MND: A New Dataset and Benchmark of Movie Scenes Classified by Their Narrative Function

Liu, Chang; Shmilovici, Armin; Last, Mark

doi:10.1007/978-3-031-25069-9_39

Cited by 2 publications

(2 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To the best of our knowledge, this is the first work on narrative classification for the medical drama genre. In the context of cinema, a similar work is the Movie Narrative Dataset (MND), introduced by Liu et al (2023). MND consists of 6,448 annotated scenes from 45 movies, manually labeled by multiple annotators into 15 key story elements.…”

Section: Related Workmentioning

confidence: 99%

“…The classifier obtained an F1 score of 0.31, which, while still leaving room for improvement, is statistically significant and outperforms a static baseline classifier. Unlike Liu et al (2023), we adopt a single-frame vision-and-language approach. This choice is motivated by the previously mentioned studies showing the potential of using only a single frame (Lei et al 2022, Buch et al 2022.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Toward the Automatic Identification of Isotopies

Fedotova,

Barrón-Cedeño

2023

Investigating Medical Drama TV Series: Approaches and Perspectives. 14th Media Mutations International Conference

View full text Add to dashboard Cite

The rise in processing power, combined with advancements in machine learning, has resulted in an increase in the use of computational methods for automated content analysis. Although human coding is more effective for handling complex variables at the core of media studies, audiovisual content is often understudied because analyzing it is difficult and time-consuming. The present work sets out to address this issue by experimenting with unimodal and multimodal transformer-based models in an attempt to automatically classify segments from the popular medical TV drama Grey's Anatomy (ABC, 2005-) into three isotopies that are typical of the medical drama genre. To approach the task, this study explores two different classification approaches: the first approach is to employ a single multiclass classifier, while the second involves using the one-vs-the-rest approach to decompose the multiclass task with a series of binary classifiers. We investigate both these approaches in unimodal and multimodal settings, with the aim of identifying the most effective combination of the two. The results of the experiments can be considered promising, as the multiclass multimodal approach results in an F1 score of 0.723, a noticeable improvement over the F1 of 0.686 obtained by the one-vs-the-rest unimodal approach based on text.

show abstract

Section: Related Workmentioning

confidence: 99%