# Movie Box Office Prediction With Self-Supervised and Visually Grounded Pretraining

arXiv: https://arxiv.org/abs/2304.10311 · HTML: https://mlsanity.com/paper/2304.10311/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 46 references that are in the map.
- First posted on arXiv 20 Apr 2023.

## Builds on (most cited first, 19 of 19)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [VL-BERT: Pre-training of Generic Visual-Linguistic Representations](https://mlsanity.com/paper/1908.08530/) (2019)
- [End-to-End Learning of Visual Representations from Uncurated Instructional Videos](https://mlsanity.com/paper/1912.06430/) (2019)
- [Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers](https://mlsanity.com/paper/2004.00849/) (2020)
- [Vokenization: Improving Language Understanding with Contextualized, Visual-Grounded Supervision](https://mlsanity.com/paper/2010.06775/) (2020)
- [Things not Written in Text: Exploring Spatial Commonsense from Visual Signals](https://mlsanity.com/paper/2203.08075/) (2022)
- [Generative Imagination Elevates Machine Translation](https://mlsanity.com/paper/2009.09654/) (2020)
- [Imagination-Augmented Natural Language Understanding](https://mlsanity.com/paper/2204.08535/) (2022)
- [Z-LaVI: Zero-Shot Language Solver Fueled by Visual Imagination](https://mlsanity.com/paper/2210.12261/) (2022)
- [NumGPT: Improving Numeracy Ability of Generative Pre-trained Models](https://mlsanity.com/paper/2109.03137/) (2021)
- [Early Predictions of Movie Success: the Who, What, and When of Profitability](https://mlsanity.com/paper/1506.05382/) (2015)
- [Initialization Matters: Regularizing Manifold-informed Initialization for Neural Recommendation Systems](https://mlsanity.com/paper/2106.04993/) (2021)
- [Predicting Personality from Book Preferences with User-Generated Content Labels](https://mlsanity.com/paper/1707.06643/) (2017)

## Built on by (most cited first, 1 of 1)

- [ECP-Bench: Benchmarking and Learning Entertainment Content Promotion with Foundation Models](https://mlsanity.com/paper/2609.22150/) (2026)

## Abstract (arXiv)

Investments in movie production are associated with a high level of risk as movie revenues have long-tailed and bimodal distributions. Accurate prediction of box-office revenue may mitigate the uncertainty and encourage investment. However, learning effective representations for actors, directors, and user-generated content-related keywords remains a challenging open problem. In this work, we investigate the effects of self-supervised pretraining and propose visual grounding of content keywords in objects from movie posters as a pertaining objective. Experiments on a large dataset of 35,794 movies demonstrate significant benefits of self-supervised training and visual grounding. In particular, visual grounding pretraining substantially improves learning on movies with content keywords and achieves 14.5% relative performance gains compared to a finetuned BERT model with identical architecture.