Grounding Action Descriptions in Videos

Michaela Regneri, Marcus Rohrbach, Dominikus Wetzel, Stefan Thater, Bernt Schiele, Manfred Pinkal

Abstract


Recent work has shown that the integration of visual information into text-based models can substantially improve model predictions, but so far only visual information extracted from static images has been used. In this paper, we consider the problem of grounding sentences describing actions in visual information extracted from videos. We present a general purpose corpus that aligns high quality videos with multiple natural language descriptions of the actions portrayed in the videos, together with an annotation of how similar the action descriptions are to each other. Experimental results demonstrate that a text-based model of similarity between actions improves substantially when combined with visual information from videos depicting the described actions.


Refbacks

  • There are currently no refbacks.


Copyright (c) 2013 Association for Computational Linguistics

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.