.png){kind=icon}
.png){kind=icon}
Return
Human action recognition with graph-based multiple-instance learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2015.11.022.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
A new approach to human action recognition from realistic videos is presented in this paper. First, an affine motion model is utilized to compensate background motion for the purpose of extracting dense foreground trajectories. Then, a trajectory spectral embedding is introduced to split up foreground action into multiple spatio-temporal action parts for constructing a mid-level representation. To deal with over segmentation, a novel density discontinuity detector is proposed for the sake of generating semantically salient action parts. Finally, to handle the ambiguity in the training set, action classification is formulated within the multiple-instance learning framework, which a spatio-temporal graph model is incorporated into. Extensive experiments show that the proposed approach achieves competitive results to state of the art on UCF Sports, Kisses/Slaps, YouTube, and Hollywood datasets. (C) 2015 Elsevier Ltd. All rights reserved.
Keywords:
Action recognition
Dense trajectory
Motion compensation
Spectral embedding
Multiple-instance learning
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.