Dense Trajectories and Motion Boundary Descriptors for Action Recognition

This paper introduces a video representation based on dense trajectories and motion boundary descriptors. Trajectories capture the local motion information of the video. A dense representation guarantees a good coverage of foreground motion as well as of the surrounding context. A state-of-the-art optical flow algorithm enables a robust and efficient… CONTINUE READING

20 Figures & Tables


Citations per Year

1,156 Citations

Semantic Scholar estimates that this publication has 1,156 citations based on the available data.

See our FAQ for additional information.