Learning Hierarchical Models of Complex Daily Activities from Annotated Videos

Jawad Tayyub, Majd Hawasly, David C. Hogg, Anthony G. Cohn
<span title="">2018</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wsjivbkuezdvxdnrhihbwjrxlu" style="color: black;">2018 IEEE Winter Conference on Applications of Computer Vision (WACV)</a> </i> &nbsp;
Effective recognition of complex long-term activities is becoming an increasingly important task in artificial intelligence. In this paper, we propose a novel approach for building models of complex long-term activities. First, we automatically learn the hierarchical structure of activities by learning about the 'parent-child' relation of activity components from a video using the variability in annotations acquired using multiple annotators. This variability allows for extracting the inherent
more &raquo; ... ierarchical structure of the activity in a video. We consolidate hierarchical structures of the same activity from different videos into a unified stochastic grammar describing the overall activity. We then describe an inference mechanism to interpret new instances of activities. We use three datasets, which have been annotated by multiple annotators, of daily activity videos to demonstrate the effectiveness of our system.
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/wacv.2018.00182">doi:10.1109/wacv.2018.00182</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/wacv/TayyubHHC18.html">dblp:conf/wacv/TayyubHHC18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/n4ylaqbv7vdlljfkiryp4c6ef4">fatcat:n4ylaqbv7vdlljfkiryp4c6ef4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180724055318/http://eprints.whiterose.ac.uk/128307/1/WACV%202018%20final%20version.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/ce/6f/ce6faeaa07b2943c83b90ea8449210d66fde4395.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/wacv.2018.00182"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>