Abstract | ||
---|---|---|
This work aims to present novel description methods for human action
recognition. Generally, a video sequence can be represented as a collection of
spatial temporal words by detecting space-time interest points and describing
the unique features around the detected points (Bag of Words representation).
Interest points as well as the cuboids around them are considered informative
for feature description in terms of both the structural distribution of
interest points and the information content inside the cuboids. Our proposed
description approaches are based on this idea and making the feature
descriptors more discriminative. |
Year | Venue | Keywords |
---|---|---|
2011 | Clinical Orthopaedics and Related Research | bag of words,information content,human computer interaction,space time |
DocType | Volume | Citations |
Journal | abs/1101.0 | 1 |
PageRank | References | Authors |
0.36 | 25 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ruoyun Gao | 1 | 33 | 1.65 |
Michael S. Lew | 2 | 2742 | 166.02 |
Ling Shao | 3 | 5424 | 249.92 |