MObyGaze: a film dataset of multimodal objectification densely annotated by experts
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912400019554304 |
|---|---|
| author | Tores, Julie Ancarani, Elisa Sassatelli, Lucile Wu, Hui-Yin Bergman, Clement Andolfi, Lea Ecrement, Victor Sun, Remy Precioso, Frederic Devars, Thierry Guaresi, Magali Julliard, Virginie Lecossais, Sarah |
| author_facet | Tores, Julie Ancarani, Elisa Sassatelli, Lucile Wu, Hui-Yin Bergman, Clement Andolfi, Lea Ecrement, Victor Sun, Remy Precioso, Frederic Devars, Thierry Guaresi, Magali Julliard, Virginie Lecossais, Sarah |
| contents | Characterizing and quantifying gender representation disparities in audiovisual storytelling contents is necessary to grasp how stereotypes may perpetuate on screen. In this article, we consider the high-level construct of objectification and introduce a new AI task to the ML community: characterize and quantify complex multimodal (visual, speech, audio) temporal patterns producing objectification in films. Building on film studies and psychology, we define the construct of objectification in a structured thesaurus involving 5 sub-constructs manifesting through 11 concepts spanning 3 modalities. We introduce the Multimodal Objectifying Gaze (MObyGaze) dataset, made of 20 movies annotated densely by experts for objectification levels and concepts over freely delimited segments: it amounts to 6072 segments over 43 hours of video with fine-grained localization and categorization. We formulate different learning tasks, propose and investigate best ways to learn from the diversity of labels among a low number of annotators, and benchmark recent vision, text and audio models, showing the feasibility of the task. We make our code and our dataset available to the community and described in the Croissant format: https://anonymous.4open.science/r/MObyGaze-F600/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_22084 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MObyGaze: a film dataset of multimodal objectification densely annotated by experts Tores, Julie Ancarani, Elisa Sassatelli, Lucile Wu, Hui-Yin Bergman, Clement Andolfi, Lea Ecrement, Victor Sun, Remy Precioso, Frederic Devars, Thierry Guaresi, Magali Julliard, Virginie Lecossais, Sarah Computer Vision and Pattern Recognition Characterizing and quantifying gender representation disparities in audiovisual storytelling contents is necessary to grasp how stereotypes may perpetuate on screen. In this article, we consider the high-level construct of objectification and introduce a new AI task to the ML community: characterize and quantify complex multimodal (visual, speech, audio) temporal patterns producing objectification in films. Building on film studies and psychology, we define the construct of objectification in a structured thesaurus involving 5 sub-constructs manifesting through 11 concepts spanning 3 modalities. We introduce the Multimodal Objectifying Gaze (MObyGaze) dataset, made of 20 movies annotated densely by experts for objectification levels and concepts over freely delimited segments: it amounts to 6072 segments over 43 hours of video with fine-grained localization and categorization. We formulate different learning tasks, propose and investigate best ways to learn from the diversity of labels among a low number of annotators, and benchmark recent vision, text and audio models, showing the feasibility of the task. We make our code and our dataset available to the community and described in the Croissant format: https://anonymous.4open.science/r/MObyGaze-F600/. |
| title | MObyGaze: a film dataset of multimodal objectification densely annotated by experts |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.22084 |