# Extending Information Bottleneck Attribution to Video Sequences

arXiv: https://arxiv.org/abs/2501.16889 · HTML: https://mlsanity.com/paper/2501.16889/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 34 references that are in the map.
- First posted on arXiv 28 Jan 2025.

## Builds on (most cited first, 22 of 22)

- [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)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [FaceForensics++: Learning to Detect Manipulated Facial Images](https://mlsanity.com/paper/1901.08971/) (2019)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [Evaluating the visualization of what a Deep Neural Network has learned](https://mlsanity.com/paper/1509.06321/) (2015)
- [DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection](https://mlsanity.com/paper/2001.03024/) (2020)
- [Explaining NonLinear Classification Decisions with Deep Taylor Decomposition](https://mlsanity.com/paper/1512.02479/) (2015)
- [Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layers](https://mlsanity.com/paper/1604.00825/) (2016)
- [FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset](https://mlsanity.com/paper/2108.05080/) (2021)
- [Restricting the Flow: Information Bottlenecks for Attribution](https://mlsanity.com/paper/2001.00396/) (2020)
- [Grounding Visual Explanations](https://mlsanity.com/paper/1807.09685/) (2018)
- [AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset](https://mlsanity.com/paper/2311.15308/) (2023)
- [An adversarial attack approach for eXplainable AI evaluation on deepfake detection models](https://mlsanity.com/paper/2312.06627/) (2023)
- [Towards Quantitative Evaluation of Explainable AI Methods for Deepfake Detection](https://mlsanity.com/paper/2404.18649/) (2024)
- [Information Bottleneck Attribution for Visual Explanations of Diagnosis and Prognosis](https://mlsanity.com/paper/2104.02869/) (2021)
- [Towards Gradient-based Time-Series Explanations through a SpatioTemporal Attention Network](https://mlsanity.com/paper/2405.17444/) (2024)
- [Where and When: Space-Time Attention for Audio-Visual Explanations](https://mlsanity.com/paper/2105.01517/) (2021)

## Built on by (most cited first, 1 of 1)

- [EIB-Net: Entropy-Guided Information Bottleneck for Generalizable AI-Generated Image Detection](https://mlsanity.com/paper/2609.29064/) (2026)

## Abstract (arXiv)

We introduce VIBA, a novel approach for explainable video classification by adapting Information Bottlenecks for Attribution (IBA) to video sequences. While most traditional explainability methods are designed for image models, our IBA framework addresses the need for explainability in temporal models used for video analysis. To demonstrate its effectiveness, we apply VIBA to video deepfake detection, testing it on two architectures: the Xception model for spatial features and a VGG11-based model for capturing motion dynamics through optical flow. Using a custom dataset that reflects recent deepfake generation techniques, we adapt IBA to create relevance and optical flow maps, visually highlighting manipulated regions and motion inconsistencies. Our results show that VIBA generates temporally and spatially consistent explanations, which align closely with human annotations, thus providing interpretability for video classification and particularly for deepfake detection.