Motion Words: A Text-Like Representation of 3D Skeleton Sequences
- 8 April 2020
- book chapter
- Published by Springer Nature
- Vol. 12035, 527-541
Abstract
There is a growing amount of human motion data captured as a continuous 3D skeleton sequence without any information about its semantic partitioning. To make such unsegmented and unlabeled data efficiently accessible, we propose to transform them into a text-like representation and employ well-known text retrieval models. Specifically, we partition each motion synthetically into a sequence of short segments and quantize the segments into motion words, i.e. compact features with similar characteristics as words in text documents. We introduce several quantization techniques for building motion-word vocabularies and propose application-independent criteria for assessing the vocabulary quality. We verify these criteria on two real-life application scenarios.Keywords
This publication has 21 references indexed in Scilit:
- Effective and efficient similarity searching in motion capture dataMultimedia Tools and Applications, 2017
- Efficient Human Motion Retrieval via Temporal Adjacent Bag of Words and Discriminative Neighborhood Preserving Dictionary LearningIEEE Transactions on Human-Machine Systems, 2017
- Efficient Unsupervised Temporal Segmentation of Motion DataIEEE Transactions on Multimedia, 2016
- PPP-Codes for Large-Scale Similarity Searching2016
- MDPV: metric distance permutation vocabularyInformation Retrieval Journal, 2014
- Using Hand Gestures for Specifying Motion Queries in Sketch-Based Video Retrieval2014
- Introduction to Information Retrieval2008
- Object retrieval with large vocabularies and fast spatial matching2007
- An Information Retrieval System for Motion Capture Data2006
- Video Google: a text retrieval approach to object matching in videos2003