Predicting human activities using spatio-temporal structure of interest points

Abstract

Early recognition and prediction of human activities are of great importance in video surveillance, e.g., by recognizing a criminal activity at its beginning stage, it is possible to avoid unfortunate outcomes. We address early activity recognition by developing a Spatial-Temporal Implicit Shape Model (STISM), which characterizes the space-time structure of… (More)
DOI: 10.1145/2393347.2396380

Topics

5 Figures and Tables

Statistics

050100150201520162017
Citations per Year

Citation Velocity: 42

Averaging 42 citations per year over the last 3 years.

Learn more about how we calculate this metric in our FAQ.

Cite this paper

@inproceedings{Yu2012PredictingHA, title={Predicting human activities using spatio-temporal structure of interest points}, author={Gang Yu and Junsong Yuan and Zicheng Liu}, booktitle={ACM Multimedia}, year={2012} }