Zero-Shot Anticipation for Instructional Activities
Abstract
How can we teach a robot to predict what will happen next for an activity it has never seen before? We address the problem of zero-shot anticipation by presenting a hierarchical model that generalizes instructional knowledge from large-scale text-corpora and transfers the knowledge to the visual domain. Given a portion of an instructional video, our model predicts coherent and plausible actions multiple steps into the future, all in rich natural language. To demonstrate the anticipation capabilities of our model, we introduce the Tasty Videos dataset, a collection of 2511 recipes for zero-shot learning, recognition and anticipation.
Cite
Text
Sener and Yao. "Zero-Shot Anticipation for Instructional Activities." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019. doi:10.1109/ICCV.2019.00095Markdown
[Sener and Yao. "Zero-Shot Anticipation for Instructional Activities." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019.](https://mlanthology.org/iccv/2019/sener2019iccv-zeroshot/) doi:10.1109/ICCV.2019.00095BibTeX
@inproceedings{sener2019iccv-zeroshot,
title = {{Zero-Shot Anticipation for Instructional Activities}},
author = {Sener, Fadime and Yao, Angela},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
year = {2019},
doi = {10.1109/ICCV.2019.00095},
url = {https://mlanthology.org/iccv/2019/sener2019iccv-zeroshot/}
}