paper-with-me

홈 › Papers

MObyGaze: a film dataset of multimodal objectification densely annotated by experts

2025-05-28 · Julie Tores, Elisa Ancarani, Lucile Sassatelli, Hui-Yin Wu, Clement Bergman, Lea Andolfi, Victor Ecrement, Remy Sun, Frederic Precioso, Thierry Devars, Magali Guaresi, Virginie Julliard, Sarah Lecossais arxiv

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 new video interpretation tasks, show the feasibility of multimodal objectification detection, and analyze data and model bias to propose improvements. We exemplify two applications of MObyGaze, showing how rich concept annotation can improve model reliability and explainability. We make our code and our dataset available to the community and described in the Croissant format: https://github.com/husky-helen/MObyGaze.

📄 PDF Abstract BibTeX arXiv:2505.22084

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Visual Objectification in Films: Towards a New AI Task for Video Interpretation

2024-01-24 · CVPR 2024 1 · Julie Tores, Lucile Sassatelli, Hui-Yin Wu, Clement Bergman 외

In film gender studies, the concept of 'male gaze' refers to the way the characters are portrayed on-screen as objects of desire rather than subjects. In this article, we introduce a novel video-interpretation task, to d…

Leveraging multimodal explanatory annotations for video interpretation with Modality Specific Dataset

2025-04-15 · Elisa Ancarani, Julie Tores, Lucile Sassatelli, Rémy Sun 외

We examine the impact of concept-informed supervision on multimodal video interpretation models using MOByGaze, a dataset containing human-annotated explanatory concepts. We introduce Concept Modality Specific Datasets (…

Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Bias

2022-12-21 · Robert Wolfe, Yiwei Yang, Bill Howe, Aylin Caliskan

Nine language-vision AI models trained on web scrapes with the Contrastive Language-Image Pretraining (CLIP) objective are evaluated for evidence of a bias studied by psychologists: the sexual objectification of girls an…

Reflecting the Male Gaze: Quantifying Female Objectification in 19th and 20th Century Novels

2024-03-25 · Kexin Luo, Yue Mao, Bei Zhang, Sophie Hao

Inspired by the concept of the male gaze (Mulvey, 1975) in literature and media studies, this paper proposes a framework for analyzing gender bias in terms of female objectification: the extent to which a text portrays f…

Computational design of antimicrobial active surfaces via automated Bayesian optimization

2022-08-31 · Hanfeng Zhai, Jingjie Yeo

Biofilms pose significant problems for engineers in diverse fields, such as marine science, bioenergy, and biomedicine, where effective biofilm control is a long-term goal. The adhesion and surface mechanics of biofilms …

Bayesian Optimization