Future Person Localization in First-Person Videos

TL;DR

This paper introduces a new task of predicting future locations of people in first-person videos, leveraging ego-motion, scale cues, and pose information to improve localization accuracy.

Contribution

It proposes a novel prediction framework that integrates multiple cues specific to first-person videos for future person localization.

Findings

Effective on a new dataset and a public social interaction dataset.

Outperforms baseline methods in future person localization.

Highlights importance of ego-motion, scale, and pose cues in first-person videos.

Abstract

We present a new task that predicts future locations of people observed in first-person videos. Consider a first-person video stream continuously recorded by a wearable camera. Given a short clip of a person that is extracted from the complete stream, we aim to predict that person's location in future frames. To facilitate this future person localization ability, we make the following three key observations: a) First-person videos typically involve significant ego-motion which greatly affects the location of the target person in future frames; b) Scales of the target person act as a salient cue to estimate a perspective effect in first-person videos; c) First-person videos often capture people up-close, making it easier to leverage target poses (e.g., where they look) for predicting their future locations. We incorporate these three observations into a prediction framework with a multi-stream convolution-deconvolution architecture. Experimental results reveal our method to be effective on our new dataset as well as on a public social interaction dataset.