3.8 Proceedings Paper

Deep Progressive Reinforcement Learning for Skeleton-based Action Recognition

Publisher

IEEE
DOI: 10.1109/CVPR.2018.00558

Keywords

-

Funding

  1. National Key Research and Development Program of China [2016YFB1001001]
  2. National Natural Science Foundation of China [61672306, U1713214, 61572271, 61527808]
  3. National 1000 Young Talents Plan Program
  4. National Basic Research Program of China [2014CB349304]
  5. Shenzhen Fundamental Research Fund (Subject Arrangement) [J-CYJ20170412170602564]

Ask authors/readers for more resources

In this paper, we propose a deep progressive reinforcement learning (DPRL) method for action recognition in skeleton-based videos, which aims to distil the most informative frames and discard ambiguous frames in sequences for recognizing actions. Since the choices of selecting representative frames are multitudinous for each video, we model the frame selection as a progressive process through deep reinforcement learning, during which we progressively adjust the chosen frames by taking two important factors into account: (1) the quality of the selected frames and (2) the relationship between the selected frames to the whole video. Moreover, considering the topology of human body inherently lies in a graph-based structure, where the vertices and edges represent the hinged joints and rigid bones respectively, we employ the graph-based convolutional neural network to capture the dependency between the joints for action recognition. Our approach achieves very competitive performance on three widely used benchmarks.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

3.8
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available