Summary of Movie Trailer Genre Classification Using Multimodal Pretrained Features, by Serkan Sulun et al.
Movie Trailer Genre Classification Using Multimodal Pretrained Features
by Serkan Sulun, Paula Viana, Matthew E. P. Davies
First submitted to arxiv on: 11 Oct 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Multimedia (cs.MM); Image and Video Processing (eess.IV)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This novel method for movie genre classification leverages a diverse set of readily accessible pretrained models to extract high-level features. By training small classifier models with low time and memory requirements, the approach efficiently fuses these features to classify movie genres. Utilizing the transformer model, this method exploits all video and audio frames without performing temporal pooling, unlike traditional methods. The results show that our approach outperforms state-of-the-art models in precision, recall, and mean average precision (mAP). Additionally, the authors make their pretrained features, code, and trained models publicly available to foster future research. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper introduces a new way to group movies into different genres. It uses special kinds of artificial intelligence called “pretrained models” that can recognize things like scenery, characters, music, and sounds in movie trailers. These models work together with some simple math to figure out what genre the movie belongs to. This method is better than others at doing this because it looks at all parts of the trailer, not just a few select frames. The authors are sharing their code and trained models so that other researchers can use them and make even more improvements. |
Keywords
» Artificial intelligence » Classification » Mean average precision » Precision » Recall » Transformer
