Commit 90377209 authored by Tediloma's avatar Tediloma
Browse files

paper ver 2.3

parent d7f225b0
......@@ -20,8 +20,8 @@
\citation{kopuk2019realtime}
\citation{estevam2020zeroshot}
\citation{perez2017effectiveness}
\@writefile{toc}{\contentsline {section}{\numberline {1}\hskip -1em.\nobreakspace {}Introduction}{1}{section.1}}
\@writefile{toc}{\contentsline {section}{\numberline {2}\hskip -1em.\nobreakspace {}Method}{1}{section.2}}
\@writefile{toc}{\contentsline {section}{\numberline {1}\hskip -1em.\nobreakspace {}Introduction}{1}{section.1}\protected@file@percent }
\@writefile{toc}{\contentsline {section}{\numberline {2}\hskip -1em.\nobreakspace {}Method}{1}{section.2}\protected@file@percent }
\newlabel{method}{{2}{1}{\hskip -1em.~Method}{section.2}{}}
\citation{jasani2019skeleton}
\citation{jasani2019skeleton}
......@@ -36,28 +36,29 @@
\citation{sung2018learning}
\citation{sung2018learning}
\citation{sung2018learning}
\@writefile{lof}{\contentsline {figure}{\numberline {1}{\ignorespaces Overview of the network modules.}}{2}{figure.1}}
\@writefile{lof}{\contentsline {figure}{\numberline {1}{\ignorespaces Overview of the network modules.}}{2}{figure.1}\protected@file@percent }
\newlabel{architecture}{{1}{2}{Overview of the network modules}{figure.1}{}}
\@writefile{toc}{\contentsline {subsection}{\numberline {2.1}\hskip -1em.\nobreakspace {}Architecture}{2}{subsection.2.1}}
\@writefile{toc}{\contentsline {subsection}{\numberline {2.2}\hskip -1em.\nobreakspace {}Augmentation}{2}{subsection.2.2}}
\@writefile{toc}{\contentsline {subsubsection}{\numberline {2.2.1}Descriptive labels}{2}{subsubsection.2.2.1}}
\@writefile{toc}{\contentsline {subsection}{\numberline {2.1}\hskip -1em.\nobreakspace {}Architecture}{2}{subsection.2.1}\protected@file@percent }
\@writefile{toc}{\contentsline {subsection}{\numberline {2.2}\hskip -1em.\nobreakspace {}Augmentation}{2}{subsection.2.2}\protected@file@percent }
\@writefile{toc}{\contentsline {subsubsection}{\numberline {2.2.1}Descriptive labels}{2}{subsubsection.2.2.1}\protected@file@percent }
\citation{ma2019nlpaug}
\citation{liu2019roberta}
\citation{Liu_2020}
\citation{reimers2019sentencebert}
\citation{gupta2021syntactically}
\citation{sung2018learning}
\@writefile{lot}{\contentsline {table}{\numberline {1}{\ignorespaces Three descriptive labels for the class "Squat down".}}{3}{table.1}}
\@writefile{lot}{\contentsline {table}{\numberline {1}{\ignorespaces Three descriptive labels for the class "Squat down".}}{3}{table.1}\protected@file@percent }
\newlabel{tab:multi_label}{{1}{3}{Three descriptive labels for the class "Squat down"}{table.1}{}}
\@writefile{lot}{\contentsline {table}{\numberline {2}{\ignorespaces Descriptive label and two automatic augmentations for "Squat down".}}{3}{table.2}}
\@writefile{lot}{\contentsline {table}{\numberline {2}{\ignorespaces Descriptive label and two automatic augmentations for "Squat down".}}{3}{table.2}\protected@file@percent }
\newlabel{tab:auto_aug}{{2}{3}{Descriptive label and two automatic augmentations for "Squat down"}{table.2}{}}
\@writefile{toc}{\contentsline {subsubsection}{\numberline {2.2.2}Multiple labels per class}{3}{subsubsection.2.2.2}}
\@writefile{toc}{\contentsline {subsubsection}{\numberline {2.2.3}Automatic augmentation}{3}{subsubsection.2.2.3}}
\@writefile{toc}{\contentsline {subsection}{\numberline {2.3}\hskip -1em.\nobreakspace {}Experiments}{3}{subsection.2.3}}
\@writefile{lot}{\contentsline {table}{\numberline {3}{\ignorespaces ZSL and GZSL results for different approaches.}}{3}{table.3}}
\@writefile{toc}{\contentsline {subsubsection}{\numberline {2.2.2}Multiple labels per class}{3}{subsubsection.2.2.2}\protected@file@percent }
\@writefile{toc}{\contentsline {subsubsection}{\numberline {2.2.3}Automatic augmentation}{3}{subsubsection.2.2.3}\protected@file@percent }
\@writefile{toc}{\contentsline {subsection}{\numberline {2.3}\hskip -1em.\nobreakspace {}Experiments}{3}{subsection.2.3}\protected@file@percent }
\@writefile{lot}{\contentsline {table}{\numberline {3}{\ignorespaces ZSL and GZSL results for different approaches.}}{3}{table.3}\protected@file@percent }
\newlabel{tab:ZSL_GZSL}{{3}{3}{ZSL and GZSL results for different approaches}{table.3}{}}
\@writefile{lot}{\contentsline {table}{\numberline {4}{\ignorespaces Unseen top-1 and top-5 accuracies in detail.}}{3}{table.4}}
\@writefile{lot}{\contentsline {table}{\numberline {4}{\ignorespaces Unseen top-1 and top-5 accuracies in detail.}}{3}{table.4}\protected@file@percent }
\newlabel{tab:top1_top5}{{4}{3}{Unseen top-1 and top-5 accuracies in detail}{table.4}{}}
\@writefile{toc}{\contentsline {section}{\numberline {3}\hskip -1em.\nobreakspace {}Results}{3}{section.3}}
\@writefile{toc}{\contentsline {section}{\numberline {3}\hskip -1em.\nobreakspace {}Results}{3}{section.3}\protected@file@percent }
\citation{jasani2019skeleton}
\citation{ma2019nlpaug}
\bibstyle{ieee_fullname}
......@@ -65,11 +66,11 @@
\bibcite{cao2019openpose}{1}
\bibcite{estevam2020zeroshot}{2}
\bibcite{gupta2021syntactically}{3}
\@writefile{toc}{\contentsline {subsection}{\numberline {3.1}\hskip -1em.\nobreakspace {}Discussion}{4}{subsection.3.1}}
\@writefile{toc}{\contentsline {subsubsection}{\numberline {3.1.1}From default to descriptive labels}{4}{subsubsection.3.1.1}}
\@writefile{toc}{\contentsline {subsubsection}{\numberline {3.1.2}Using multiple labels}{4}{subsubsection.3.1.2}}
\@writefile{toc}{\contentsline {subsubsection}{\numberline {3.1.3}Automatic augmentation}{4}{subsubsection.3.1.3}}
\@writefile{toc}{\contentsline {section}{\numberline {4}\hskip -1em.\nobreakspace {}Conclusion}{4}{section.4}}
\@writefile{toc}{\contentsline {subsection}{\numberline {3.1}\hskip -1em.\nobreakspace {}Discussion}{4}{subsection.3.1}\protected@file@percent }
\@writefile{toc}{\contentsline {subsubsection}{\numberline {3.1.1}From default to descriptive labels}{4}{subsubsection.3.1.1}\protected@file@percent }
\@writefile{toc}{\contentsline {subsubsection}{\numberline {3.1.2}Using multiple labels}{4}{subsubsection.3.1.2}\protected@file@percent }
\@writefile{toc}{\contentsline {subsubsection}{\numberline {3.1.3}Automatic augmentation}{4}{subsubsection.3.1.3}\protected@file@percent }
\@writefile{toc}{\contentsline {section}{\numberline {4}\hskip -1em.\nobreakspace {}Conclusion}{4}{section.4}\protected@file@percent }
\bibcite{jasani2019skeleton}{4}
\bibcite{kopuk2019realtime}{5}
\bibcite{Liu_2020}{6}
......@@ -81,3 +82,4 @@
\bibcite{reimers2019sentencebert}{12}
\bibcite{sung2018learning}{13}
\bibcite{yan2018spatial}{14}
\gdef \@abspage@last{5}
This diff is collapsed.
......@@ -166,11 +166,11 @@ To reduce the manual annotation effort, we would like to generate additional lab
\subsection{Experiments}
In this work we use the NTU RGB+D 120 dataset \cite{Liu_2020}, which contains 3D skeleton data for 114,480 samples of 120 different human action classes. To evaluate our model we pick 40 gestures classes that we split into a subset of 35 seen and 5 unseen classes.
In this work we use the NTU RGB+D 120 dataset \cite{Liu_2020}, which contains 3D skeleton data for 114,480 samples of 120 different human action classes. To evaluate our model we pick a subset of 40 gestures classes to execute four performance tests: one with our default labels as a baseline, and one per augmentation method. A performance test consists of eight training runs on 35/5 (seen/unseen) splits, which are randomized in such a way that every single class is unseen in exactly one training run.
The remaining 80 classes are utilized to train the GCN to ensure that the unseen gestures have not already appeared in the training process at some early point before inference. We execute four performance tests: one with our default labels as a baseline, and one per augmentation method.\\
During training, only the weights of the AN and RN modules are adjusted. The GCN is trained beforehand on the 80 unused classes of the NTU dataset to ensure that the unseen gestures have not already appeared in the training process at some early point before inference and the SBERT module has been trained in \cite{reimers2019sentencebert}.
A performance test consists of eight training runs on 35/5 (seen/unseen) splits, which are randomized in such a way that every single class is unseen in exactly one training run. During training, only the weights of the AN and RN modules are adjusted. All other modules remain unchanged after their individual training. After testing, the accuracies are averaged over the eight individual experiments. For each augmentation method we test the performance in two scenarios: In the ZSL scenario, the model only predicts on the unseen classes, while it predicts on all classes (seen and unseen) in the GZSL scenario. In the latter we measure the accuracy for seen and unseen samples, as well as the harmonic mean, following recent works \cite{gupta2021syntactically}. For default and descriptive labels, we train our Network with a batch size of 32 and without batch norm, as was done in the original paper \cite{sung2018learning}. For the multi labels however, we used a batch size of 128 and batch norm at the input of the RN.
After testing, the accuracies are averaged over the eight individual experiments. For each augmentation method we test the performance in two scenarios: In the ZSL scenario, the model only predicts on the unseen classes, while it predicts on all classes (seen and unseen) in the GZSL scenario. In the latter we measure the accuracy for seen and unseen samples, as well as the harmonic mean, following recent works \cite{gupta2021syntactically}. For default and descriptive labels, we train our Network with a batch size of 32 and without batch norm, as was done in the original paper \cite{sung2018learning}. For the multi labels however, we used a batch size of 128 and batch norm at the input of the RN.
This was mainly done due to performance reasons because the multi label approach with more than three labels did not learn anything without batch norm at all. %batchnorm in general -> decrease in unseen
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment