{"url":"/dataset/casia-b","name":"CASIA-B","full_name":"CASIA-B","description_markdown":"CASIA-B is a large multiview gait database, which is created in January 2005. There are 124 subjects, and the gait data was captured from 11 views. Three variations, namely view angle, clothing and carrying condition changes, are separately considered. Besides the video files, we still provide human silhouettes extracted from video files. The detailed information about Dataset B and an evaluation framework can be found in this paper .\r\n\r\nThe format of the video filename in Dataset B is 'xxx-mm-nn-ttt.avi', where\r\n\r\n    xxx: subject id, from 001 to 124.\r\n    mm: walking status, can be 'nm' (normal), 'cl' (in a coat) or 'bg' (with a bag).\r\n    nn: sequence number.\r\n    ttt: view angle, can be '000', '018', ..., '180'.","description_withheld":null,"homepage":"http://www.cbsr.ia.ac.cn/english/Gait%20Databases.asp","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Gait Recognition","url":"/task/gait-recognition","datasets_with_task":"/datasets/task/gait-recognition"},{"name":"Multiview Gait Recognition","url":"/task/multiview-gait-recognition","datasets_with_task":"/datasets/task/multiview-gait-recognition"},{"name":"Gait Identification","url":"/task/gait-identification","datasets_with_task":"/datasets/task/gait-identification"}],"languages":[],"variants":["CASIA-B"],"data_loaders":[],"num_papers_in_archive":18,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/multiview-gait-recognition-on-casia-b","task":"Multiview Gait Recognition","dataset_variant":"CASIA-B","rows":12,"metrics":["Accuracy (Cross-View, Avg)","NM#5-6 ","BG#1-2","CL#1-2","NM#5-6"],"first_row_in_archive_order":{"model":"CAL (RGB), AP3DNLResNet50","paper":"/paper/clothes-changing-person-re-identification","metrics":{"Accuracy (Cross-View, Avg)":"97.3","BG#1-2":"99.8","CL#1-2":"92.3","NM#5-6":"99.9"},"code_links":[{"title":"guxinqian/simple-ccreid","url":"https://github.com/guxinqian/simple-ccreid"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/gaitstr-gait-recognition-with-sequential-two","title":"GaitSTR: Gait Recognition with Sequential Two-stream Refinement","date":"2024-04-02","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/hierarchical-spatio-temporal-representation","title":"Hierarchical Spatio-Temporal Representation Learning for Gait Recognition","date":"2023-07-19","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":3,"samples_unverified":2,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/gaitref-gait-recognition-with-refined","title":"GaitRef: Gait Recognition with Refined Sequential Skeletons","date":"2023-04-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/gaitmixer-skeleton-based-gait-representation","title":"GaitMixer: Skeleton-based Gait Representation Learning via Wide-spectrum Multi-axial Mixer","date":"2022-10-27","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/gaitfm-fine-grained-motion-representation-for","title":"GaitMM: Multi-Granularity Motion Sequence Learning for Gait Recognition","date":"2022-09-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/clothes-changing-person-re-identification","title":"Clothes-Changing Person Re-identification with RGB Modality Only","date":"2022-04-14","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/context-sensitive-temporal-feature-learning-1","title":"Multi-scale Context-aware Network with Transformer for Gait Recognition","date":"2022-04-07","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/gait-recognition-with-mask-based","title":"Gait Recognition with Mask-based Regularization","date":"2022-03-08","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/gaitgraph-graph-convolutional-network-for","title":"GaitGraph: Graph Convolutional Network for Skeleton-Based Gait Recognition","date":"2021-01-27","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/gaitpart-temporal-part-based-model-for-gait","title":"GaitPart: Temporal Part-Based Model for Gait Recognition","date":"2020-06-01","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/gaitset-regarding-gait-as-a-set-for-cross","title":"GaitSet: Regarding Gait as a Set for Cross-View Gait Recognition","date":"2018-11-15","rows_on_this_dataset":1,"code_links":3,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":6,"samples_ran":4,"samples_unverified":2,"pointer_only_for_licence":5,"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."}