{"url":"/dataset/bp4d","name":"BP4D","full_name":null,"description_markdown":"The **BP4D**-Spontaneous dataset is a 3D video database of spontaneous facial expressions in a diverse group of young adults. Well-validated emotion inductions were used to elicit expressions of emotion and paralinguistic communication. Frame-level ground-truth for facial actions was obtained using the Facial Action Coding System. Facial features were tracked in both 2D and 3D domains using both person-specific and generic approaches.\r\nThe database includes forty-one participants (23 women, 18 men). They were 18 – 29 years of age; 11 were Asian, 6 were African-American, 4 were Hispanic, and 20 were Euro-American.  An emotion elicitation protocol was designed to elicit emotions of participants effectively. Eight tasks were covered with an interview process and a series of activities to elicit eight emotions.\r\nThe database is structured by participants. Each participant is associated with 8 tasks. For each task, there are both 3D and 2D videos. As well, the Metadata include manually annotated action units (FACS AU), automatically tracked head pose, and 2D/3D facial landmarks.  The database is in the size of about 2.6TB (without compression).\r\n\r\nSource: [http://www.cs.binghamton.edu/~lijun/Research/3DFE/3DFE_Analysis.html](http://www.cs.binghamton.edu/~lijun/Research/3DFE/3DFE_Analysis.html)\r\nImage Source: [http://www.cs.binghamton.edu/~lijun/Research/3DFE/3DFE_Analysis.html](http://www.cs.binghamton.edu/~lijun/Research/3DFE/3DFE_Analysis.html)","description_withheld":null,"homepage":"http://www.cs.binghamton.edu/~lijun/Research/3DFE/3DFE_Analysis.html","introduced_date":"2014-01-01","introduced_date_note":null,"introduced_by":{"paper":null,"title":"BP4D-Spontaneous: a high-resolution spontaneous 3D dynamic facial expression database","first_author":null,"url":"https://doi.org/10.1016/j.imavis.2014.06.002"},"license":{"name":"Custom","url":"http://www.cs.binghamton.edu/~lijun/Research/3DFE/3DFE_Analysis.html"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Videos","url":"/datasets/modality/videos"},{"name":"3D","url":"/datasets/modality/3d"}],"tasks":[{"name":"Facial Expression Recognition (FER)","url":"/task/facial-expression-recognition","datasets_with_task":"/datasets/task/facial-expression-recognition"},{"name":"Facial Action Unit Detection","url":"/task/facial-action-unit-detection","datasets_with_task":"/datasets/task/facial-action-unit-detection"},{"name":"Action Unit Detection","url":"/task/action-unit-detection","datasets_with_task":"/datasets/task/action-unit-detection"}],"languages":[],"variants":["BP4D"],"data_loaders":[],"num_papers_in_archive":104,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/facial-action-unit-detection-on-bp4d","task":"Facial Action Unit Detection","dataset_variant":"BP4D","rows":10,"metrics":["Average F1","Average AUC"],"first_row_in_archive_order":{"model":"FMAE-IAT","paper":"/paper/representation-learning-and-identity","metrics":{"Average F1":"67.1"},"code_links":[{"title":"forever208/fmae-iat","url":"https://github.com/forever208/fmae-iat"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/facial-expression-recognition-on-bp4d","task":"Facial Expression Recognition (FER)","dataset_variant":"BP4D","rows":2,"metrics":["ICC"],"first_row_in_archive_order":{"model":"Norface","paper":"/paper/norface-improving-facial-expression-analysis","metrics":{"ICC":"0.74"},"code_links":[{"title":"liuhw01/Norface","url":"https://github.com/liuhw01/Norface"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/action-unit-detection-on-bp4d","task":"Action Unit Detection","dataset_variant":"BP4D","rows":1,"metrics":["Avg F1"],"first_row_in_archive_order":{"model":"AU R-CNN","paper":"/paper/au-r-cnn-encoding-expert-prior-knowledge-into","metrics":{"Avg F1":"63.1"},"code_links":[{"title":"sharpstill/AU_R-CNN","url":"https://github.com/sharpstill/AU_R-CNN"},{"title":"machanic/AU_R-CNN","url":"https://github.com/machanic/AU_R-CNN"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/norface-improving-facial-expression-analysis","title":"Norface: Improving Facial Expression Analysis by Identity Normalization","date":"2024-07-22","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/representation-learning-and-identity","title":"Representation Learning and Identity Adversarial Training for Facial Behavior Understanding","date":"2024-07-15","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/multi-scale-dynamic-and-hierarchical","title":"Multi-scale Dynamic and Hierarchical Relationship Modeling for Facial Action Units Recognition","date":"2024-04-09","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":9,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-multi-dimensional-edge-feature-based","title":"Learning Multi-dimensional Edge Feature-based AU Relation Graph for Facial Action Unit Recognition","date":"2022-05-02","rows_on_this_dataset":4,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":7,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/pre-training-strategies-and-datasets-for","title":"Pre-training strategies and datasets for facial representation learning","date":"2021-03-30","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/au-r-cnn-encoding-expert-prior-knowledge-into","title":"AU R-CNN: Encoding Expert Prior Knowledge into R-CNN for Action Unit Detection","date":"2018-12-14","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/deep-adaptive-attention-for-joint-facial","title":"Deep Adaptive Attention for Joint Facial Action Unit Detection and Face Alignment","date":"2018-03-15","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multi-view-dynamic-facial-action-unit","title":"Multi-View Dynamic Facial Action Unit Detection","date":"2017-04-25","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/deep-region-and-multi-label-learning-for","title":"Deep Region and Multi-Label Learning for Facial Action Unit Detection","date":"2016-06-01","rows_on_this_dataset":1,"code_links":2,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":18,"samples_ran":16,"samples_unverified":2,"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."}