Early Classifying Multimodal Sequences
Not on the map. Why?
Abstract (arXiv)
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%.
Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 12 of its 24 references that are in the map. First posted on arXiv 2 May 2023.
Builds on
12 of 24 references.
References · 12
- 2017Attention Is All You Needcited by 60,106
- 2015Deep Residual Learning for Image Recognitioncited by 51,950
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,304
- 2017Proximal Policy Optimization Algorithmscited by 14,592
- 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,143
- 2019Multimodal Transformer for Unaligned Multimodal Language Sequencescited by 639
- 2022Multimodal Learning with Transformers: A Surveycited by 399
- 2019Multimodal Transformer with Multi-View Visual Representation for Image Captioningcited by 86
- 2021N24News: A New Dataset for Multimodal News Classificationcited by 40
- 2019OmniNet: A unified architecture for multi-modal multi-task learningcited by 25
- 2016Look, Listen and Learn - A Multimodal LSTM for Speaker Identificationcited by 4
- 2023A Policy for Early Sequence Classificationcited by 2
Built on by
Not cited yet.