"Previously on..." from Recaps to Story Summarization
Aditya Kumar Singh, Dhruv Srivastava, Makarand Tapaswi
Abstract
Recap -That's Jack Bauer! -[Jack] Get up or I will kill you right here. -Who is it you're looking for? -I need you to break the story... -Novakovich was just murdered. -... Bauer has no idea...Novakovich was operating under my orders? -It's about the people...murdered your father. -... working under Russian agents. -Bauer contacted Meredith Reed. -You're suggesting muzzling the press? -... Meredith Reed. Call her publisher and demand not to run the story. -... muzzling press. The freedom of press is constitutionally protected? -You are the President. Tell them this story will create a war. -... I don't need to tell what damage your criminal prosecution will do. -You're poison. ... never should have let you do this. -Where's Novakovich? What did he say to Bauer? -Nothing ... was bleeding ... wounded by one of the guards. -... murdered. Bauer learned that Novakovich killed Omar and Renee. -Lunatic was gonna kill me, Yuri. Think of it as sacri cing a rook for a king. -... orders? There's nothing more dangerous than a wounded animal. Figure 1 . We illustrate how TV show recaps can be used to generate labels for multimodal story summarization. The top half features the recap shown at the beginning of the episode S08E23 based on key moments (shots and dialogs) from S08E22 of the TV series 24. As recaps help viewers recall essential story events, we extend these aligned segments to create summarization labels (visualized in the bottom half where the actual shots and dialogs inherited from recap are marked in deep red). For example, in the sub-story (left), the recap hints at Jack Bauer relaying classified information to the press, while the summary presents the complete sub-story, including Logan informing President Taylor about their failure to catch Jack and their disagreement over muzzling the press.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Builds on25
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and GenerationJunnan Li, Dongxu Li, Caiming Xiong, Steven C. H. HoiICML 2022 · 6,549 citations
- PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive SummarizationJingqing Zhang, Yao Zhao, Mohammad Saleh, Peter J. LiuICML 2020 · 2,453 citations
- ViLT: Vision-and-Language Transformer Without Convolution or Region SupervisionWonjae Kim, Bokyung Son, Ildoo KimICML 2021 · 2,258 citations
- MPNet: Masked and Permuted Pre-training for Language UnderstandingKaitao Song, Xu Tan, Tao Qin, Jianfeng Lu et al.NeurIPS 2020 · 1,957 citations
Related papers
- Screenplay Summarization Using Latent Narrative StructurePinelopi Papalampidi, Frank Keller, Lea Frermann, Mirella LapataACL 2020 · 8 citations
- SummScreen: A Dataset for Abstractive Screenplay SummarizationMingda Chen, Zewei Chu, Sam Wiseman, Kevin GimpelACL 2022
- A Modular Approach for Multimodal Summarization of TV ShowsLouis Mahon, Mirella LapataACL 2024 · 1 citation
- Query-Focused Multimodal Summarization with Gate-Guided Mixture-of-ExpertsJiajun Han, Xuran Yang, Hui ZhangACM MM 2025 · 1 citation
- REGen: Multimodal Retrieval-Embedded Generation for Long-to-Short Video EditingWeihan Xu, Yimeng Ma, Jingyue Huang, Yang Li et al.NeurIPS 2025 · 1 citation
