385 citations · 1.5k across the 33 of their papers we have counts for
Showing 2016Show all
2 papers · 1 filter
cs.CV2016
Real-time Action Recognition with Enhanced Motion Vector CNNs
Bowen Zhang, Limin Wang, Zhe Wang +2
The deep two-stream architecture exhibited excellent performance on video based action recognition. The most computationally expensive step in this approach comes from the calculat…
cs.CV2016
Actionness Estimation Using Hybrid Fully Convolutional Networks
Limin Wang, Yu Qiao, Xiaoou Tang +1
Actionness was introduced to quantify the likelihood of containing a generic action instance at a specific location. Accurate and efficient estimation of actionness is important in…