{"url":"/dataset/oulu-casia","name":"Oulu-CASIA","full_name":"Oulu-CASIA NIR&VIS facial expression database","description_markdown":"The **Oulu-CASIA** NIR&VIS facial expression database consists of six expressions (surprise, happiness, sadness, anger, fear and disgust) from 80 people between 23 and 58 years old. 73.8% of the subjects are males. The subjects were asked to sit on a chair in the observation room in a way that he/ she is in front of camera. Camera-face distance is about 60 cm. Subjects were asked to make a facial expression according to an expression example shown in picture sequences. The imaging hardware works at the rate of 25 frames per second and the image resolution is 320 × 240 pixels.\r\n\r\nSource: [Facial expression recognition from near-infrared videos](https://ieeexplore.ieee.org/abstract/document/4761697)\r\nImage Source: [https://arxiv.org/abs/1712.03474](https://arxiv.org/abs/1712.03474)","description_withheld":null,"homepage":"https://www.oulu.fi/cmvs/node/41316","introduced_date":"2011-01-01","introduced_date_note":null,"introduced_by":{"paper":null,"title":"Facial expression recognition from near-infrared videos","first_author":null,"url":"https://doi.org/10.1016/j.imavis.2011.07.002"},"license":{"name":"Custom","url":"https://www.oulu.fi/en/data-privacy-notice-university-oulu"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Facial Expression Recognition (FER)","url":"/task/facial-expression-recognition","datasets_with_task":"/datasets/task/facial-expression-recognition"},{"name":"Face Verification","url":"/task/face-verification","datasets_with_task":"/datasets/task/face-verification"}],"languages":[],"variants":["Oulu-CASIA","CASIA NIR-VIS 2.0","Oulu-CASIA NIR-VIS"],"data_loaders":[],"num_papers_in_archive":80,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/face-verification-on-casia-nir-vis-20","task":"Face Verification","dataset_variant":"CASIA NIR-VIS 2.0","rows":3,"metrics":["TAR @ FAR=0.001"],"first_row_in_archive_order":{"model":"LightCNN-29 + DVG","paper":"/paper/dual-variational-generation-for-low-shot","metrics":{"TAR @ FAR=0.001":"99.8"},"code_links":[{"title":"BradyFU/DVG","url":"https://github.com/BradyFU/DVG"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/face-verification-on-oulu-casia-nir-vis","task":"Face Verification","dataset_variant":"Oulu-CASIA NIR-VIS","rows":3,"metrics":["TAR @ FAR=0.001","TAR @ FAR=0.01"],"first_row_in_archive_order":{"model":"LightCNN-29 + DVG","paper":"/paper/dual-variational-generation-for-low-shot","metrics":{"TAR @ FAR=0.001":"92.9","TAR @ FAR=0.01":"98.5"},"code_links":[{"title":"BradyFU/DVG","url":"https://github.com/BradyFU/DVG"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/facial-expression-recognition-on-oulu-casia","task":"Facial Expression Recognition (FER)","dataset_variant":"Oulu-CASIA","rows":2,"metrics":["Accuracy (10-fold)"],"first_row_in_archive_order":{"model":"Dynamic MTL","paper":"/paper/dynamic-multi-task-learning-for-face","metrics":{"Accuracy (10-fold)":"89.6"},"code_links":[{"title":"hengxyz/Dynamic_multi-task-learning","url":"https://github.com/hengxyz/Dynamic_multi-task-learning"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/face-verification-on-oulu-casia","task":"Face Verification","dataset_variant":"Oulu-CASIA","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"DeepId2+","paper":"/paper/deeply-learned-face-representations-are","metrics":{"Accuracy":"96.50"},"code_links":[{"title":"serengil/deepface","url":"https://github.com/serengil/deepface"},{"title":"melgor/pyface","url":"https://github.com/melgor/pyface"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/dynamic-multi-task-learning-for-face","title":"Dynamic Multi-Task Learning for Face Recognition with Facial Expression","date":"2019-11-08","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/dual-variational-generation-for-low-shot","title":"Dual Variational Generation for Low-Shot Heterogeneous Face Recognition","date":"2019-03-25","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/disentangled-variational-representation-for","title":"Disentangled Variational Representation for Heterogeneous Face Recognition","date":"2018-09-06","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/wasserstein-cnn-learning-invariant-features","title":"Wasserstein CNN: Learning Invariant Features for NIR-VIS Face Recognition","date":"2017-08-08","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/peak-piloted-deep-network-for-facial","title":"Peak-Piloted Deep Network for Facial Expression Recognition","date":"2016-07-24","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/deeply-learned-face-representations-are","title":"Deeply learned face representations are sparse, selective, and robust","date":"2014-12-03","rows_on_this_dataset":1,"code_links":2,"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."}