CVLGMay 18, 2024

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

arXiv:2405.17444v14 citationsh-index: 1
Originality Synthesis-oriented
AI Analysis

This work addresses the need for explainable AI in time-series analysis, specifically for medical activity recognition, but it appears incremental as it applies existing gradient-based methods to a new model.

The paper tackled the problem of identifying important frames in time-series video data for activity classification using a transformer-based spatiotemporal attention network (STAN) and gradient-based XAI techniques, demonstrating its potential in experiments on four medically relevant activity datasets.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes