ML Anthology

Robust-MSA: Understanding the Impact of Modality Noise on Multimodal Sentiment Analysis

Huisheng Mao, Baozheng Zhang, Hua Xu, Ziqi Yuan, Yihe Liu
AAAI 2023 pp. 16458-16460
doi:10.1609/AAAI.V37I13.27078 /aaai/2023/mao2023aaai-robust/

Abstract

Improving model robustness against potential modality noise, as an essential step for adapting multimodal models to real-world applications, has received increasing attention among researchers. For Multimodal Sentiment Analysis (MSA), there is also a debate on whether multimodal models are more effective against noisy features than unimodal ones. Stressing on intuitive illustration and in-depth analysis of these concerns, we present Robust-MSA, an interactive platform that visualizes the impact of modality noise as well as simple defence methods to help researchers know better about how their models perform with imperfect real-world data.

PDF AAAI Semantic Scholar

Cite

Text

Mao et al. "Robust-MSA: Understanding the Impact of Modality Noise on Multimodal Sentiment Analysis." AAAI Conference on Artificial Intelligence, 2023. doi:10.1609/AAAI.V37I13.27078

Markdown

[Mao et al. "Robust-MSA: Understanding the Impact of Modality Noise on Multimodal Sentiment Analysis." AAAI Conference on Artificial Intelligence, 2023.](https://mlanthology.org/aaai/2023/mao2023aaai-robust/) doi:10.1609/AAAI.V37I13.27078

BibTeX

@inproceedings{mao2023aaai-robust,
  title     = {{Robust-MSA: Understanding the Impact of Modality Noise on Multimodal Sentiment Analysis}},
  author    = {Mao, Huisheng and Zhang, Baozheng and Xu, Hua and Yuan, Ziqi and Liu, Yihe},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2023},
  pages     = {16458-16460},
  doi       = {10.1609/AAAI.V37I13.27078},
  url       = {https://mlanthology.org/aaai/2023/mao2023aaai-robust/}
}