Time-series Clustering with Jointly Learning Deep Representations, Clusters and Temporal Boundaries
Open Access
- 1 May 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Abstract
Clustering and segmentation of temporal data is an important task across several fields, with prominent applications in computer vision and machine learning such as face and gesture segmentation. Several related methods have been proposed in literature, focusing on learning temporal boundaries and clusters, with recent works focusing on learning deep representations for clustering. However, none of the proposed methods is suitable for jointly learning segments, clusters, as well as representations. In this paper, we propose the first methodology that simultaneously discovers suitable deep representations, as well as clusters and temporal boundaries, with the clustering process providing supervisory cues for updating temporal boundaries and training the proposed deep learning architecture. We demonstrate the power of the proposed approach on a human motion segmentation task using the CMU-MMAC database. Our method provides the best results with respect to normalized mutual information compared to other clustering algorithms.Keywords
This publication has 16 references indexed in Scilit:
- A Deep Matrix Factorization Method for Learning Attribute RepresentationsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- FaceNet: A unified embedding for face recognition and clustering2015
- A genetic algorithm approach to human motion capture data segmentationComputer Animation and Virtual Worlds, 2014
- Structured Time Series Analysis for Human Action Segmentation and RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Hierarchical Aligned Cluster Analysis for Temporal Clustering of Human MotionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Graph Degree Linkage: Agglomerative Clustering on a Directed Graph2012
- Learning and Inferring Motion Patterns using Parametric Segmental Switching Linear Dynamic SystemsInternational Journal of Computer Vision, 2007
- Statistical analysis of dynamic actionsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2006
- A Survey of Clustering Data Mining Techniques2006
- Segmenting visual actions based on spatio-temporal motion patterns2002