Towards Gradient-based Time-Series Explanations through a SpatioTemporal Attention Network

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Lee, Min Hun
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911889656643584
author Lee, Min Hun
author_facet Lee, Min Hun
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_17444
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Gradient-based Time-Series Explanations through a SpatioTemporal Attention Network
Lee, Min Hun
Computer Vision and Pattern Recognition
Machine Learning
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.
title Towards Gradient-based Time-Series Explanations through a SpatioTemporal Attention Network
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2405.17444