Abstract | ||
---|---|---|
We explore the feasibility of utilizing large, crowd-generated online repositories to construct prior knowledge models for high-level activity recognition. Towards this, we mine the popular location-based social network, Foursquare, for geo-tagged activity reports. Although unstructured and noisy, we are able to extract, categorize and geographically map people's activities, thereby answering the question: what activities are possible where? Through Foursquare text only, we obtain a testing accuracy of 59.2% with 10 activity categories; using additional contextual cues such as venue semantics, we obtain an increased accuracy of 67.4%. By mapping prior odds of activities via geographical coordinates, we directly benefit activity recognition systems built on geo-aware mobile phones. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1145/2493988.2494343 | ISWC |
Keywords | Field | DocType |
increased accuracy,high-level activity recognition,activity category,testing accuracy,social data,geo-tagged activity report,foursquare text,prior odds,activity recognition system,prior knowledge model,human activity,additional contextual cue,activity recognition,web mining | Categorization,World Wide Web,Social network,Activity recognition,Web mining,Computer science,Geographic coordinate system,Odds,Semantics | Conference |
Citations | PageRank | References |
3 | 0.38 | 5 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zack Zhu | 1 | 67 | 5.52 |
Ulf Blanke | 2 | 699 | 36.03 |
Alberto Calatroni | 3 | 375 | 23.43 |
Gerhard Tröster | 4 | 2493 | 250.70 |