MMAICVDec 31, 2020

Investigating Memorability of Dynamic Media

arXiv:2012.15641v1
Originality Synthesis-oriented
AI Analysis

This paper addresses challenges in predicting media memorability for researchers working on dynamic media analysis, but the impact is incremental as it only presents initial results.

The authors identify high-dynamic content in videos and limited dataset size as core challenges for the MediaEval'20 Predicting Media Memorability task. They propose directions to overcome these challenges and present initial results.

The Predicting Media Memorability task in MediaEval'20 has some challenging aspects compared to previous years. In this paper we identify the high-dynamic content in videos and dataset of limited size as the core challenges for the task, we propose directions to overcome some of these challenges and we present our initial result in these directions.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes