The Open World of Micro-Videos

TL;DR

This paper explores the unique properties of micro-videos, introduces a large labeled dataset, and proposes models to analyze their diverse viewpoints and open-world temporal dynamics for advancing video understanding.

Contribution

It presents a new micro-video dataset with 58,000 tags and develops viewpoint-specific, temporally-evolving models for large-scale video analysis.

Findings

Micro-videos exhibit diverse viewpoints and narrative structures.

The dataset enables research on open-world and temporal dynamics.

Proposed models effectively analyze micro-video content.

Abstract

Micro-videos are six-second videos popular on social media networks with several unique properties. Firstly, because of the authoring process, they contain significantly more diversity and narrative structure than existing collections of video "snippets". Secondly, because they are often captured by hand-held mobile cameras, they contain specialized viewpoints including third-person, egocentric, and self-facing views seldom seen in traditional produced video. Thirdly, due to to their continuous production and publication on social networks, aggregate micro-video content contains interesting open-world dynamics that reflects the temporal evolution of tag topics. These aspects make micro-videos an appealing well of visual data for developing large-scale models for video understanding. We analyze a novel dataset of micro-videos labeled with 58 thousand tags. To analyze this data, we introduce viewpoint-specific and temporally-evolving models for video understanding, defined over state-of-the-art motion and deep visual features. We conclude that our dataset opens up new research opportunities for large-scale video analysis, novel viewpoints, and open-world dynamics.