{"url":"/dataset/gazefollow","name":"GazeFollow","full_name":"GazeFollow","description_markdown":"GazeFollow is a large-scale dataset annotated with the location of where people in images are looking. It uses several major datasets that contain people as a source of images: 1, 548 images from SUN, 33, 790 images from MS COCO, 9, 135 images from Actions 40, 7, 791 images from PASCAL, 508 images from the ImageNet detection challenge and 198, 097 images from the Places dataset. This concatenation results in a challenging and large image collection of people performing diverse activities in many everyday scenarios.\r\n\r\nSource: [GazeFollow](http://gazefollow.csail.mit.edu/index.html)","description_withheld":null,"homepage":"http://gazefollow.csail.mit.edu/index.html","introduced_date":"2015-12-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/where-are-they-looking","title":"Where are they looking?","first_author":"Adria Recasens","url":null},"license":{"name":"Custom (research-only)","url":"http://gazefollow.csail.mit.edu/index.html"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Pose Estimation","url":"/task/pose-estimation","datasets_with_task":"/datasets/task/pose-estimation"},{"name":"Activity Recognition","url":"/task/activity-recognition","datasets_with_task":"/datasets/task/activity-recognition"},{"name":"Decision Making","url":"/task/decision-making","datasets_with_task":"/datasets/task/decision-making"},{"name":"Gaze Target Estimation","url":"/task/gaze-target-estimation","datasets_with_task":"/datasets/task/gaze-target-estimation"}],"languages":[],"variants":["GazeFollow"],"data_loaders":[],"num_papers_in_archive":38,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/gaze-target-estimation-on-gazefollow","task":"Gaze Target Estimation","dataset_variant":"GazeFollow","rows":1,"metrics":["AUC","Average Distance"],"first_row_in_archive_order":{"model":"ViTGaze","paper":"/paper/vitgaze-gaze-following-with-interaction","metrics":{"AUC":"0.949","Average Distance":"0.105"},"code_links":[{"title":"hustvl/vitgaze","url":"https://github.com/hustvl/vitgaze"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/vitgaze-gaze-following-with-interaction","title":"ViTGaze: Gaze Following with Interaction Features in Vision Transformers","date":"2024-03-19","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"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."}