# Movie Summarization via Sparse Graph Construction

arXiv: https://arxiv.org/abs/2012.07536 · HTML: https://mlsanity.com/paper/2012.07536/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Dec 2020.

## Built on by (most cited first, 22 of 22)

- [AutoAD II: The Sequel -- Who, When, and What in Movie Audio Description](https://mlsanity.com/paper/2310.06838/) (2023)
- [IntentVizor: Towards Generic Query Guided Interactive Video Summarization](https://mlsanity.com/paper/2109.14834/) (2021)
- [A Modular Approach for Multimodal Summarization of TV Shows](https://mlsanity.com/paper/2403.03823/) (2024)
- [Finding the Right Moment: Human-Assisted Trailer Creation via Task Composition](https://mlsanity.com/paper/2111.08774/) (2021)
- [Hierarchical3D Adapters for Long Video-to-text Summarization](https://mlsanity.com/paper/2210.04829/) (2022)
- [Match Cutting: Finding Cuts with Smooth Visual Transitions](https://mlsanity.com/paper/2210.05766/) (2022)
- [Select and Summarize: Scene Saliency for Movie Script Summarization](https://mlsanity.com/paper/2404.03561/) (2024)
- [Synopses of Movie Narratives: a Video-Language Dataset for Story Understanding](https://mlsanity.com/paper/2203.05711/) (2022)
- [ScreenWriter: Automatic Screenplay Generation and Movie Summarisation](https://mlsanity.com/paper/2410.19809/) (2024)
- [A Closer Look at Temporal Ordering in the Segmentation of Instructional Videos](https://mlsanity.com/paper/2209.15501/) (2022)
- [MEGA: Multimodal Alignment Aggregation and Distillation For Cinematic Video Segmentation](https://mlsanity.com/paper/2308.11185/) (2023)
- [Unsupervised Audio-Visual Lecture Segmentation](https://mlsanity.com/paper/2210.16644/) (2022)
- [Parameter-free Video Segmentation for Vision and Language Understanding](https://mlsanity.com/paper/2503.01201/) (2025)
- [DiscoGraMS: Enhancing Movie Screen-Play Summarization using Movie Character-Aware Discourse Graph](https://mlsanity.com/paper/2410.14666/) (2024)
- [Contrastive Learning with Narrative Twins for Modeling Story Salience](https://mlsanity.com/paper/2601.07765/) (2026)
- ["Previously on ..." From Recaps to Story Summarization](https://mlsanity.com/paper/2405.11487/) (2024)
- [BEAT: Rhythm-Elastic Alignment for Agentic Music-guided Movie Trailer Generation](https://mlsanity.com/paper/2605.27067/) (2026)
- [REFRAMED: Towards Realistic Audio Description Generation for Movies](https://mlsanity.com/paper/2608.09765/) (2026)
- [MTP: A Dataset for Multi-Modal Turning Points in Casual Conversations](https://mlsanity.com/paper/2409.14801/) (2024)
- [Prompt2LVideos: Exploring Prompts for Understanding Long-Form Multimodal Videos](https://mlsanity.com/paper/2503.08335/) (2025)
- [Integrating Video and Text: A Balanced Approach to Multimodal Summary Generation and Evaluation](https://mlsanity.com/paper/2505.06594/) (2025)
- [Minimal Clips, Maximum Salience: Long Video Summarization via Key Moment Extraction](https://mlsanity.com/paper/2512.11399/) (2025)

## Abstract (arXiv)

We summarize full-length movies by creating shorter videos containing their most informative scenes. We explore the hypothesis that a summary can be created by assembling scenes which are turning points (TPs), i.e., key events in a movie that describe its storyline. We propose a model that identifies TP scenes by building a sparse movie graph that represents relations between scenes and is constructed using multimodal information. According to human judges, the summaries created by our approach are more informative and complete, and receive higher ratings, than the outputs of sequence-based models and general-purpose summarization algorithms. The induced graphs are interpretable, displaying different topology for different movie genres.