Time-series Clustering with Jointly Learning Deep Representations, Clusters and Temporal Boundaries

  title={Time-series Clustering with Jointly Learning Deep Representations, Clusters and Temporal Boundaries},
  author={Panagiotis Tzirakis and Mihalis A. Nicolaou and B. Schuller and S. Zafeiriou},
  journal={2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019)},
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. [...] Key Method 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…Expand
3 Citations
Deep Multivariate Time Series Embedding Clustering via Attentive-Gated Autoencoder
  • 1
  • PDF
A Review of Motion Segmentation: Approaches and Major Challenges
Spatio-Temporal Clustering of Traffic Data with Deep Embedded Clustering
  • 1


Joint Unsupervised Learning of Deep Representations and Image Clusters
  • 417
  • Highly Influential
  • PDF
Human Motion Segmentation via Robust Kernel Sparse Subspace Clustering
  • 25
Aligned Cluster Analysis for temporal segmentation of human motion
  • 163
  • Highly Influential
  • PDF
Hierarchical Aligned Cluster Analysis for Temporal Clustering of Human Motion
  • 297
  • PDF
Structured Time Series Analysis for Human Action Segmentation and Recognition
  • 79
Learning A Task-Specific Deep Architecture For Clustering
  • 57
  • PDF
Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering
  • 308
  • PDF
Efficient Unsupervised Temporal Segmentation of Motion Data
  • 45
  • PDF
A Proximity-Aware Hierarchical Clustering of Faces
  • 27
  • PDF