An Integrated Framework for Multi-Granular Explanation of Video Summarization

TL;DR

This paper introduces an integrated, multi-granular explanation framework for video summarization that identifies influential video fragments and objects, enhancing interpretability of summarization decisions.

Contribution

It extends previous work by combining fragment-level and object-level explanations using a model-agnostic perturbation approach and panoptic segmentation integration.

Findings

Framework accurately identifies influential video fragments and objects.

Quantitative and qualitative evaluations validate the explanation quality.

The approach enhances understanding of video summarization outputs.

Abstract

In this paper, we propose an integrated framework for multi-granular explanation of video summarization. This framework integrates methods for producing explanations both at the fragment level (indicating which video fragments influenced the most the decisions of the summarizer) and the more fine-grained visual object level (highlighting which visual objects were the most influential for the summarizer). To build this framework, we extend our previous work on this field, by investigating the use of a model-agnostic, perturbation-based approach for fragment-level explanation of the video summarization results, and introducing a new method that combines the results of video panoptic segmentation with an adaptation of a perturbation-based explanation approach to produce object-level explanations. The performance of the developed framework is evaluated using a state-of-the-art summarization method and two datasets for benchmarking video summarization. The findings of the conducted quantitative and qualitative evaluations demonstrate the ability of our framework to spot the most and least influential fragments and visual objects of the video for the summarizer, and to provide a comprehensive set of visual-based explanations about the output of the summarization process.