Visual interestingness prediction: A benchmark framework and literature review

MG Constantin, LD Ştefan, B Ionescu… - International Journal of …, 2021 - Springer
In this paper, we report on the creation of a publicly available, common evaluation
framework for image and video visual interestingness prediction. We propose a robust data …

Computational understanding of visual interestingness beyond semantics: literature survey and analysis of covariates

MG Constantin, M Redi, G Zen, B Ionescu - ACM Computing Surveys …, 2019 - dl.acm.org
Understanding visual interestingness is a challenging task addressed by researchers in
various disciplines ranging from humanities and psychology to, more recently, computer …

Overview of the ImageCLEF 2022: Multimedia retrieval in medical, social media and nature applications

B Ionescu, H Müller, R Péteri, J Rückert… - … Conference of the Cross …, 2022 - Springer
This paper presents an overview of the ImageCLEF 2022 lab that was organized as part of
the Conference and Labs of the Evaluation Forum–CLEF Labs 2022. ImageCLEF is an …

Annotating, understanding, and predicting long-term video memorability

R Cohendet, K Yadati, NQK Duong… - Proceedings of the 2018 …, 2018 - dl.acm.org
Memorability can be regarded as a useful metric of video importance to help make a choice
between competing videos. Research on computational understanding of video …

Deep learning for predicting image memorability

H Squalli-Houssaini, NQK Duong… - … on acoustics, speech …, 2018 - ieeexplore.ieee.org
Memorability of media content such as images and videos has recently become an
important research subject in computer vision. This paper presents our computation model …

MMTF-14K: a multifaceted movie trailer feature dataset for recommendation and retrieval

Y Deldjoo, MG Constantin, B Ionescu… - Proceedings of the 9th …, 2018 - dl.acm.org
In this paper we propose a new dataset, ie, the MMTF-14K multi-faceted dataset. It is
primarily designed for the evaluation of video-based recommender systems, but it also …

Unsupervised online learning for robotic interestingness with visual memory

C Wang, Y Qiu, W Wang, Y Hu, S Kim… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Autonomous robots frequently need to detect “interesting” scenes to decide on further
exploration, or to decide which data to share for cooperation. These scenarios often require …

Deep multimodal features for movie genre and interestingness prediction

O Ben-Ahmed, B Huet - 2018 international conference on …, 2018 - ieeexplore.ieee.org
In this paper, we propose a multimodal framework for video segment interestingness
prediction based on the genre and affective impact of movie content. We hypothesize that …

[PDF][PDF] Overview of ImageCLEFfusion 2022 Task-Ensembling Methods for Media Interestingness Prediction and Result Diversification.

LD Stefan, MG Constantin… - CLEF (Working …, 2022 - gconstantin.aimultimedialab.ro
The 2022 ImageCLEFfusion task is the first edition of this task, targeting the creation of late
fusion or ensembling methods in two different scenarios:(i) the prediction of media visual …

Stories of love and violence: zero-shot interesting events' classification for unsupervised tv series summarization

A Reboud, I Harrando, P Lisena, R Troncy - Multimedia Systems, 2023 - Springer
In this paper, we propose an unsupervised approach to generate TV series summaries
using screenplays that are composed of dialogue and scenic textual descriptions. In the last …