Using Saliency and Cropping to Improve Video Memorability
arXiv:2309.11881 · doi:10.1007/978-3-031-53305-1_26
Abstract
Video memorability is a measure of how likely a particular video is to be remembered by a viewer when that viewer has no emotional connection with the video content. It is an important characteristic as videos that are more memorable are more likely to be shared, viewed, and discussed. This paper presents results of a series of experiments where we improved the memorability of a video by selectively cropping frames based on image saliency. We present results of a basic fixed cropping as well as the results from dynamic cropping where both the size of the crop and the position of the crop within the frame, move as the video is played and saliency is tracked. Our results indicate that especially for videos of low initial memorability, the memorability score can be improved.
arXiv comment12 pages
References in corpus (7)
- Learning Transferable Visual Models From Natural Language Supervision
- Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Model
- Review of Visual Saliency Detection with Comprehensive Information
- The Influence of Audio on Video Memorability with an Audio Gestalt Regulated Video Memorability System
- Overview of The MediaEval 2022 Predicting Video Memorability Task
- Overview of The MediaEval 2021 Predicting Media Memorability Task
- Analysing the Memorability of a Procedural Crime-Drama TV Series, CSI