output
20012024
most citedCDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videos

60 citations

researchers with a paper here

Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.

collaborating institutions
Showing 2017 · cs.CVShow all

1 paper · 2 filters

cs.CV2017★ 60 cited

CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videos

Zheng Shou, Jonathan Chan, Alireza Zareian +2

Temporal action localization is an important yet challenging problem. Given a long, untrimmed video consisting of multiple action instances and complex background contents, we need…