Summary of An Integrated Framework For Multi-granular Explanation Of Video Summarization, by Konstantinos Tsigos et al.
An Integrated Framework for Multi-Granular Explanation of Video Summarization
by Konstantinos Tsigos, Evlampios Apostolidis, Vasileios Mezaris
First submitted to arxiv on: 16 May 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper proposes an integrated framework for multi-granular explanation of video summarization. The framework combines methods for producing explanations 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). The framework builds upon previous work by extending a model-agnostic, perturbation-based approach for fragment-level explanation and introducing a new method combining video panoptic segmentation with perturbation-based explanation. The performance of the framework is evaluated using state-of-the-art summarization methods and two datasets for benchmarking video summarization. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps us understand how to summarize videos in a way that shows which parts were most important. It combines two types of explanations: one showing which fragments of the video mattered most, and another highlighting specific objects in the video that influenced the summary. The authors tested their approach using top-notch summarization methods and datasets for evaluating video summaries. |
Keywords
» Artificial intelligence » Summarization
