Visual Motif Identification: Elaboration of a Curated Comparative Dataset and Classification Methods

TL;DR

This paper introduces a new machine learning approach utilizing CLIP features and a custom dataset to classify visual motifs in cinema, achieving high accuracy and providing insights through ablation studies.

Contribution

It presents a novel model and dataset for visual motif classification, demonstrating effective use of CLIP features and a shallow network architecture.

Findings

Achieved an F1-score of 0.91 on test data.

Validated the effectiveness of CLIP features for motif classification.

Provided ablation studies on features, architecture, and hyperparameters.

Abstract

In cinema, visual motifs are recurrent iconographic compositions that carry artistic or aesthetic significance. Their use throughout the history of visual arts and media is interesting to researchers and filmmakers alike. Our goal in this work is to recognise and classify these motifs by proposing a new machine learning model that uses a custom dataset to that end. We show how features extracted from a CLIP model can be leveraged by using a shallow network and an appropriate loss to classify images into 20 different motifs, with surprisingly good results: an $F_1$-score of 0.91 on our test set. We also present several ablation studies justifying the input features, architecture and hyperparameters used.