mlsanityData to 14 Oct 2026

An Experimental Study on Generating Plausible Textual Explanations for Video Summarization

arXiv 2509.26225 ↗First posted 30 Sep 2025cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

In this paper, we present our experimental study on generating plausible textual explanations for the outcomes of video summarization. For the needs of this study, we extend an existing framework for multigranular explanation of video summarization by integrating a SOTA Large Multimodal Model (LLaVA-OneVision) and prompting it to produce natural language descriptions of the obtained visual explanations. Following, we focus on one of the most desired characteristics for explainable AI, the plausibility of the obtained explanations that relates with their alignment with the humans' reasoning and expectations. Using the extended framework, we propose an approach for evaluating the plausibility of visual explanations by quantifying the semantic overlap between their textual descriptions and the textual descriptions of the corresponding video summaries, with the help of two methods for creating sentence embeddings (SBERT, SimCSE). Based on the extended framework and the proposed plausibility evaluation approach, we conduct an experimental study using a SOTA method (CA-SUM) and two datasets (SumMe, TVSum) for video summarization, to examine whether the more faithful explanations are also the more plausible ones, and identify the most appropriate approach for generating plausible textual explanations for video summarization.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 38 references that are in the map. First posted on arXiv 30 Sep 2025.

Builds on

20 of 38 references.

References · 20

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  3. 2014Going Deeper with Convolutionscited by 4,241
  4. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,719
  5. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,173
  6. 2020Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?cited by 599
  7. 2019Unmasking Clever Hans Predictors and Assessing What Machines Really Learncited by 365
  8. 2021Video Summarization Using Deep Neural Networks: A Surveycited by 85
  9. 2024Can ChatGPT Detect DeepFakes? A Study of Using Multimodal Large Language Models for Media Forensicscited by 69
  10. 2022Rethinking Attention-Model Explainability through Faithfulness Violation Testcited by 43
  11. 2019Explainable Video Action Reasoning via Prior Knowledge and State Transitionscited by 33
  12. 2021Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classificationcited by 29
8 more
  1. 2022EVAL: Explainable Video Anomaly Localizationcited by 19
  2. 2020Interpreting video features: a comparison of 3D convolutional networks and convolutional LSTM networkscited by 12
  3. 2021Discrete neural representations for explainable anomaly detectioncited by 12
  4. 2023Why is plausibility surprisingly problematic as an XAI criterion?cited by 9
  5. 2023Causalainer: Causal Explainer for Automatic Video Summarizationcited by 8
  6. 2024T-TAME: Trainable Attention Mechanism for Explaining Convolutional Networks and Vision Transformerscited by 4
  7. 2025Improving the Perturbation-Based Explanation of Deepfake Detectors Through the Use of Adversarially-Generated Samplescited by 2
  8. 2024An Integrated Framework for Multi-Granular Explanation of Video Summarizationcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Realizing Video Summarization from the Path of Language-based Semantic Understanding
  2. 2026Cut to the Chase: Training-free Multimodal Summarization via Chain-of-Events
  3. 2025Summarization of Multimodal Presentations with Vision-Language Models: Study of the Effect of Modalities and Structure
  4. 2024Multimodal Language Models for Domain-Specific Procedural Video Summarization
  5. 2026HAS: Highlight-guided Attention Steering for Multimodal LLM Video Summarization
  6. 2024Personalized Video Summarization by Multimodal Video Understanding
  7. 2026A Systematic Evaluation of Positional Bias in Multi-Video Summarization with MLLMs
  8. 2021UniMS: A Unified Framework for Multimodal Summarization with Knowledge Distillation