# REVEX: A Unified Framework for Removal-Based Explainable Artificial Intelligence in Video

arXiv: https://arxiv.org/abs/2401.11796 · HTML: https://mlsanity.com/paper/2401.11796/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 48 references that are in the map.
- First posted on arXiv 22 Jan 2024.

## Builds on (most cited first, 28 of 28)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [Distribution-Free Predictive Inference For Regression](https://mlsanity.com/paper/1604.04173/) (2016)
- [Interpretable Explanations of Black Boxes by Meaningful Perturbation](https://mlsanity.com/paper/1704.03296/) (2017)
- [Top-down Neural Attention by Excitation Backprop](https://mlsanity.com/paper/1608.00507/) (2016)
- [Understanding Deep Networks via Extremal Perturbations and Smooth Masks](https://mlsanity.com/paper/1910.08485/) (2019)
- [Explaining NonLinear Classification Decisions with Deep Taylor Decomposition](https://mlsanity.com/paper/1512.02479/) (2015)
- [Explaining by Removing: A Unified Framework for Model Explanation](https://mlsanity.com/paper/2011.14878/) (2020)
- [Temporal Pyramid Network for Action Recognition](https://mlsanity.com/paper/2004.03548/) (2020)
- [TAM: Temporal Adaptive Module for Video Recognition](https://mlsanity.com/paper/2005.06803/) (2020)
- [Black-box Explanation of Object Detectors via Saliency Maps](https://mlsanity.com/paper/2006.03204/) (2020)
- [ETRI-Activity3D: A Large-Scale RGB-D Dataset for Robots to Recognize Daily Activities of the Elderly](https://mlsanity.com/paper/2003.01920/) (2020)
- [Saliency Tubes: Visual Explanations for Spatio-Temporal Convolutions](https://mlsanity.com/paper/1902.01078/) (2019)
- [Assessing Fidelity in XAI post-hoc techniques: A Comparative Study with Ground Truth Explanations Datasets](https://mlsanity.com/paper/2311.01961/) (2023)
- [Class Feature Pyramids for Video Explanation](https://mlsanity.com/paper/1909.08611/) (2019)
- [Explaining Motion Relevance for Activity Recognition in Video Deep Learning Models](https://mlsanity.com/paper/2003.14285/) (2020)
- [Discriminating Spatial and Temporal Relevance in Deep Taylor Decompositions for Explainable Activity Recognition](https://mlsanity.com/paper/1908.01536/) (2019)
- [Understanding Patch-Based Learning by Explaining Predictions](https://mlsanity.com/paper/1806.06926/) (2018)

## Abstract (arXiv)

We developed REVEX, a removal-based video explanations framework. This work extends fine-grained explanation frameworks for computer vision data and adapts six existing techniques to video by adding temporal information and local explanations. The adapted methods were evaluated across networks, datasets, image classes, and evaluation metrics. By decomposing explanation into steps, strengths and weaknesses were revealed in the studied methods, for example, on pixel clustering and perturbations in the input. Video LIME outperformed other methods with deletion values up to 31% lower and insertion up to 30% higher, depending on method and network. Video RISE achieved superior performance in the average drop metric, with values 10% lower. In contrast, localization-based metrics revealed low performance across all methods, with significant variation depending on network. Pointing game accuracy reached 53%, and IoU-based metrics remained below 20%. Drawing on the findings across XAI methods, we further examine the limitations of the employed XAI evaluation metrics and highlight their suitability in different applications.