Multimodal Memorability: Modeling Effects of Semantics and Decay on Video Memorability
| Autor: | Barry A. McNamara, Allen S. Lee, Camilo Fosco, Vincent Casser, Anelise Newman, Aude Oliva |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Computer science
business.industry Event (computing) 05 social sciences Contrast (statistics) 02 engineering and technology Semantics computer.software_genre 050105 experimental psychology 0202 electrical engineering electronic engineering information engineering Key (cryptography) 020201 artificial intelligence & image processing 0501 psychology and cognitive sciences Artificial intelligence Semantic information business computer Natural language processing Meaning (linguistics) |
| Zdroj: | Computer Vision – ECCV 2020 ISBN: 9783030585167 ECCV (16) |
| DOI: | 10.1007/978-3-030-58517-4_14 |
| Popis: | A key capability of an intelligent system is deciding when events from past experience must be remembered and when they can be forgotten. Towards this goal, we develop a predictive model of human visual event memory and how those memories decay over time. We introduce Memento10k, a new, dynamic video memorability dataset containing human annotations at different viewing delays. Based on our findings we propose a new mathematical formulation of memorability decay, resulting in a model that is able to produce the first quantitative estimation of how a video decays in memory over time. In contrast with previous work, our model can predict the probability that a video will be remembered at an arbitrary delay. Importantly, our approach combines visual and semantic information (in the form of textual captions) to fully represent the meaning of events. Our experiments on two video memorability benchmarks, including Memento10k, show that our model significantly improves upon the best prior approach (by 12% on average). |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|