{"url":"/dataset/g-vue","name":"G-VUE","full_name":"General-purpose Visual Understanding Evaluation","description_markdown":"**General-purpose Visual Understanding Evaluation (G-VUE)** is a comprehensive benchmark covering the full spectrum of visual cognitive abilities with four functional domains -- Perceive, Ground, Reason, and Act. The four domains are embodied in 11 carefully curated tasks, from 3D reconstruction to visual reasoning and manipulation.\r\n\r\nSource: [Perceive, Ground, Reason, and Act: A Benchmark for General-purpose Visual Representation](https://arxiv.org/pdf/2211.15402v1.pdf)\r\n\r\nImage Source: [https://github.com/wllmzhu/G-VUE](https://github.com/wllmzhu/G-VUE)","description_withheld":null,"homepage":"https://github.com/wllmzhu/G-VUE","introduced_date":"2022-11-28","introduced_date_note":null,"introduced_by":{"paper":"/paper/perceive-ground-reason-and-act-a-benchmark","title":"Perceive, Ground, Reason, and Act: A Benchmark for General-purpose Visual Representation","first_author":"Jiangyong Huang","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","datasets_with_task":"/datasets/task/semantic-segmentation"},{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Depth Estimation","url":"/task/depth-estimation","datasets_with_task":"/datasets/task/depth-estimation"},{"name":"3D Reconstruction","url":"/task/3d-reconstruction","datasets_with_task":"/datasets/task/3d-reconstruction"},{"name":"Common Sense Reasoning","url":"/task/common-sense-reasoning","datasets_with_task":"/datasets/task/common-sense-reasoning"},{"name":"Visual Reasoning","url":"/task/visual-reasoning","datasets_with_task":"/datasets/task/visual-reasoning"},{"name":"Phrase Grounding","url":"/task/phrase-grounding","datasets_with_task":"/datasets/task/phrase-grounding"},{"name":"Navigate","url":"/task/navigate","datasets_with_task":"/datasets/task/navigate"}],"languages":[],"variants":["G-VUE"],"data_loaders":[],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}