Phillips, AdamGrandes Rodriguez, DanielSánchez Manzano, MiriamSalvadó-Romero, AlanGarín Boronat, ManuelHaro Ortega, GloriaBallester, Coloma2025-06-022024Phillips A, Grandes Rodriguez D, Sánchez-Manzano M, Salvadó A, Garin M, Haro G, Ballester C. Visual motif identification: elaboration of a curated comparative dataset and classification methods. In: Leonardis A, Ricci E, Roth S, Russakovsky O, Sattler T, Varol G, editors. 18th European Conference on Computer Vision Part VI (ECCV 2024); 2024 Sept 29 - October 4; Milan, Italy. Cham: Springer Verlag; 2024. p.341-61. (LNCS; no. 15628). DOI: 10.1007/978-3-031-91572-7_21http://hdl.handle.net/10230/70580In 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 F1-score of 0.91 on our test set. We also present several ablation studies justifying the input features, architecture and hyperparameters used.application/pdfeng© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AGinfo:eu-repo/semantics/conferenceObjectVisual motifDatasetDeep learning based modelsCLIP featuresRecognition and classificationinfo:eu-repo/semantics/embargoedAccess