Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Discriminating spatial and temporal relevance in deep Taylor decompositions for explainable activity recognition

Hiley, L., Preece, A., Hicks, Y., Taylor, H. and Marshall, D. 2019. Discriminating spatial and temporal relevance in deep Taylor decompositions for explainable activity recognition. Presented at: 28th International Joint Conference on Artificial Intelligence (IJCAI-19), Macao, China, 10-16 August 2019.

Full text not available from this repository.

Abstract

Current techniques for explainable AI have been applied with some success to image processing. The recent rise of research in video processing has called for similar work n deconstructing and explaining spatio-temporal models. While many techniques are designed for 2D convolutional models, others are inherently applicable to any input domain. One such body of work, deep Taylor decomposition, propagates relevance from the model output distributively onto its input and thus is not restricted to image processing models. However, by exploiting a simple technique that removes motion information, we show that it is not the case that this technique is effective as-is for representing relevance in non-image tasks. We instead propose a discriminative method that produces a naïve representation of both the spatial and temporal relevance of a frame as two separate objects. This new discriminative relevance model exposes relevance in the frame attributed to motion, that was previously ambiguous in the original explanation. We observe the effectiveness of this technique on a range of samples from the UCF-101 action recognition dataset, two of which are demonstrated in this paper.

Item Type: Conference or Workshop Item (Paper)
Status: In Press
Schools: Engineering
Last Modified: 03 Jun 2020 13:30
URI: http://orca.cf.ac.uk/id/eprint/132146

Actions (repository staff only)

Edit Item Edit Item