Future Person Localization 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.

Accepted to CVPR 2018

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• Unsupervised Learning of Depth and Ego-Motion from Video
• Next-Active-Object prediction from Egocentric Videos
• DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents
• Deep Learning Driven Visual Path Prediction from a Single Image
• First-Person Activity Forecasting with Online Inverse Reinforcement Learning