# Class Feature Pyramids for Video Explanation

Source: [Class Feature Pyramids for Video Explanation](<https://www.sota2.com/research/paper/68fa67c71e209131cea18438>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:21:05.859Z

Authors: Alexandros Stergiou, Georgios Kapidis, Grigorios Kalliatakis, Christos Chrysoulas, Ronald Poppe, Remco Veltkamp

Published: 2019-09-18T07:10:32.000Z

## Abstract

Deep convolutional networks are widely used in video action recognition. 3D convolutions are one prominent approach to deal with the additional time dimension. While 3D convolutions typically lead to higher accuracies, the inner workings of the trained models are more difficult to interpret. We focus on creating human-understandable visual explanations that represent the hierarchical parts of spatio-temporal networks. We introduce Class Feature Pyramids, a method that traverses the entire network structure and incrementally discovers kernels at different network depths that are informative for a specific class. Our method does not depend on the network's architecture or the type of 3D convolutions, supporting grouped and depth-wise convolutions, convolutions in fibers, and convolutions in branches. We demonstrate the method on six state-of-the-art 3D convolution neural networks (CNNs) on three action recognition (Kinetics-400, UCF-101, and HMDB-51) and two egocentric action recognition datasets (EPIC-Kitchens and EGTEA Gaze+).

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1909.08611>)

[PDF](<https://arxiv.org/pdf/1909.08611.pdf>)
