Temporal Action Localization by Structured Maximal Sums

  title={Temporal Action Localization by Structured Maximal Sums},
  author={Ze-Huan Yuan and Jonathan C. Stroud and Tong Lu and Jia Deng},
  journal={2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
We address the problem of temporal action localization in videos. We pose action localization as a structured prediction over arbitrary-length temporal windows, where each window is scored as the sum of frame-wise classification scores. Additionally, our model classifies the start, middle, and end of each action as separate components, allowing our system to explicitly model each actions temporal evolution and take advantage of informative temporal dependencies present in that structure. In… CONTINUE READING
Highly Cited
This paper has 20 citations. REVIEW CITATIONS
Recent Discussions
This paper has been referenced on Twitter 9 times over the past 90 days. VIEW TWEETS
15 Citations
31 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 15 extracted citations


Publications referenced by this paper.
Showing 1-10 of 31 references

THUMOS challenge: Action recognition with a large number of classes

  • A. Gorban, H. Idrees, +4 authors R. Sukthankar
  • http://crcv.ucf.edu/THUMOS14/
  • 2014
Highly Influential
10 Excerpts

Similar Papers

Loading similar papers…