Connecting Vision and Language with Video Localized Narratives
This work addresses the problem of multimodal understanding in videos for researchers, providing a new dataset and benchmarks, but it is incremental as it extends an existing image-based method to video.
The authors tackled the challenge of grounding language in video by introducing Video Localized Narratives, a multimodal annotation protocol that connects spoken words with mouse traces on videos, and they annotated 20k videos with 1.7M words to create new benchmarks for video tasks.
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/.