Summary of Semi-iin: Semi-supervised Intra-inter Modal Interaction Learning Network For Multimodal Sentiment Analysis, by Jinhao Lin et al.
Semi-IIN: Semi-supervised Intra-inter modal Interaction Learning Network for Multimodal Sentiment Analysis
by Jinhao Lin, Yifei Wang, Yanwu Xu, Qi Liu
First submitted to arxiv on: 13 Dec 2024
Categories
- Main: Computation and Language (cs.CL)
- 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 Medium Difficulty Summary: Despite the promising research area of multimodal sentiment analysis, current approaches rely on high annotation costs and suffer from label ambiguity, making it challenging to acquire high-quality labeled data. To address this issue, we propose Semi-IIN, a Semi-supervised Intra-inter modal Interaction learning Network that integrates masked attention and gating mechanisms to effectively select dynamic intra- and inter-modal interactions. By combining this approach with self-training, Semi-IIN can fully utilize knowledge learned from unlabeled data. Experimental results on MOSI and MOSEI datasets demonstrate the effectiveness of Semi-IIN, achieving a new state-of-the-art on several metrics. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Low Difficulty Summary: This paper is about finding a better way to analyze emotions expressed through different media, like words or images. Right now, this task requires a lot of work and is tricky because emotions can be hard to understand. To solve these problems, the authors created a new method called Semi-IIN that can learn from both labeled and unlabeled data. They tested it on two big datasets and showed that it works better than other methods. |
Keywords
» Artificial intelligence » Attention » Self training » Semi supervised
