Summary of Multi-scale Spatio-temporal Graph Convolutional Network For Facial Expression Spotting, by Yicheng Deng et al.
Multi-Scale Spatio-Temporal Graph Convolutional Network for Facial Expression Spotting
by Yicheng Deng, Hideaki Hayashi, Hajime Nagahara
First submitted to arxiv on: 24 Mar 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
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 A novel approach to facial expression spotting is presented in this paper, which addresses the challenges of irrelevant movements and subtle motions in micro-expressions. The Multi-Scale Spatio-Temporal Graph Convolutional Network (SpoT-GCN) is designed to extract robust motion features by tracking both short- and long-term facial muscle movements in adaptive sliding windows. The resulting graph representation is learned through a graph convolutional network, which incorporates local and global features from multiple scales of facial graph structures using the proposed facial local graph pooling (FLGP). To enhance discriminative capability, supervised contrastive learning is introduced. Experimental results on SAMM-LV and CAS(ME)^2 datasets demonstrate state-of-the-art performance, particularly in micro-expression spotting. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps us better understand facial expressions by developing a new way to spot emotions. It’s like trying to read someone’s face to figure out how they’re feeling. The problem is that faces can move around and make it hard to tell the difference between real emotions and fake ones. To solve this, scientists created a special kind of computer program that looks at facial muscles to see if they’re moving in a way that shows an emotion. This program is really good at finding tiny movements on people’s faces that show how they’re feeling. |
Keywords
» Artificial intelligence » Convolutional network » Gcn » Supervised » Tracking
