{"url":"/dataset/gtea","name":"GTEA","full_name":"Georgia Tech Egocentric Activity","description_markdown":"The Georgia Tech Egocentric Activities (**GTEA**) dataset contains seven types of daily activities such as making sandwich, tea, or coffee. Each activity is performed by four different people, thus totally 28 videos. For each video, there are about 20 fine-grained action instances such as take bread, pour ketchup, in approximately one minute.\r\n\r\nSource: [TricorNet: A Hybrid Temporal Convolutional and Recurrent Network for Video Action Segmentation](https://arxiv.org/abs/1705.07818)\r\nImage Source: [http://cbs.ic.gatech.edu/fpv/](http://cbs.ic.gatech.edu/fpv/)","description_withheld":null,"homepage":"http://cbs.ic.gatech.edu/fpv/","introduced_date":"2011-01-01","introduced_date_note":null,"introduced_by":{"paper":null,"title":"Learning to recognize objects in egocentric activities","first_author":null,"url":"https://doi.org/10.1109/CVPR.2011.5995444"},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Action Segmentation","url":"/task/action-segmentation","datasets_with_task":"/datasets/task/action-segmentation"},{"name":"Weakly Supervised Action Localization","url":"/task/weakly-supervised-action-localization","datasets_with_task":"/datasets/task/weakly-supervised-action-localization"},{"name":"Fine-Grained Action Detection","url":"/task/fine-grained-action-detection","datasets_with_task":"/datasets/task/fine-grained-action-detection"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["GTEA"],"data_loaders":[],"num_papers_in_archive":120,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/action-segmentation-on-gtea-1","task":"Action Segmentation","dataset_variant":"GTEA","rows":28,"metrics":["F1@50%","F1@25%","F1@10%","Acc","Edit"],"first_row_in_archive_order":{"model":"Semantic2Graph","paper":"/paper/semantic2graph-graph-based-multi-modal","metrics":{"Acc":"89.8","Edit":"92.0","F1@10%":"95.7","F1@25%":"94.2","F1@50%":"91.3"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/weakly-supervised-action-localization-on-gtea","task":"Weakly Supervised Action Localization","dataset_variant":"GTEA","rows":6,"metrics":["mAP@0.1:0.7","mAP@0.5"],"first_row_in_archive_order":{"model":"AU-Action","paper":"/paper/is-weakly-supervised-action-segmentation","metrics":{"mAP@0.1:0.7":"76.9","mAP@0.5":"66.3"},"code_links":[{"title":"fandulu/DD-Net","url":"https://github.com/fandulu/DD-Net"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/efficient-temporal-action-segmentation-via","title":"Efficient Temporal Action Segmentation via Boundary-aware Query Voting","date":"2024-05-25","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/fact-frame-action-cross-attention-temporal","title":"FACT: Frame-Action Cross-Attention Temporal Modeling for Efficient Action Segmentation","date":"2024-01-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/is-weakly-supervised-action-segmentation","title":"Is Weakly-supervised Action Segmentation Ready For Human-Robot Interaction? No, Let's Improve It With Action-union Learning","date":"2023-10-22","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/bit-bi-level-temporal-modeling-for-efficient","title":"BIT: Bi-Level Temporal Modeling for Efficient Supervised Action Segmentation","date":"2023-08-28","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/hr-pro-point-supervised-temporal-action","title":"HR-Pro: Point-supervised Temporal Action Localization via Hierarchical Reliability Propagation","date":"2023-08-24","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/sf-tmn-slowfast-temporal-modeling-network-for","title":"SF-TMN: SlowFast Temporal Modeling Network for Surgical Phase Recognition","date":"2023-06-15","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/diffusion-action-segmentation","title":"Diffusion Action Segmentation","date":"2023-03-31","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":9,"samples_ran":5,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/semantic2graph-graph-based-multi-modal","title":"Semantic2Graph: Graph-based Multi-modal Feature Fusion for Action Segmentation in Videos","date":"2022-09-13","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/unified-fully-and-timestamp-supervised","title":"Unified Fully and Timestamp Supervised Temporal Action Segmentation via Sequence to Sequence Translation","date":"2022-09-01","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/efficient-u-transformer-with-boundary-aware","title":"Do we really need temporal convolutions in action segmentation?","date":"2022-05-26","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/cross-enhancement-transformer-for-action","title":"Cross-Enhancement Transformer for Action Segmentation","date":"2022-05-19","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/maximization-and-restoration-action","title":"Maximization and restoration: Action segmentation through dilation passing and temporal reconstruction","date":"2022-05-02","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/bridge-prompt-towards-ordinal-action","title":"Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videos","date":"2022-03-26","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/asformer-transformer-for-action-segmentation","title":"ASFormer: Transformer for Action Segmentation","date":"2021-10-16","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+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/learning-action-completeness-from-points-for","title":"Learning Action Completeness from Points for Weakly-supervised Temporal Action Localization","date":"2021-08-11","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/coarse-to-fine-multi-resolution-temporal","title":"Coarse to Fine Multi-Resolution Temporal Convolutional Network","date":"2021-05-23","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/efficient-two-step-networks-for-temporal","title":"Efficient Two-Step Networks for Temporal Action Segmentation","date":"2021-04-30","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/action-segmentation-with-mixed-temporal","title":"Action Segmentation with Mixed Temporal Domain Adaptation","date":"2021-04-15","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/temporal-action-segmentation-from-timestamp","title":"Temporal Action Segmentation from Timestamp Supervision","date":"2021-03-11","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":4,"samples_ran":4,"samples_unverified":0,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/depthwise-separable-temporal-convolutional","title":"Depthwise Separable Temporal Convolutional Network for Action Segmentation","date":"2021-01-19","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/refining-action-segmentation-with","title":"Refining Action Segmentation With Hierarchical Video Representations","date":"2021-01-01","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/point-level-temporal-action-localization","title":"Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses","date":"2020-12-15","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/boundary-aware-cascade-networks-for-temporal","title":"Boundary-Aware Cascade Networks for Temporal Action Segmentation","date":"2020-08-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/alleviating-over-segmentation-errors-by","title":"Alleviating Over-segmentation Errors by Detecting Action Boundaries","date":"2020-07-14","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":11,"samples_ran":0,"samples_unverified":11,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/ms-tcn-multi-stage-temporal-convolutional-2","title":"MS-TCN++: Multi-Stage Temporal Convolutional Network for Action Segmentation","date":"2020-06-16","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/sf-net-single-frame-supervision-for-temporal","title":"SF-Net: Single-Frame Supervision for Temporal Action Localization","date":"2020-03-15","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/action-segmentation-with-joint-self","title":"Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation","date":"2020-03-05","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/ms-tcn-multi-stage-temporal-convolutional","title":"MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation","date":"2019-03-05","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/temporal-deformable-residual-networks-for","title":"Temporal Deformable Residual Networks for Action Segmentation in Videos","date":"2018-06-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/temporal-convolutional-networks-for-action","title":"Temporal Convolutional Networks for Action Segmentation and Detection","date":"2016-11-16","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":21,"samples_ran":2,"samples_unverified":19,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/segmental-spatiotemporal-cnns-for-fine","title":"Segmental Spatiotemporal CNNs for Fine-grained Action Segmentation","date":"2016-02-09","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":8,"samples_harvested":53,"samples_ran":19,"samples_unverified":34,"pointer_only_for_licence":8,"papers_with_no_sample_that_ran":1,"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."}