Walking and talking: A bilinear approach to multi-label action recognition

Sameh Khamis, Larry S. Davis
<span title="">2015</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ilwxppn4d5hizekyd3ndvy2mii" style="color: black;">2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)</a> </i> &nbsp;
Action recognition is a fundamental problem in computer vision. However, all the current approaches pose the problem in a multi-class setting, where each actor is modeled as performing a single action at a time. In this work we pose the action recognition as a multi-label problem, i.e., an actor can be performing any plausible subset of actions. Determining which subsets of labels can co-occur is typically treated as a separate problem, typically modeled sparsely or fixed apriori to label
more &raquo; ... ation coefficients. In contrast, we formulate multi-label training and label correlation estimation as a joint max-margin bilinear classification problem. Our joint approach effectively trains discriminative bilinear classifiers that leverage label correlations. To evaluate our approach we relabeled the UCLA Courtyard dataset for the multi-label setting. We demonstrate that our joint model outperforms baselines on the same task and report state-of-the-art per-label accuracies on the dataset.
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvprw.2015.7301277">doi:10.1109/cvprw.2015.7301277</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cvpr/KhamisD15.html">dblp:conf/cvpr/KhamisD15</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ueal4yqlerhrrn3mknqp45iwhy">fatcat:ueal4yqlerhrrn3mknqp45iwhy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170809070914/http://www.cv-foundation.org/openaccess/content_cvpr_workshops_2015/W04/papers/Khamis_Walking_and_Talking_2015_CVPR_paper.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/2a/9a/2a9a1da7b652ab2dafa627d507ec9a6452f6b17e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvprw.2015.7301277"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>