# Explaining Motion Relevance for Activity Recognition in Video Deep Learning Models

arXiv: https://arxiv.org/abs/2003.14285 · HTML: https://mlsanity.com/paper/2003.14285/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Mar 2020.

## Built on by (most cited first, 7 of 7)

- [Explainable AI: current status and future directions](https://mlsanity.com/paper/2107.07045/) (2021)
- [Automatic Concept Extraction for Concept Bottleneck-based Video Classification](https://mlsanity.com/paper/2206.10129/) (2022)
- [Adaptive occlusion sensitivity analysis for visually explaining video recognition networks](https://mlsanity.com/paper/2207.12859/) (2022)
- [Working memory inspired hierarchical video decomposition with transformative representations](https://mlsanity.com/paper/2204.10105/) (2022)
- [How to Squeeze An Explanation Out of Your Model](https://mlsanity.com/paper/2412.05134/) (2024)
- [LD-ViCE: Latent Diffusion Model for Video Counterfactual Explanations](https://mlsanity.com/paper/2509.08422/) (2025)
- [REVEX: A Unified Framework for Removal-Based Explainable Artificial Intelligence in Video](https://mlsanity.com/paper/2401.11796/) (2024)

## Abstract (arXiv)

A small subset of explainability techniques developed initially for image recognition models has recently been applied for interpretability of 3D Convolutional Neural Network models in activity recognition tasks. Much like the models themselves, the techniques require little or no modification to be compatible with 3D inputs. However, these explanation techniques regard spatial and temporal information jointly. Therefore, using such explanation techniques, a user cannot explicitly distinguish the role of motion in a 3D model's decision. In fact, it has been shown that these models do not appropriately factor motion information into their decision. We propose a selective relevance method for adapting the 2D explanation techniques to provide motion-specific explanations, better aligning them with the human understanding of motion as conceptually separate from static spatial features. We demonstrate the utility of our method in conjunction with several widely-used 2D explanation methods, and show that it improves explanation selectivity for motion. Our results show that the selective relevance method can not only provide insight on the role played by motion in the model's decision -- in effect, revealing and quantifying the model's spatial bias -- but the method also simplifies the resulting explanations for human consumption.