Snoek, C. G. M.; Worring, M.; van Gemert, J. C.; Geusebroek, J. M.; Smeulders, A. W. M. (2006). The challenge problem for automated detection of 101 semantic concepts in multimedia.
mediamill
mldr.datasets::get.mldr("mediamill")
Summary
Instances | 43907 |
---|---|
Attributes | 221 |
Inputs | 120 |
Labels | 101 |
Labelsets | 6555 |
Single labelsets | 4104 |
Max frequency | 2363 |
Cardinality | 4.3756 |
Density | 0.0433 |
Mean IR | 256.4047 |
SCUMBLE | 0.3547 |
TCS | 18.1906 |
Citation
Snoek, C. G. M.; Worring, M.; van Gemert, J. C.; Geusebroek, J. M.; Smeulders, A. W. M. (2006). The challenge problem for automated detection of 101 semantic concepts in multimedia.
@inproceedings{,
title = "The challenge problem for automated detection of 101 semantic concepts in multimedia",
author = "Snoek, C. G. M. and Worring, M. and van Gemert, J. C. and Geusebroek, J. M. and Smeulders, A. W. M.",
booktitle = "Proc. 14th ACM International Conference on Multimedia, MULTIMEDIA06,
year = "2006",
pages = "421--430"
}
Concurrence plot
In this concurrence plot, sectors represent labels and links between them depict label co-occurrences. SCUMBLE is a measure designed to assess the concurrence among imbalanced labels.