Name
Abstract | ||
|---|---|---|
This paper explores the problem of large-scale automatic video geolocation. A methodology is developed to infer the location at which videos from Anonymized.com were recorded using video content and various additional signals. Specifically, multiple binary Adaboost classifiers are trained to identify particular places based on learning decision stumps on sets of hundreds of thousands of sparse features. A one-vs-all classification strategy is then used to classify the location at which videos were recorded. Empirical validation is performed on an immense data set of 20 million labeled videos. Results demonstrate that high accuracy video geolocation is indeed possible for many videos and locations and interesting relationships exist between between videos and the places where they are recorded. |
Year | DOI | Venue |
|---|---|---|
2011 | 10.1109/ICDMW.2011.88 | ICDM Workshops |
Keywords | Field | DocType |
high accuracy video geolocation,video content,multiple binary adaboost classifier,particular place,interesting relationship,empirical validation,immense data,one-vs-all classification strategy,large-scale automatic video geolocation,decision stump,learning artificial intelligence,image classification | Data mining,AdaBoost,Pattern recognition,Computer science,Geolocation,Artificial intelligence,Contextual image classification,Machine learning | Conference |
Citations | PageRank | References |
1 | 0.36 | 15 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jasper Snoek | 1 | 1051 | 62.71 |
| Luciano Sbaiz | 2 | 84 | 11.42 |
| Hrishikesh Aradhye | 3 | 113 | 10.37 |