Summary of the paper
| Title | Annotation of Human Gesture using 3D Skeleton Controls |
|---|---|
| Authors | Quan Nguyen and Michael Kipp |
| Abstract | The manual transcription of human gesture behavior from video for linguisticanalysis is a work-intensive process that results in a rather coarsedescription of the original motion. We present a novel approach fortranscribing gestural movements: by overlaying an articulated 3D skeleton ontothe video frame(s) the human coder can replicate original motions on apose-by-pose basis by manipulating the skeleton.Our tool is integrated in the ANVIL tool so that both symbolic interval dataand 3D pose data can be entered in a single tool. Our method allows arelatively quick annotation of human poses which has been validated in a userstudy. The resulting data are precise enough to create animations that matchthe original speaker's motion which can be validated with a realtime viewer.The tool can be applied for a variety of research topics in the areas ofconversational analysis, gesture studies and intelligent virtual agents. |
| Language | Tools, systems, applications |
| Topics | Corpus (creation, annotation, etc.), Discourse annotation, representation and processing, Tools, systems, applications |
Full paper  |
Annotation of Human Gesture using 3D Skeleton Controls |
| Bibtex | @InProceedings{NGUYEN10.952, author = {Quan Nguyen and Michael Kipp}, title = {Annotation of Human Gesture using 3D Skeleton Controls}, booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)}, year = {2010}, month = {may}, date = {19-21}, address = {Valletta, Malta}, editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias}, publisher = {European Language Resources Association (ELRA)}, isbn = {2-9517408-6-7}, language = {english} } |