[visionlist] 1st Call for Participation & registration: MediaEval 2023 Predicting Video Memorability Task

[MIHAI-GABRIEL CONSTANTIN (115317)]

[Apologies for cross-postings]



*******************************************************

1st CALL FOR PARTICIPATION & DEVELOPMENT DATA RELEASE

Predicting Video Memorability Task

2023 MediaEval Benchmarking Initiative for Multimedia Evaluation

https://multimediaeval.github.io/editions/2023/tasks/memorability/

*******************************************************

Register to participate by filling in the MediaEval 2023 Registration form:

https://docs.google.com/forms/d/e/1FAIpQLSfu1TfBZ5PKN1MdTrJFjEKt7r2_qTZw-_WBG8VTgSpT7JWi9A/viewform

*******************************************************


The Predicting Video Memorability Task focuses on the problem of predicting how memorable a video will be. It requires participants to automatically predict memorability scores for videos, which reflect the probability of a video being remembered.


Participants will be provided with an extensive dataset of videos with memorability annotations, related information, pre-extracted state-of-the-art visual features, and electroencephalography (EEG) recordings. The ground truth has been collected through recognition tests, and, for this reason, reflects objective measures of memory performance. In contrast to previous work on image memorability prediction, where memorability was measured a few minutes after memorisation, the dataset comes with short-term and long-term memorability annotations. Because memories continue to evolve in long-term memory, in particular during the first day following memorisation, we expect long-term memorability annotations to be more representative of long-term memory performance, which is used preferably in numerous applications. The outputs of the prediction models – i.e., the predicted memorability scores for the videos – will be compared with ground truth memorability scores using classic evaluation metrics (e.g., Spearman’s rank correlation).


*******************************************************

Generalization subtask 1

*******************************************************

The aim of the Generalization subtask is to check system performance on other types of video data. Participants will train their system on one of the two sources of data we provide and will test them on the other source of data. This is an optional subtask.


*******************************************************

EEG-based prediction subtask 2

*******************************************************

The aim of the Memorability-EEG pilot task is to promote interest in the use of neural signals—either alone, or in combination with other data sources—in the context of predicting video memorability by demonstrating what EEG data can provide. The dataset will be a set of features pre-extracted from the EEG from subjects as they viewed the videos, for a subset of videos from task 1. This task requires participants to automatically predict if a person will remember a video. Participants are required to generate automatic systems that predict if a person will remember a new video based on the given video dataset and their EEG record.


***********************

Target communities

***********************

Researchers will find this task interesting if they work in the areas of human perception and scene understanding, such as image and video interestingness, memorability, attractiveness, aesthetics prediction, event detection, multimedia affect and perceptual analysis, multimedia content analysis, and machine learning (although not limited to these areas).


******************************

Workshop

******************************

Participants to the task are invited to present their results during the annual MediaEval Workshop, which will be held in Bergen, Norway with opportunity for online, on 12-13 January 2023. Working notes proceedings are to appear with CEUR Workshop Proceedings (ceur-ws.org).


******************************

Important dates (tentative)

******************************

25 August 2023: Data release

30 November 2023: Runs due and results returned. Exact dates to be announced.

8 December 2023: Results returned

15 December 2023: Working notes paper

1-2 February 2024: 14th Annual MediaEval Workshop, Collocated with MMM 2024 in Amsterdam, Netherlands and also online.


***********************

Task coordination

***********************

Alba García Seco de Herrera, Sebastian Halder, Ana Matran-Fernandez, University of Essex, UK;

Mihai Gabriel Constantin, Bogdan Ionescu, University Politehnica of Bucharest, Romania;

Lorin Sweeney, Graham Healy, Alan Smeaton, Dublin City University, Ireland;

Claire-Hélène Demarty, InterDigital, R&I, France;

Camilo Fosco, Massachusetts Institute of Technology Cambridge, Massachusetts, USA;

Rukiye Savran Kiziltepe, Karadeniz Technical University, Turkey.


On behalf of the Organisers,

Mihai Gabriel Constantin


-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://visionscience.com/pipermail/visionlist_visionscience.com/attachments/20230919/597f07c6/attachment.html>