Moments in Time Dataset: one million videos for event understanding

TL;DR

The Moments in Time Dataset is a large-scale collection of one million short videos annotated with event labels, designed to advance models in understanding complex, multi-modal dynamic events within three seconds.

Contribution

It introduces a comprehensive, human-annotated video dataset with diverse event classes and analyzes its scale, diversity, and baseline model performance across multiple modalities.

Findings

Dataset contains one million videos with 339 event classes.

Baseline models show challenges in multi-modal event understanding.

Dataset offers a new benchmark for complex event recognition.

Abstract

We present the Moments in Time Dataset, a large-scale human-annotated collection of one million short videos corresponding to dynamic events unfolding within three seconds. Modeling the spatial-audio-temporal dynamics even for actions occurring in 3 second videos poses many challenges: meaningful events do not include only people, but also objects, animals, and natural phenomena; visual and auditory events can be symmetrical in time ("opening" is "closing" in reverse), and either transient or sustained. We describe the annotation process of our dataset (each video is tagged with one action or activity label among 339 different classes), analyze its scale and diversity in comparison to other large-scale video datasets for action recognition, and report results of several baseline models addressing separately, and jointly, three modalities: spatial, temporal and auditory. The Moments in Time dataset, designed to have a large coverage and diversity of events in both visual and auditory modalities, can serve as a new challenge to develop models that scale to the level of complexity and abstract reasoning that a human processes on a daily basis.