Motionlets: Mid-level 3D Parts for Human Motion Recognition

This paper proposes motionlet, a mid-level and spatiotemporal part, for human motion recognition. Motion let can be seen as a tight cluster in motion and appearance space, corresponding to the moving process of different body parts. We postulate three key properties of motion let for action recognit...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:2013 IEEE Conference on Computer Vision and Pattern Recognition s. 2674 - 2681
Hlavní autori: LiMin Wang, Yu Qiao, Xiaoou Tang
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 01.06.2013
Predmet:
Detectors
Feature extraction
Histograms
Spatiotemporal phenomena
Three-dimensional displays
Vectors
Videos
ISSN:1063-6919, 1063-6919
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:This paper proposes motionlet, a mid-level and spatiotemporal part, for human motion recognition. Motion let can be seen as a tight cluster in motion and appearance space, corresponding to the moving process of different body parts. We postulate three key properties of motion let for action recognition: high motion saliency, multiple scale representation, and representative-discriminative ability. Towards this goal, we develop a data-driven approach to learn motion lets from training videos. First, we extract 3D regions with high motion saliency. Then we cluster these regions and preserve the centers as candidate templates for motion let. Finally, we examine the representative and discriminative power of the candidates, and introduce a greedy method to select effective candidates. With motion lets, we present a mid-level representation for video, called motionlet activation vector. We conduct experiments on three datasets, KTH, HMDB51, and UCF50. The results show that the proposed methods significantly outperform state-of-the-art methods.
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2013.345