Abstract
Current approaches for spatiotemporal action recognition have achieved impressive progress, especially in temporal information processing. Meanwhile, the power of spatial information may be underestimated. Thus, a non-uniform key frame selector is proposed to pick the most representative frames according to the relationship between frames along the temporal dimension. Specifically, the reweight high-level frame features are used to generate an importance score sequence, while the key frames, in each temporal section, are selected based on the above scores. Such selected frames have richer semantic information, which has positive impact on the network training. The proposed model is evaluated on two action recognition, namely datasets HMDB51 and UCF101, and promising accuracy improvement is achieved.

This publication has 22 references indexed in Scilit: