Action Recognition with Stacked Fisher Vectors

Representation of video is a vital problem in action recognition. This paper proposes Stacked Fisher Vectors (SFV), a new representation with multi-layer nested Fisher vector encoding, for action recognition. In the first layer, we densely sample large subvolumes from input videos, extract local features, and encode them using Fisher vectors (FVs). The… CONTINUE READING

9 Figures & Tables

Topics

Statistics

05010020142015201620172018
Citations per Year

251 Citations

Semantic Scholar estimates that this publication has 251 citations based on the available data.

See our FAQ for additional information.