AI & softwareResearch findings
MindMem: A Multimodal AI Model for Predicting Advertisement Memorability
Original published 2025.02.26 02:09 KSTAdded to Blackdeck 2026.10.24 16:08 KST
What has changed?
Integrates text, video, and audio data to accurately predict ad memorability
Key points
- Proposes a multimodal model to predict ad memorability using diverse data types
- Achieves Spearman's correlation of 0.631 on LAMBDA and 0.731 on Memento10K
- Video pacing, scene complexity, and emotional resonance are key factors affecting memorability
Connect it to your work
Achieves state-of-the-art performance on LAMBDA and Memento10K datasets
What remains unproven
The abstract reports simulation results; real-world performance is not established by this input.
Originals used for this note
Links open the original publisher in a new tab.