"Towards gradient-based time-series explanations through a spatiotempor" by Min Hun LEE
 

Publication Type

Conference Paper

Version

acceptedVersion

Publication Date

8-2024

Abstract

In this paper, we explore the feasibility of using a transformer-based, spatiotemporal attention network (STAN) for gradient-based time-series explanations. First, we trained the STAN model for video classifications using the global and local views of data and weakly supervised labels on time-series data (i.e. the type of an activity). We then leveraged a gradient-based XAI technique (e.g. saliency map) to identify salient frames of time-series data. According to the experiments using the datasets of four medically relevant activities, the STAN model demonstrated its potential to identify important frames of videos.

Discipline

Artificial Intelligence and Robotics

Research Areas

Intelligent Systems and Optimization

Areas of Excellence

Digital transformation

Publication

IJCAI 2024 Explainable Artificial Intelligence (XAI) Workshop, Virtual Conference, August 15

Identifier

10.48550/arXiv.2405.17444

Publisher

Springer

City or Country

Virtual Conference

Comments

https://sites.google.com/view/xai2024/proceedings?authuser=0 https://arxiv.org/abs/2405.17444

Share

COinS