Summary of Exploring a Multimodal Fusion-based Deep Learning Network For Detecting Facial Palsy, by Heng Yim Nicole Oo et al.
Exploring a Multimodal Fusion-based Deep Learning Network for Detecting Facial Palsy
by Heng Yim Nicole Oo, Min Hun Lee, Jeong Hoon Lim
First submitted to arxiv on: 26 May 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed algorithmic detection system for facial palsy utilizes multimodal fusion-based deep learning models that combine unstructured data from image frames with structured data from facial expression features. The approach demonstrates improved accuracy and precision compared to traditional methods, which rely on subjective clinical assessments. This paper investigates the efficacy of different data modalities, including RGB images, facial line segments, coordinates of facial landmarks, and facial expression features, using a dataset of 21 facial palsy patients. Experimental results show that multimodal fusion-based models leveraging both image frames and facial expression features achieve the highest precision scores (76.22) while maintaining acceptable recall rates. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A new way to detect facial palsy is being developed using artificial intelligence. This method uses a combination of different types of data, such as images and measurements of facial expressions. The goal is to improve how doctors diagnose facial palsy, which currently relies on time-consuming and subjective evaluations. Researchers tested various approaches using videos of 21 people with facial palsy and found that combining different types of data resulted in the most accurate diagnoses. |
Keywords
» Artificial intelligence » Deep learning » Precision » Recall
