Institute Homepage
Institute Homepage DE Sign In

Back

Perceiving Systems Empirical Inference Conference Paper 2019

Local Temporal Bilinear Pooling for Fine-grained Action Parsing

Thumb ticker sm profile1
Perceiving Systems
Yan Zhang
Thumb ticker sm img 20170401 214555 1
Perceiving Systems
Siyu Tang
Guest Scientist
Thumb ticker sm krikamol
Empirical Inference
Krikamol Muandet
Research Group Leader
Cvpr2019 demo v2.001

Fine-grained temporal action parsing is important in many applications, such as daily activity understanding, human motion analysis, surgical robotics and others requiring subtle and precise operations in a long-term period. In this paper we propose a novel bilinear pooling operation, which is used in intermediate layers of a temporal convolutional encoder-decoder net. In contrast to other work, our proposed bilinear pooling is learnable and hence can capture more complex local statistics than the conventional counterpart. In addition, we introduce exact lower-dimension representations of our bilinear forms, so that the dimensionality is reduced with neither information loss nor extra computation. We perform intensive experiments to quantitatively analyze our model and show the superior performances to other state-of-the-art work on various datasets.

Author(s): Yan Zhang and Siyu Tang and Krikamol Muandet and Christian Jarvers and Heiko Neumann
Book Title: Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)
Pages: 12005--12015
Year: 2019
Month: June
Project(s):
Bibtex Type: Conference Paper (inproceedings)
Event Name: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2019
Event Place: Long Beach, USA
URL: https://arxiv.org/abs/1812.01922
Electronic Archiving: grant_archive
Links:
Attachments:

BibTex 

@inproceedings{zhangbilinear2018,
  title = {Local Temporal Bilinear Pooling for Fine-grained Action Parsing},
  booktitle = {Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)},
  abstract = {Fine-grained temporal action parsing is important in many applications, such as daily activity understanding, human motion analysis, surgical robotics and others requiring subtle and precise operations in a long-term period. In this paper we propose a novel bilinear pooling operation, which is used in intermediate layers of a temporal convolutional encoder-decoder net. In contrast to other work, our proposed bilinear pooling is learnable and hence can capture more complex local statistics than the conventional counterpart. In addition, we introduce exact lower-dimension representations of our bilinear forms, so that the dimensionality is reduced with neither information loss nor extra computation. We perform intensive experiments to quantitatively analyze our model and show the superior performances to other state-of-the-art work on various datasets.},
  pages = {12005--12015},
  month = jun,
  year = {2019},
  slug = {bilinear2018},
  author = {Zhang, Yan and Tang, Siyu and Muandet, Krikamol and Jarvers, Christian and Neumann, Heiko},
  url = {https://arxiv.org/abs/1812.01922},
  month_numeric = {6}
}