Abstract
Not every visual media production is equally retained in memory. Recent studies have shown that the elements of an image, as well as their mutual semantic dependencies, provide a strong clue as to whether a video clip will be recalled on a second viewing or not. We believe that short textual descriptions encapsulate most of these relationships among the elements of a video, and thus they represent a rich yet concise source of information to tackle the problem of media memorability prediction. In this paper, we deepen the study of short captions as a means to convey in natural language the visual semantics of a video. We propose to use vector embeddings from a pretrained SBERT topic detection model with no adaptation as input features to a linear regression model, showing that, from such a representation, simpler algorithms can outperform deep visual models. Our results suggest that text descriptions expressed in natural language might be effective in embodying the visual semantics required to model video memorability.
Highlights
The human brain has evolved to potentially hold an incredibly large amount of detailed visual memories for long periods of time, even a lifetime
We propose to use vector embeddings from a pretrained SBERT topic detection model with no adaptation as input features to a linear regression model, showing that, from such a representation, simpler algorithms can outperform deep visual models
Our results suggest that text descriptions expressed in natural language might be effective in embodying the visual semantics required to model video memorability
Summary
The human brain has evolved to potentially hold an incredibly large amount of detailed visual memories for long periods of time, even a lifetime. And opposed to the traditional belief, human memory is not completely subjective, but rather an intrinsic property of an image [1]. We are exposed to huge amounts of video clips, and companies and institutions alike struggle to catch our attention and make their messages persist in our memory. It is in this context that a system able to automatically predict what videos will remain memorable and which ones will be quickly forgotten would have huge applicability, as well as an obvious scientific interest
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
