Sebastian Halder, Bogdan Ionescu, Rukiye Savran Kiziltepe, Ana Matran-Fernandez, Alba G. Seco de Herrera

Working notes papers:

• Exploring Movie Recall Prediction Using Functional Descriptors of the EEG Signal
  Iván Martín-Fernández, Mario Lobo-Alonso, Sergio Esteban-Romero, Manuel Gil-Martín, Fernando Fernández-Martínez

• MediaEval 2025: A Multimodal Approach for Predicting Movie and Commercial Memorability using Stacking and Gradient Boosting
  Sakthi Mukesh Thanga Mariappan, Muthulakshmi Ramasamy, Beulah Arul

• Predicting Movie and Commercial Memorability
  J Bhuvana, Ramanan Mahendran, S Siddharth Chandrasekar, J Pragatheesh

• Multimodal Feature Fusion for Video and Brand Memorability
  Elif Nur Tekay, Irem Azra Isleyen, Murat Karakus, Rukiye Savran Kiziltepe

• Memorability: Predicting movie and commercial memorability using visual and audio features
  Prabavathy Balasundaram, Dhanush Parthasarathy, Tuhina Shaw, Nunna Jahnvi, Praveen M

• DACS-UM-RTL: Early Fusion and Pre-text task learning for Video Memorability Prediction
  Aashutosh Ganesh, Iris Huijben, Bulat Khaertdinov, Iskaj Janssen, Mirela Popa, Nava Tintarev

• LLM-Based Fusion of Multi-modal features for Commercial Memorability Prediction
  Aleksandar Pramov

• Exploring Visual, Textual, And Engagement Features for Memorability Predictions
  Mahnoor Adeel, Kisa Fatima, Muhammad Ibrahim Ayoubi, Mustafa Usmani, Muhammad Atif Tahir

MultiSumm

Overview paper:

• MultiSumm: An AI-Powered System for Automated Multimodal News Summarization
  Dhannya S M, Lakshmi Priya S, Shalini M, Avanthika Vijayakumar, Ranjan S

Working notes papers:

• LLM in Multi-Document Summarisation : MultiSumm Task at MediaEval 2025
  Anastasiia Potiagalova, Gareth Jones

• MultiSumm: Multimodal Summarization Of Multiple Topically Related Websites
  D Swathi, B Swetha, M Aswin

Quest for insight papers:

• MultiSumm - Multimodal Summarisation Task at MediaEval 2025
  Anastasiia Potyagalova, Gareth Jones