{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/beyond-image-text-matching-verb-understanding","title":"Beyond Image-Text Matching: Verb Understanding in Multimodal Transformers Using Guided Masking","arxiv_id":"2401.16575","date":"2024-01-29","proceeding":null,"authors":["Ivana Beňová","Jana Košecká","Michal Gregor","Martin Tamajka","Marcel Veselý","Marián Šimko"],"abstract":"The dominant probing approaches rely on the zero-shot performance of image-text matching tasks to gain a finer-grained understanding of the representations learned by recent multimodal image-language transformer models. The evaluation is carried out on carefully curated datasets focusing on counting, relations, attributes, and others. This work introduces an alternative probing strategy called guided masking. The proposed approach ablates different modalities using masking and assesses the model's ability to predict the masked word with high accuracy. We focus on studying multimodal models that consider regions of interest (ROI) features obtained by object detectors as input tokens. We probe the understanding of verbs using guided masking on ViLBERT, LXMERT, UNITER, and VisualBERT and show that these models can predict the correct verb with high accuracy. This contrasts with previous conclusions drawn from image-text matching probing techniques that frequently fail in situations requiring verb understanding. The code for all experiments will be publicly available https://github.com/ivana-13/guided_masking.","url_abs":"https://arxiv.org/abs/2401.16575v1","url_pdf":"https://arxiv.org/pdf/2401.16575v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"beyond-image-text-matching-verb-understanding","repo_url":"https://github.com/ivana-13/guided_masking","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-text-matching","task_name":"Image-text matching"},{"task_slug":"text-matching","task_name":"Text Matching"}],"methods":[{"method_slug":"focus","method_name":"Focus"},{"method_slug":"lxmert","method_name":"LXMERT"},{"method_slug":"uniter","method_name":"UNITER"},{"method_slug":"vilbert","method_name":"ViLBERT"},{"method_slug":"visualbert","method_name":"VisualBERT"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}