Early Classifying Multimodal Sequences
This work addresses the need for dynamic classification in sequential data processing for applications like real-time monitoring, though it is incremental as it builds on existing methods.
The paper tackled the problem of early classification for multimodal sequences, which had previously been limited to unimodal data, by combining existing methods and achieved experimental AUC improvements of up to 8.7%.
Often pieces of information are received sequentially over time. When did one collect enough such pieces to classify? Trading wait time for decision certainty leads to early classification problems that have recently gained attention as a means of adapting classification to more dynamic environments. However, so far results have been limited to unimodal sequences. In this pilot study, we expand into early classifying multimodal sequences by combining existing methods. We show our new method yields experimental AUC advantages of up to 8.7%.