6 Seconds of Sound and Vision: Creativity in Micro-videos

Abstract

The notion of creativity, as opposed to related concepts such as beauty or interestingness, has not been studied from the perspective of automatic analysis of multimedia content. Meanwhile, short online videos shared on social media platforms, or micro-videos, have arisen as a new medium for creative expression. In this paper we study creative microvideos in an effort to understand the features that make a video creative, and to address the problem of automatic detection of creative content. Defining creative videos as those that are novel and have aesthetic value, we conduct a crowdsourcing experiment to create a dataset of over 3,800 microvideos labelled as creative and non-creative. We propose a set of computational features that we map to the components of our definition of creativity, and conduct an analysis to determine which of these features correlate most with creative video. Finally, we evaluate a supervised approach to automatically detect creative video, with promising results, showing that it is necessary to model both aesthetic value and novelty to achieve optimal classification accuracy.

Visual Affect Around the World

“…Our work is closely related to Multimedia and Vision research that focus on visual aesthetics [22], interestingness [14], popularity [23], and creativity [35]. Our work also relates to research in Cognitive and Social Psychology, especially emotion and culture research [11,30,34], but also neuroaesthetics [41], visual preference [41,44], and social interaction [28].…”

And Now for Something Completely Different

“…Past work has quantified the creativity of visual art as a combination of both novelty and influence using visual features [18]. Redi et al quantify the novelty of short video clips using a similar approach to ours [44], while Khosla et al use image features to predict engagement on social media [32]. Natural language processing has also been applied to measure the novelty of textual content including scientific article abstracts [9,20] and equity crowdfunding campaigns [29].…”

“…Specifically we define novelty as one minus the norm of the Fisher vector of an image over the Gaussian mixture models. This approach is similar in style to a recent method to calculate novelty using a data point's distance to the centroids of a k-means clustering [44].…”

Social Popularity Score

“…A number of studies have attempted to assess the attractiveness of uploaded content using social connections [4], textual information [2], and visual information [2,5,6]. Each of these approaches has its advantages and drawbacks.…”