</> Code with Papers by Syntology

Datasets › GTEA

GTEA (Georgia Tech Egocentric Activity)

Introduced in Learning to recognize objects in egocentric activities1 Jan 2011 archive 2025-07-28

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.

Source: TricorNet: A Hybrid Temporal Convolutional and Recurrent Network for Video Action Segmentation Image Source: http://cbs.ic.gatech.edu/fpv/

HomepageBenchmarksPapers JSON

Benchmarks archive 2025-07-28

All 2 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Action Segmentation GTEA Semantic2Graph F1@50% 91.3 Semantic2Graph: Graph-based Multi-modal Feature Fusion... — 28 Compare
Weakly Supervised Action Localization GTEA AU-Action mAP@0.1:0.7 76.9 Is Weakly-supervised Action Segmentation Ready For... fandulu/DD-Net 6 Compare

Papers archive 2025-07-28

30 shown of 31 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 120. The Syntology column is from Syntology's graph (read 2026-09-25), stated per sample; it is not part of any archive number.

DateSamples run Syntology
Efficient Temporal Action Segmentation via Boundary-aware Query Voting 1 1 25 May 2024 not harvested
FACT: Frame-Action Cross-Attention Temporal Modeling for Efficient Action Segmentation 1 1 1 Jan 2024 not harvested
Is Weakly-supervised Action Segmentation Ready For Human-Robot Interaction? No, Let's Improve It With Action-union Learning 1 2 22 Oct 2023 not harvested
BIT: Bi-Level Temporal Modeling for Efficient Supervised Action Segmentation 0 1 28 Aug 2023 not harvested
HR-Pro: Point-supervised Temporal Action Localization via Hierarchical Reliability Propagation 1 1 24 Aug 2023 not harvested
SF-TMN: SlowFast Temporal Modeling Network for Surgical Phase Recognition 0 1 15 Jun 2023 not harvested
Diffusion Action Segmentation 1 1 31 Mar 2023 ran 5 of 9 samples (4 unverified)
Semantic2Graph: Graph-based Multi-modal Feature Fusion for Action Segmentation in Videos 0 1 13 Sep 2022 not harvested
Unified Fully and Timestamp Supervised Temporal Action Segmentation via Sequence to Sequence Translation 2 1 1 Sep 2022 ran 2 of 2 samples (0 unverified; 2 pointer-only for licence)
Do we really need temporal convolutions in action segmentation? 1 1 26 May 2022 not harvested
Cross-Enhancement Transformer for Action Segmentation 1 1 19 May 2022 not harvested
Maximization and restoration: Action segmentation through dilation passing and temporal reconstruction 0 1 2 May 2022 not harvested
Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videos 1 1 26 Mar 2022 ran 2 of 2 samples (0 unverified; 2 pointer-only for licence)
ASFormer: Transformer for Action Segmentation 1 1 16 Oct 2021 ran 1 of 1 samples (0 unverified)
Learning Action Completeness from Points for Weakly-supervised Temporal Action Localization 1 1 11 Aug 2021 not harvested
Coarse to Fine Multi-Resolution Temporal Convolutional Network 1 1 23 May 2021 not harvested
Efficient Two-Step Networks for Temporal Action Segmentation 1 1 30 Apr 2021 not harvested
Action Segmentation with Mixed Temporal Domain Adaptation 0 1 15 Apr 2021 not harvested
Temporal Action Segmentation from Timestamp Supervision 1 1 11 Mar 2021 ran 4 of 4 samples (0 unverified; 4 pointer-only for licence)
Depthwise Separable Temporal Convolutional Network for Action Segmentation 0 1 19 Jan 2021 not harvested
Refining Action Segmentation With Hierarchical Video Representations 1 2 1 Jan 2021 not harvested
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses 0 1 15 Dec 2020 not harvested
Boundary-Aware Cascade Networks for Temporal Action Segmentation 1 1 1 Aug 2020 not harvested
Alleviating Over-segmentation Errors by Detecting Action Boundaries 1 1 14 Jul 2020 ran 0 of 11 samples (11 unverified)
MS-TCN++: Multi-Stage Temporal Convolutional Network for Action Segmentation 1 2 16 Jun 2020 not harvested
SF-Net: Single-Frame Supervision for Temporal Action Localization 1 1 15 Mar 2020 not harvested
Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation 1 1 5 Mar 2020 ran 3 of 3 samples (0 unverified)
MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation 2 1 5 Mar 2019 not harvested
Temporal Deformable Residual Networks for Action Segmentation in Videos 0 1 1 Jun 2018 not harvested
Temporal Convolutional Networks for Action Segmentation and Detection 5 1 16 Nov 2016 ran 2 of 21 samples (19 unverified)

The full list of 31 is in the JSON twin.

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

Action SegmentationWeakly Supervised Action LocalizationFine-Grained Action Detection

License archive 2025-07-28

Unknown

Modalities archive 2025-07-28

ImagesVideos

Languages archive 2025-07-28

Chinese

Variants archive 2025-07-28

  • GTEA

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections