</> Code with Papers by Syntology

Datasets › Penn Action

Penn Action

Introduced in From Actemes to Action: A Strongly-Supervised Representation for Detailed Action Understanding1 Jan 2013 archive 2025-07-28

The Penn Action Dataset contains 2326 video sequences of 15 different actions and human joint annotations for each sequence.

Source: http://dreamdragon.github.io/PennAction/ Image Source: http://dreamdragon.github.io/PennAction/

HomepageBenchmarksPapers JSON

Benchmarks archive 2025-07-28

All 4 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
Pose Estimation UPenn Action OmniPose Mean PCK@0.2 99.4 OmniPose: A Multi-Scale Framework for Multi-Person Pose... bmartacho/OmniPose 5 Compare
Video Alignment UPenn Action TCC + TCN Kendall's Tau 0.7672 Temporal Cycle-Consistency Learning google-research/google-research +1 4 Compare
Skeleton Based Action Recognition UPenn Action UNIK Accuracy 97.9 UNIK: A Unified Framework for Real-world Skeleton-based... YangDi666/UNIK 3 Compare
Action Recognition Penn Action 3DA (RGB + Pose) Accuracy 99.7 Cross-Modal Learning with 3D Deformable Attention for... — 2 Compare

Papers archive 2025-07-28

12 shown of 12 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 110. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
Cross-Modal Learning with 3D Deformable Attention for Action Recognition 0 1 12 Dec 2022 not harvested
STAR-Transformer: A Spatio-temporal Cross Attention Transformer for Human Action Recognition 0 1 14 Oct 2022 not harvested
UNIK: A Unified Framework for Real-world Skeleton-based Action Recognition 1 1 19 Jul 2021 not harvested
OmniPose: A Multi-Scale Framework for Multi-Person Pose Estimation 1 1 18 Mar 2021 not harvested
UniPose: Unified Human Pose Estimation in Single Images and Videos 2 1 22 Jan 2020 not harvested
View-Invariant Probabilistic Embedding for Human Pose 2 2 2 Dec 2019 not harvested
Bayesian Hierarchical Dynamic Model for Human Action Recognition 1 1 1 Jun 2019 not harvested
Temporal Cycle-Consistency Learning 2 2 16 Apr 2019 ran 0 of 12 samples (12 unverified)
LSTM Pose Machines 1 1 18 Dec 2017 not harvested
Time-Contrastive Networks: Self-Supervised Learning from Video 7 1 23 Apr 2017 not harvested
Thin-Slicing Network: A Deep Structured Model for Pose Estimation in Videos 0 1 31 Mar 2017 not harvested
Pose for Action - Action for Pose 0 1 13 Mar 2016 not harvested

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

Pose EstimationAction RecognitionSkeleton Based Action RecognitionVideo Alignment

License archive 2025-07-28

Unknown

Modalities archive 2025-07-28

ImagesVideos

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • UPenn Action
  • Penn Action

2 variant names, 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