# Finding the Right Moment: Human-Assisted Trailer Creation via Task Composition

arXiv: https://arxiv.org/abs/2111.08774 · HTML: https://mlsanity.com/paper/2111.08774/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 71 references that are in the map.
- First posted on arXiv 16 Nov 2021.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips](https://mlsanity.com/paper/1906.03327/) (2019)
- [Convolutional Networks on Graphs for Learning Molecular Fingerprints](https://mlsanity.com/paper/1509.09292/) (2015)
- [End-to-End Learning of Visual Representations from Uncurated Instructional Videos](https://mlsanity.com/paper/1912.06430/) (2019)
- [Universal Sentence Encoder](https://mlsanity.com/paper/1803.11175/) (2018)
- [Do Deep Nets Really Need to be Deep?](https://mlsanity.com/paper/1312.6184/) (2013)
- [TVQA: Localized, Compositional Video Question Answering](https://mlsanity.com/paper/1809.01696/) (2018)
- [MovieQA: Understanding Stories in Movies through Question-Answering](https://mlsanity.com/paper/1512.02902/) (2015)
- [Molecular Graph Convolutions: Moving Beyond Fingerprints](https://mlsanity.com/paper/1603.00856/) (2016)
- [Unifying distillation and privileged information](https://mlsanity.com/paper/1511.03643/) (2015)
- [TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval](https://mlsanity.com/paper/2001.09099/) (2020)
- [MovieNet: A Holistic Dataset for Movie Understanding](https://mlsanity.com/paper/2007.10937/) (2020)
- [A Dataset for Movie Description](https://mlsanity.com/paper/1501.02530/) (2015)
- [Spatio-Temporal Graph for Video Captioning with Knowledge Distillation](https://mlsanity.com/paper/2003.13942/) (2020)
- [Condensed Movies: Story Based Retrieval with Contextual Embeddings](https://mlsanity.com/paper/2005.04208/) (2020)
- [SummScreen: A Dataset for Abstractive Screenplay Summarization](https://mlsanity.com/paper/2104.07091/) (2021)
- [Contrastive Distillation on Intermediate Representations for Language Model Compression](https://mlsanity.com/paper/2009.14167/) (2020)
- [VIOLIN: A Large-Scale Dataset for Video-and-Language Inference](https://mlsanity.com/paper/2003.11618/) (2020)
- [Learning Trailer Moments in Full-Length Movies](https://mlsanity.com/paper/2008.08502/) (2020)
- [Movie Plot Analysis via Turning Point Identification](https://mlsanity.com/paper/1908.10328/) (2019)
- [MovieCuts: A New Dataset and Benchmark for Cut Type Recognition](https://mlsanity.com/paper/2109.05569/) (2021)
- [Screenplay Summarization Using Latent Narrative Structure](https://mlsanity.com/paper/2004.12727/) (2020)
- [Movie Summarization via Sparse Graph Construction](https://mlsanity.com/paper/2012.07536/) (2020)

## Built on by (most cited first, 12 of 12)

- [Hierarchical3D Adapters for Long Video-to-text Summarization](https://mlsanity.com/paper/2210.04829/) (2022)
- [From Shots to Stories: LLM-Assisted Video Editing with Unified Language Representations](https://mlsanity.com/paper/2505.12237/) (2025)
- [ScreenWriter: Automatic Screenplay Generation and Movie Summarisation](https://mlsanity.com/paper/2410.19809/) (2024)
- [Shot Sequence Ordering for Video Editing: Benchmarks, Metrics, and Cinematology-Inspired Computing Methods](https://mlsanity.com/paper/2503.17975/) (2025)
- [MEGA: Multimodal Alignment Aggregation and Distillation For Cinematic Video Segmentation](https://mlsanity.com/paper/2308.11185/) (2023)
- [Generating a Low-code Complete Workflow via Task Decomposition and RAG](https://mlsanity.com/paper/2412.00239/) (2024)
- [Self-Paced and Self-Corrective Masked Prediction for Movie Trailer Generation](https://mlsanity.com/paper/2512.04426/) (2025)
- [Mind-of-Director: Multi-modal Agent-Driven Film Previsualization via Collaborative Decision-Making](https://mlsanity.com/paper/2603.14790/) (2026)
- ["Previously on ..." From Recaps to Story Summarization](https://mlsanity.com/paper/2405.11487/) (2024)
- [VCoME: Verbal Video Composition with Multimodal Editing Effects](https://mlsanity.com/paper/2407.04697/) (2024)
- [BEAT: Rhythm-Elastic Alignment for Agentic Music-guided Movie Trailer Generation](https://mlsanity.com/paper/2605.27067/) (2026)
- [Find the Cliffhanger: Multi-Modal Trailerness in Soap Operas](https://mlsanity.com/paper/2401.16076/) (2024)

## Abstract (arXiv)

Movie trailers perform multiple functions: they introduce viewers to the story, convey the mood and artistic style of the film, and encourage audiences to see the movie. These diverse functions make trailer creation a challenging endeavor. In this work, we focus on finding trailer moments in a movie, i.e., shots that could be potentially included in a trailer. We decompose this task into two subtasks: narrative structure identification and sentiment prediction. We model movies as graphs, where nodes are shots and edges denote semantic relations between them. We learn these relations using joint contrastive training which distills rich textual information (e.g., characters, actions, situations) from screenplays. An unsupervised algorithm then traverses the graph and selects trailer moments from the movie that human judges prefer to ones selected by competitive supervised approaches. A main advantage of our algorithm is that it uses interpretable criteria, which allows us to deploy it in an interactive tool for trailer creation with a human in the loop. Our tool allows users to select trailer shots in under 30 minutes that are superior to fully automatic methods and comparable to (exclusive) manual selection by experts.