datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
aide_elderly
Aide Elderly Dataset
Description
Small dataset for experiments related to project Aide.
Authors
Fabien Allemand (fabien.allemand@cea.fr)
image-captioningwikiart-artist-lucas-cranach-the-elderuser-vlm-elderly-bench
VLM Benchmark for Domain-Specefic Evaluation
To assess the personalization capabilities of the proposed model compared to the baseline, we employed this benchmark:
ElderlyTech-VQA Bench: Comprising 144 triplets of images, questions, and answers, this benchmark focuses on real-world technology-related queries from elderly individuals. The questions are provided to us by Assistance publique Hôpitaux de Paris (APHP) and the images, sourced from FairFace, ensure diversity in ethnicity… See the full description on the dataset page: https://huggingface.co/datasets/ACIDE/user-vlm-elderly-bench.user-vlm-elderlyHealthELDER-STATS