Title:
Modeling Actions through State Changes
Modeling Actions through State Changes
Author(s)
Fathi, Alireza
Rehg, James M.
Rehg, James M.
Advisor(s)
Editor(s)
Collections
Supplementary to
Permanent Link
Abstract
in this paper we present a model of action based on the change in the state of the environment. Many actions involve similar dynamics and hand-object relationships, but differ in their purpose and meaning. The key to differentiating these actions is the ability to identify how they change
the state of objects and materials in the environment. We
propose a weakly supervised method for learning the object and material states that are necessary for recognizing
daily actions. Once these state detectors are learned, we
can apply them to input videos and pool their outputs to detect actions. We further demonstrate that our method can be
used to segment discrete actions from a continuous video of
an activity. Our results outperform state-of-the-art action
recognition and activity segmentation results.
Sponsor
Date Issued
2013-06
Extent
Resource Type
Text
Resource Subtype
Post-print
Proceedings
Proceedings