![](http://vialabdev.science.ontariotechu.ca/wp-content/uploads/2022/02/LearnGenerateRankExplainCoverImage-1024x622.png)
Contributors:
Chris Kim, Xiao Lin, Christopher Collins, Graham W. Taylor, and Mohamed R. Amer
While the computer vision problem of searching for activities in videos is usually addressed by using discriminative models, their decisions tend to be opaque and difficult for people to understand. We propose a case study of a novel machine learning approach for generative searching and ranking of motion capture activities with visual explanation. Instead of directly ranking videos in the database given a text query, our approach uses a variant of Generative Adversarial Networks (GANs) to generate exemplars based on the query and uses them to search for the activity of interest in a large database. Our model is able to achieve comparable results to its discriminative counterpart, while being able to dynamically generate visual explanations. In addition to our searching and ranking method, we present an explanation interface that enables the user to successfully explore the model’s explanations and its confidence by revealing query-based, model-generated motion capture clips that contributed to the model’s decision. Finally, we conducted a user study with 44 participants to show that by using our model and interface, participants benefit from a deeper understanding of the model’s conceptualization of the search query. We discovered that the XAI system yielded a comparable level of efficiency, accuracy, and user-machine synchronization as its black-box counterpart, if the user exhibited a high level of trust for AI explanation.
Case Study Participant Interface
The web-based study interface is available for public access at http://gr.ckprototype.com/.
Publications
-
C. Kim, X. Lin, C. Collins, G. W. Taylor, and M. R. Amer, “Learn, Generate, Rank, Explain: A Case Study of Visual Explanation by Generative Machine Learning”, ACM Trans. Interact. Intell. Syst., vol 11, no 3–4, Aug 2021.
@article{kim2021,
author = {Kim, Chris and Lin, Xiao and Collins, Christopher and Taylor, Graham W. and Amer, Mohamed R.},
title = {Learn, Generate, Rank, Explain: A Case Study of Visual Explanation by Generative Machine Learning},
year = {2021},
issue_date = {December 2021},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
volume = {11},
number = {3–4},
issn = {2160-6455},
url = {doi.org/10.1145/3465407},
doi = {10.1145/3465407},
journal = {ACM Trans. Interact. Intell. Syst.},
month = aug,
articleno = {23},
numpages = {34},
keywords = {model-generated explanation, trust and reliance, Explainable artificial intelligence, user study}
}