{"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/vinvl-l-enriching-visual-representation-with","title":"VinVL+L: Enriching Visual Representation with Location Context in VQA","arxiv_id":null,"date":"2023-02-22","proceeding":"Computer Vision Winter Workshop 2023 2","authors":["Jiří Vyskočil","Lukáš Picek"],"abstract":"In this paper, we describe a novel method - VinVL+L - that enriches the visual representations (i.e. object tags and region features) of the State-of-the-Art Vision and Language (VL) method - VinVL - with Location information. To verify the importance of such metadata for VL models, we (i) trained a Swin-B model on the Places365 dataset and obtained additional sets of visual and tag features; both were made public to allow reproducibility and further experiments, (ii) did an architectural update to the existing VinVL method to include the new feature sets, and (iii) provide a qualitative and quantitative evaluation. By including just binary location metadata, the VinVL+L method provides incremental improvement to the State-of-the-Art VinVL in Visual Question Answering (VQA). The VinVL+L achieved an accuracy of 64.85% and increased the performance by +0.32% in terms of accuracy on the GQA dataset; the statistical significance of the new representations is verified via Approximate Randomization.\r\nThe code and newly generated sets of features are available at https://github.com/vyskocj/VinVL-L.","url_abs":"https://ceur-ws.org/Vol-3349/","url_pdf":"https://ceur-ws.org/Vol-3349/paper4.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":"vinvl-l-enriching-visual-representation-with","repo_url":"https://github.com/vyskocj/VinVL-L","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"tag","task_name":"TAG"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-question-answering-on-gqa-test2019","task":"Visual Question Answering (VQA)","dataset":"GQA Test2019","model":"VinVL+L","rank_in_archive_order":10,"of":127,"metrics":{"Accuracy":"64.85","Binary":"82.59","Consistency":"94.0","Distribution":"4.59","Open":"49.19","Plausibility":"84.91","Validity":"96.62"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}