# Are we asking the right questions in MovieQA?

arXiv: https://arxiv.org/abs/1911.03083 · HTML: https://mlsanity.com/paper/1911.03083/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Nov 2019.

## Built on by (most cited first, 10 of 10)

- [A Simple LLM Framework for Long-Range Video Question-Answering](https://mlsanity.com/paper/2312.17235/) (2023)
- [Grounded Multi-Hop VideoQA in Long-Form Egocentric Videos](https://mlsanity.com/paper/2408.14469/) (2024)
- [AMEGO: Active Memory from long EGOcentric videos](https://mlsanity.com/paper/2409.10917/) (2024)
- [Learning to Cut by Watching Movies](https://mlsanity.com/paper/2108.04294/) (2021)
- [Video Question Answering with Phrases via Semantic Roles](https://mlsanity.com/paper/2104.03762/) (2021)
- [MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks](https://mlsanity.com/paper/2506.07016/) (2025)
- [Long Story Short: a Summarize-then-Search Method for Long Video Question Answering](https://mlsanity.com/paper/2311.01233/) (2023)
- [SynopGround: A Large-Scale Dataset for Multi-Paragraph Video Grounding from TV Dramas and Synopses](https://mlsanity.com/paper/2408.01669/) (2024)
- [TrUMAn: Trope Understanding in Movies and Animations](https://mlsanity.com/paper/2108.04542/) (2021)
- [Situation and Behavior Understanding by Trope Detection on Films](https://mlsanity.com/paper/2101.07632/) (2021)

## Abstract (arXiv)

Joint vision and language tasks like visual question answering are fascinating because they explore high-level understanding, but at the same time, can be more prone to language biases. In this paper, we explore the biases in the MovieQA dataset and propose a strikingly simple model which can exploit them. We find that using the right word embedding is of utmost importance. By using an appropriately trained word embedding, about half the Question-Answers (QAs) can be answered by looking at the questions and answers alone, completely ignoring narrative context from video clips, subtitles, and movie scripts. Compared to the best published papers on the leaderboard, our simple question + answer only model improves accuracy by 5% for video + subtitle category, 5% for subtitle, 15% for DVS and 6% higher for scripts.