# MTP: A Dataset for Multi-Modal Turning Points in Casual Conversations

arXiv: https://arxiv.org/abs/2409.14801 · HTML: https://mlsanity.com/paper/2409.14801/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 28 references that are in the map.
- First posted on arXiv 23 Sep 2024.

## Builds on (most cited first, 11 of 11)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [TVQA: Localized, Compositional Video Question Answering](https://mlsanity.com/paper/1809.01696/) (2018)
- [WhisperX: Time-Accurate Speech Transcription of Long-Form Audio](https://mlsanity.com/paper/2303.00747/) (2023)
- [Movie Plot Analysis via Turning Point Identification](https://mlsanity.com/paper/1908.10328/) (2019)
- [OpenViDial: A Large-Scale, Open-Domain Dialogue Dataset with Visual Contexts](https://mlsanity.com/paper/2012.15015/) (2020)
- [Movie Summarization via Sparse Graph Construction](https://mlsanity.com/paper/2012.07536/) (2020)
- [Discovering Emotion and Reasoning its Flip in Multi-Party Conversations using Masked Memory Network and Transformer](https://mlsanity.com/paper/2103.12360/) (2021)
- [VSTAR: A Video-grounded Dialogue Dataset for Situated Semantic Understanding with Scene and Topic Transitions](https://mlsanity.com/paper/2305.18756/) (2023)
- [PTVD: A Large-Scale Plot-Oriented Multimodal Dataset Based on Television Dramas](https://mlsanity.com/paper/2306.14644/) (2023)

## Abstract (arXiv)

Detecting critical moments, such as emotional outbursts or changes in decisions during conversations, is crucial for understanding shifts in human behavior and their consequences. Our work introduces a novel problem setting focusing on these moments as turning points (TPs), accompanied by a meticulously curated, high-consensus, human-annotated multi-modal dataset. We provide precise timestamps, descriptions, and visual-textual evidence high-lighting changes in emotions, behaviors, perspectives, and decisions at these turning points. We also propose a framework, TPMaven, utilizing state-of-the-art vision-language models to construct a narrative from the videos and large language models to classify and detect turning points in our multi-modal dataset. Evaluation results show that TPMaven achieves an F1-score of 0.88 in classification and 0.61 in detection, with additional explanations aligning with human expectations.