Abstract | ||
---|---|---|
Discovering knowledge from video data has recently at- tracted growing interest from vision researchers. In this pa- per, we describe a tensor space representation for analyzing human activity patterns in monocular videos. Given a set of moving silhouettes derived from raw video data, the pro- posed methodology first learns a tensor subspace model to embed the silhouettes into low-dimensional projection tra- jectories with preserved temporal order. Symmetric mean Hausdorff distance is then used to measure dissimilarity be- tween the embedded motion trajectories in the tensor sub- space, as the basis for supervised or unsupervised learn- ing. The experimental results on two recent video data sets have shown that the proposed method can effectively ana- lyze human activities with intra- and inter-person variations on both temporal and spatial scales. |
Year | DOI | Venue |
---|---|---|
2007 | 10.1109/ICDMW.2007.107 | ICDM Workshops |
Keywords | Field | DocType |
lyze human activity,video sequences,raw video data,analyzing activity patterns,tensor subspace model,temporal order,recent video data set,video data,human activity pattern,tensor space learning,monocular video,tensor space representation,tensor sub,tensile stress,pixel,computer science,data mining,pattern analysis | Computer vision,Data set,Block-matching algorithm,Tensor,Subspace topology,Computer science,Motion compensation,Hausdorff distance,Artificial intelligence,Motion estimation,Motion analysis | Conference |
ISBN | Citations | PageRank |
0-7695-3033-8 | 10 | 0.68 |
References | Authors | |
17 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Liang Wang | 1 | 4317 | 243.28 |
Christopher Leckie | 2 | 2422 | 155.20 |
Xiaozhe Wang | 3 | 255 | 22.84 |
kotagiri ramamohanarao | 4 | 4716 | 993.87 |
and Jim Bezdek | 5 | 10 | 0.68 |