Header logo is ps

Local Temporal Bilinear Pooling for Fine-grained Action Parsing





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
Journal: arXiv preprint arXiv:1812.01922
Year: 2018

Department(s): Empirical Inference, Perceiving Systems
Bibtex Type: Article (article)
Paper Type: Technical Report

URL: https://arxiv.org/abs/1812.01922

Additional (custom) Fields:
code: https://github.com/yz-cnsdqz/TemporalActionParsing-FineGrained

Links: Code (Github)
Attachments: video demo


  title = {Local Temporal Bilinear Pooling for Fine-grained Action Parsing},
  author = {Zhang, Yan and Tang, Siyu and Muandet, Krikamol and Jarvers, Christian and Neumann, Heiko},
  journal = {arXiv preprint arXiv:1812.01922},
  year = {2018},
  url = {https://arxiv.org/abs/1812.01922}