Deep-Aligned Convolutional Neural Network for Skeleton-based Action Recognition and Segmentation

Hosseini B, Hammer B (Accepted)
Presented at the 2019 IEEE International Conference on Data Mining (ICDM), Beijing.

Konferenzbeitrag | Angenommen | Englisch
 
Download
OA 3.28 MB
Abstract / Bemerkung
Convolutional neural networks (CNNs) are deep learning frameworks which are well-known for their notable performance in classification tasks. Hence, many skeleton-based action recognition and segmentation (SBARS) algorithms benefit from them in their designs. However, a shortcoming of such applications is the general lack of spatial relationships between the input features in such data types. Besides, non-uniform temporal scalings is a common issue in skeleton-based data streams which leads to having different input sizes even within one specific action category. In this work, we propose a novel deep-aligned convolutional neural network (DACNN) to tackle the above challenges for the particular problem of SBARS. Our network is designed by introducing a new type of filters in the context of CNNs which are trained based on their alignments to the local subsequences in the inputs. These filters result in efficient predictions as well as learning interpretable patterns in the data. We empirically evaluate our framework on real-world benchmarks showing that the proposed DACNN algorithm obtains a competitive performance compared to the state-of-the-art while benefiting from a less complicated yet more interpretable model.
Erscheinungsjahr
2019
Konferenz
2019 IEEE International Conference on Data Mining (ICDM)
Konferenzort
Beijing
Konferenzdatum
2019-11-08 – 2019-11-11
Page URI
https://pub.uni-bielefeld.de/record/2937842

Zitieren

Hosseini B, Hammer B. Deep-Aligned Convolutional Neural Network for Skeleton-based Action Recognition and Segmentation. Presented at the 2019 IEEE International Conference on Data Mining (ICDM), Beijing.
Hosseini, B., & Hammer, B. (Accepted). Deep-Aligned Convolutional Neural Network for Skeleton-based Action Recognition and Segmentation. Presented at the 2019 IEEE International Conference on Data Mining (ICDM), Beijing.
Hosseini, Babak, and Hammer, Barbara. Accepted. “Deep-Aligned Convolutional Neural Network for Skeleton-based Action Recognition and Segmentation”. Presented at the 2019 IEEE International Conference on Data Mining (ICDM), Beijing .
Hosseini, B., and Hammer, B. (Accepted).“Deep-Aligned Convolutional Neural Network for Skeleton-based Action Recognition and Segmentation”. Presented at the 2019 IEEE International Conference on Data Mining (ICDM), Beijing.
Hosseini, B., & Hammer, B., Accepted. Deep-Aligned Convolutional Neural Network for Skeleton-based Action Recognition and Segmentation. Presented at the 2019 IEEE International Conference on Data Mining (ICDM), Beijing.
B. Hosseini and B. Hammer, “Deep-Aligned Convolutional Neural Network for Skeleton-based Action Recognition and Segmentation”, Presented at the 2019 IEEE International Conference on Data Mining (ICDM), Beijing, Accepted.
Hosseini, B., Hammer, B.: Deep-Aligned Convolutional Neural Network for Skeleton-based Action Recognition and Segmentation. Presented at the 2019 IEEE International Conference on Data Mining (ICDM), Beijing (Accepted).
Hosseini, Babak, and Hammer, Barbara. “Deep-Aligned Convolutional Neural Network for Skeleton-based Action Recognition and Segmentation”. Presented at the 2019 IEEE International Conference on Data Mining (ICDM), Beijing, Accepted.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Copyright Statement:
Dieses Objekt ist durch das Urheberrecht und/oder verwandte Schutzrechte geschützt. [...]
Volltext(e)
Titel
Presentation slides
Access Level
OA Open Access
Zuletzt Hochgeladen
2019-11-13T10:25:42Z
MD5 Prüfsumme
1320ac526f6552dbf97f7371de1f79b3


Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Quellen

arXiv: 1911.04969

Suchen in

Google Scholar