# Moviescope: Large-scale Analysis of Movies using Multiple Modalities

arXiv: https://arxiv.org/abs/1908.03180 · HTML: https://mlsanity.com/paper/1908.03180/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Aug 2019.

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

- [Conversational Question Answering: A Survey](https://mlsanity.com/paper/2106.00874/) (2021)
- [MovieCLIP: Visual Scene Recognition in Movies](https://mlsanity.com/paper/2210.11065/) (2022)
- [Two-Stream Transformer Architecture for Long Video Understanding](https://mlsanity.com/paper/2208.01753/) (2022)
- [PTVD: A Large-Scale Plot-Oriented Multimodal Dataset Based on Television Dramas](https://mlsanity.com/paper/2306.14644/) (2023)
- [Improving Transfer Learning with a Dual Image and Video Transformer for Multi-label Movie Trailer Genre Classification](https://mlsanity.com/paper/2210.07983/) (2022)
- [Incorporating Domain Knowledge Graph into Multimodal Movie Genre Classification with Self-Supervised Attention and Contrastive Learning](https://mlsanity.com/paper/2310.08032/) (2023)
- [Personalized Video Summarization by Multimodal Video Understanding](https://mlsanity.com/paper/2411.03531/) (2024)
- [A Case Study of Deep Learning Based Multi-Modal Methods for Predicting the Age-Suitability Rating of Movie Trailers](https://mlsanity.com/paper/2101.11704/) (2021)
- [Movie Trailer Genre Classification Using Multimodal Pretrained Features](https://mlsanity.com/paper/2410.19760/) (2024)
- [Demystifying Visual Features of Movie Posters for Multi-Label Genre Identification](https://mlsanity.com/paper/2309.12022/) (2023)
- [Movie Genre Classification by Language Augmentation and Shot Sampling](https://mlsanity.com/paper/2203.13281/) (2022)
- [Unraveling Movie Genres through Cross-Attention Fusion of Bi-Modal Synergy of Poster](https://mlsanity.com/paper/2410.19764/) (2024)

## Abstract (arXiv)

Film media is a rich form of artistic expression. Unlike photography, and short videos, movies contain a storyline that is deliberately complex and intricate in order to engage its audience. In this paper we present a large scale study comparing the effectiveness of visual, audio, text, and metadata-based features for predicting high-level information about movies such as their genre or estimated budget. We demonstrate the usefulness of content-based methods in this domain in contrast to human-based and metadata-based predictions in the era of deep learning. Additionally, we provide a comprehensive study of temporal feature aggregation methods for representing video and text and find that simple pooling operations are effective in this domain. We also show to what extent different modalities are complementary to each other. To this end, we also introduce Moviescope, a new large-scale dataset of 5,000 movies with corresponding movie trailers (video + audio), movie posters (images), movie plots (text), and metadata.