Media platforms such as social networks, media advertisement, information retrieval and recommendation systems deal with exponentially growing data day after day. Enhancing the relevance of multimedia occurrences in our everyday life requires new ways to organize – in particular, to retrieve – digital content. Like other metrics of video importance, such as aesthetics or interestingness, memorability can be regarded as useful to help make a choice between competing videos. This is even truer when one considers the specific use cases of creating commercials or creating educational content. Because the impact of different multimedia content, images or videos, on human memory is unequal, the capability of predicting the memorability level of a given piece of content is obviously of high importance for professionals in the field of advertising. Beyond advertising, other applications, such as filmmaking, education, content retrieval, etc., may also be impacted by the proposed project. 

This projects proposed a task as part of the MediaEval evaluation campaign.

The task requires participants to automatically predict memorability scores for videos, that reflect the probability for a video to be remembered. Participants will be provided with an extensive data set of videos with memorability annotations, related information, and pre-extracted state-of-the-art visual features. 

You can find more details here.

Example of videos in the training set and their short-term memorability score .

Project members

Team members

Acknowledgements

This project is partially supported by the University of Essex Faculty of Science and Health Research Innovation and Support Fund. (see Neural correlates of memory encoding project).

This work was part-funded by NIST Award No. 60NANB19D155 and by Science Foundation Ireland under grant number SFI/12/RC/2289_P2.

University Politehnica of Bucharest's contribution is supported under project AI4Media, a European Excellence Centre for Media, Society and Democracy, H2020 ICT-48-2020, grant #951911. 

The work of Rukiye Savran Kiziltepe is partially funded by the Turkish Ministry of National Education. This work was part-funded by NIST Award No. 60NANB19D155 and by Science Foundation Ireland under grant number SFI/12/RC/2289_P2.
Quaero supports MediaEval'13 | Quaero

Publications

  1. Kiziltepe, RS., Sweeney, L., Constantin, MG., Doctor, F., García Seco de Herrera, A., Demarty, C-H., Healy, G., Ionescu, B. and Smeaton, AF., (2021). An annotated video dataset for computing video memorability. Data in Brief. 39, 107671-107671
  2. Sweeney, L., Matran-Fernandez, A., Halder, S., Garcia Seco De Herrera, A., Smeaton, A. and Healy, G., Overview of the EEG Pilot Subtask at MediaEval 2021: Predicting Media Memorability
  3. Savran Kiziltepe, R., Constantin, MG., Demarty, C-H., Healy, G., Fosco, C., Garcia Seco De Herrera, A., Halder, S., Ionescu, B., Matran-Fernandez, A., Smeaton, AF. and Sweeney, L., Overview of The MediaEval 2021 Predicting Media Memorability Task
  4. Garcia Seco De Herrera, A., Savran Kiziltepe, R., Chamberlain, J., Constantin, MG., Claire-Hélène, D., Doctor, FAIYAZ., Ionescu, B. and Smeaton, AF., (2020). Overview of MediaEval 2020 Predicting Media Memorability task: What does it Make a Video Memorable?"
  5. Jacutprakart, J., Savran Kiziltepe, R., Gan, J., Papanastasiou, G. and Garcia Seco De Herrera, A., (2020). Essex-NLIP at MediaEval Predicting MediaMemorability 2020 Task
  6. Leyva, R., Doctor, F., Garcia Seco De Herrera, A. and Sahab, S., (2019). Multimodal Deep Features Fusion For Video Memorability Prediction