Connecting Vision and Language with Video Localized Narratives

TL;DR

This paper introduces Video Localized Narratives, a new multimodal annotation method linking vision and language in videos, enabling detailed storytelling and grounding for complex events, with extensive dataset creation and benchmark establishment.

Contribution

It presents a novel annotation protocol for videos, creates a large-scale dataset, and establishes benchmarks for video narrative grounding and question answering tasks.

Findings

Annotated 20k videos with 1.7M words

Constructed new benchmarks for video narrative grounding

Provided baseline model results

Abstract

We propose Video Localized Narratives, a new form of multimodal video annotations connecting vision and language. In the original Localized Narratives, annotators speak and move their mouse simultaneously on an image, thus grounding each word with a mouse trace segment. However, this is challenging on a video. Our new protocol empowers annotators to tell the story of a video with Localized Narratives, capturing even complex events involving multiple actors interacting with each other and with several passive objects. We annotated 20k videos of the OVIS, UVO, and Oops datasets, totalling 1.7M words. Based on this data, we also construct new benchmarks for the video narrative grounding and video question answering tasks, and provide reference results from strong baseline models. Our annotations are available at https://google.github.io/video-localized-narratives/.