@inproceedings{03702a278e8f453cb294a2519a2ce352,
title = "Forecasting hands and objects in future frames",
abstract = "This paper presents an approach to forecast future presence and location of human hands and objects. Given an image frame, the goal is to predict what objects will appear in the future frame (e.g., 5 s later) and where they will be located at, even when they are not visible in the current frame. The key idea is that (1) an intermediate representation of a convolutional object recognition model abstracts scene information in its frame and that (2) we can predict (i.e., regress) such representations corresponding to the future frames based on that of the current frame. We present a new two-stream fully convolutional neural network (CNN) architecture designed for forecasting future objects given a video. The experiments confirm that our approach allows reliable estimation of future objects in videos, obtaining much higher accuracy compared to the state-of-the-art future object presence forecast method on public datasets.",
keywords = "Activity prediction, Future location forecast, Object forecast",
author = "Chenyou Fan and Jangwon Lee and Ryoo, \{Michael S.\}",
note = "Publisher Copyright: {\textcopyright} Springer Nature Switzerland AG 2019.; 15th European Conference on Computer Vision, ECCV 2018 ; Conference date: 08-09-2018 Through 14-09-2018",
year = "2019",
doi = "10.1007/978-3-030-11015-4\_12",
language = "English",
isbn = "9783030110147",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "124--137",
editor = "Laura Leal-Taix{\'e} and Stefan Roth",
booktitle = "Computer Vision – ECCV 2018 Workshops, Proceedings",
}