Staff employed at University of Copenhagen – University of Copenhagen

Forward this page to a friend Resize Print Bookmark and Share

CTR > People and Networks > Staff

Automatic identification of head movements in video-recorded conversations: can words help?

Research output: Research - peer-reviewPoster

We present an approach where an SVM classifier learns to classify head movements based on velocity, acceleration, and the third derivative of position with respect to time, jerk. The automatic annotation of new data performs better than the majority baseline and reaches an accuracy of 68 %. We then conduct a statistical analysis of the distribution of words in the annotated data to understand if word features could be used to improve the learning model. We conclude that word features may help increase the accuracy of the model.
Original languageEnglish
Publication date4 Apr 2017
Number of pages3
StatePublished - 4 Apr 2017
EventThe 6th Workshop on Vision and Language - Valencia, Spain
Duration: 4 Apr 20174 Apr 2017


WorkshopThe 6th Workshop on Vision and Language
Internet address


ID: 182426544