The MCMI workshop will take place in 2026, in Lyon, France, co-located with ICPR 2026.
| Time | Event |
|---|---|
| 08:30 - 08:40 |
Welcome & opening remarks
Slides
|
| 08:40 - 09:20 |
Keynote: Movement as a Biomarker: Multimodal Analysis of Handwriting and Gait for Cognitive Disorders
|
| Session 1 - Security & Anomaly Detection | |
| 09:20 - 09:40 |
Sunglasses-Region Adversarial Perturbations for Feature-Space Face Recognition Attacks
Slides
|
| 09:40 - 10:00 |
Detect, Anticipate, and Explain Anomalies in Agricultural Robots: A Review
Slides
|
| Coffee break - 10:00 - 10:30 | |
| Session 2 - Vision-Language Retrieval | |
| 10:30 - 10:50 |
SemRank: Semantic Image Retrieval via Knowledge Graph Filtering and CLIP Embeddings
Slides
|
| 10:50 - 11:10 |
Leveraging Phrase-Level Consistency between Images and Texts for Text-Based Person Search
|
| 11:10 - 11:30 |
Evaluating Pre-trained Image Encoders of Vision-Language and Multimodal Models for Synthetic Facial Image Detection
Slides
|
| Session 3 - Real-World & Edge Deployment | |
| 11:30 - 11:50 |
Vision-Language Models for Gait-Based Screening via Zero-Shot and Multimodal In-Context Learning
Slides
|
| 11:50 - 12:10 |
Gaze-based Attention-driven Multimodal Single-Object Inference for Microcontroller-Class Edge Vision
Slides
|
| 12:10 - 12:30 |
Closing remarks & open discussion
Slides
|
Each paper: 15' presentation + 5' Q&A