van Hout, J., Yeh, E., Koelma, D. C., Snoek, C. G., Sun, C., Nevatia, R., … & Myers, G. K. (2014, May). Late fusion and calibration for multimedia event detection using few examples. In 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 4598-4602). IEEE.
Abstract
The state-of-the-art in example-based multimedia event detection (MED) rests on heterogeneous classifiers whose scores are typically
combined in a late-fusion scheme. Recent studies on this topic have failed to reach a clear consensus as to whether machine learning
techniques can outperform rule-based fusion schemes with varying amount of training data. In this paper, we present two parametric
approaches to late fusion: a normalization scheme for arithmetic mean fusion (logistic averaging) and a fusion scheme based on logistic regression, and compare them to widely used rule-based fusion schemes. We also describe how logistic regression can be used to
calibrate the fused detection scores to predict an optimal threshold given a detection prior and costs on errors. We discuss the advantages and shortcomings of each approach when the amount of positives available for training varies from 10 positives (10Ex) to 100 positives (100Ex). Experiments were run using video data from the NIST TRECVID MED 2013 evaluation and results were reported in terms of a ranking metric: the mean average precision (mAP) and R0, a cost-based metric introduced in TRECVID MED 2013.
Index Terms— multimedia event detection, late fusion, score calibration, score normalization, system fusion