Watch-n-Patch: Unsupervised Learning of Actions and Relations | IEEE Journals & Magazine | IEEE Xplore

Watch-n-Patch: Unsupervised Learning of Actions and Relations


Abstract:

There is a large variation in the activities that humans perform in their everyday lives. We consider modeling these composite human activities which comprises multiple b...Show More

Abstract:

There is a large variation in the activities that humans perform in their everyday lives. We consider modeling these composite human activities which comprises multiple basic level actions in a completely unsupervised setting. Our model learns high-level co-occurrence and temporal relations between the actions. We consider the video as a sequence of short-term action clips, which contains human-words and object-words. An activity is about a set of action-topics and object-topics indicating which actions are present and which objects are interacting with. We then propose a new probabilistic model relating the words and the topics. It allows us to model long-range action relations that commonly exist in the composite activities, which is challenging in previous works. We apply our model to the unsupervised action segmentation and clustering, and to a novel application that detects forgotten actions, which we call action patching. For evaluation, we contribute a new challenging RGB-D activity video dataset recorded by the new Kinect v2, which contains several human daily activities as compositions of multiple actions interacting with different objects. Moreover, we develop a robotic system that watches and reminds people using our action patching algorithm. Our robotic setup can be easily deployed on any assistive robots.
Published in: IEEE Transactions on Pattern Analysis and Machine Intelligence ( Volume: 40, Issue: 2, 01 February 2018)
Page(s): 467 - 481
Date of Publication: 07 March 2017

ISSN Information:

PubMed ID: 28287959

References

References is not available for this document.