Summary of A Review Of Multimodal Explainable Artificial Intelligence: Past, Present and Future, by Shilin Sun et al.
A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Future
by Shilin Sun, Wenbin An, Feng Tian, Fang Nan, Qidong Liu, Jun Liu, Nazaraf Shah, Ping Chen
First submitted to arxiv on: 18 Dec 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG); Multimedia (cs.MM)
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 paper proposes Multimodal eXplainable AI (MXAI) to integrate multiple modalities for prediction and explanation tasks in complex reasoning scenarios. This approach aims to enhance human understanding and trust in AI decision-making processes, addressing the “black-box” nature of AI models. The review categorizes MXAI methods across four eras: traditional machine learning, deep learning, discriminative foundation models, and generative LLMs. It also evaluates metrics and datasets used in MXAI research, concluding with future challenges and directions. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary MXAI is a way to make artificial intelligence (AI) more understandable and trustworthy by using multiple types of data, like images or speech, to make predictions and explain how AI makes decisions. The paper looks back at the history of this approach and groups it into four parts: old machine learning methods, deep learning methods, special kinds of models that are good for certain tasks, and large language models. It also talks about what metrics and datasets are used to test these methods and what challenges need to be solved in the future. |
Keywords
» Artificial intelligence » Deep learning » Machine learning
