# Explainable Deep Learning for Video Recognition Tasks: A Framework & Recommendations

arXiv: https://arxiv.org/abs/1909.05667 · HTML: https://mlsanity.com/paper/1909.05667/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Sep 2019.

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

- [A Deeper Dive Into What Deep Spatiotemporal Networks Encode: Quantifying Static vs. Dynamic Information](https://mlsanity.com/paper/2206.02846/) (2022)
- [Is Appearance Free Action Recognition Possible?](https://mlsanity.com/paper/2207.06261/) (2022)
- [TV-TREES: Multimodal Entailment Trees for Neuro-Symbolic Video Reasoning](https://mlsanity.com/paper/2402.19467/) (2024)
- [Quantifying and Learning Static vs. Dynamic Information in Deep Spatiotemporal Networks](https://mlsanity.com/paper/2211.01783/) (2022)
- [Temporal Relevance Analysis for Video Action Models](https://mlsanity.com/paper/2204.11929/) (2022)
- [Object-ABN: Learning to Generate Sharp Attention Maps for Action Recognition](https://mlsanity.com/paper/2207.13306/) (2022)
- [Evaluating the Faithfulness of Saliency-based Explanations for Deep Learning Models for Temporal Colour Constancy](https://mlsanity.com/paper/2211.07982/) (2022)

## Abstract (arXiv)

The popularity of Deep Learning for real-world applications is ever-growing. With the introduction of high performance hardware, applications are no longer limited to image recognition. With the introduction of more complex problems comes more and more complex solutions, and the increasing need for explainable AI. Deep Neural Networks for Video tasks are amongst the most complex models, with at least twice the parameters of their Image counterparts. However, explanations for these models are often ill-adapted to the video domain. The current work in explainability for video models is still overshadowed by Image techniques, while Video Deep Learning itself is quickly gaining on methods for still images. This paper seeks to highlight the need for explainability methods designed with video deep learning models, and by association spatio-temporal input in mind, by first illustrating the cutting edge for video deep learning, and then noting the scarcity of research into explanations for these methods.