Datasets › HACS

HACS (Human Action Clips and Segments)

Introduced by Hang Zhao et al. in HACS: Human Action Clips and Segments Dataset for Recognition and Temporal Localization archive 2025-07-28

HACS is a dataset for human action recognition. It uses a taxonomy of 200 action classes, which is identical to that of the ActivityNet-v1.3 dataset. It has 504K videos retrieved from YouTube. Each one is strictly shorter than 4 minutes, and the average length is 2.6 minutes. A total of 1.5M clips of 2-second duration are sparsely sampled by methods based on both uniform randomness and consensus/disagreement of image classifiers. 0.6M and 0.9M clips are annotated as positive and negative samples, respectively.

Authors split the collection into training, validation and testing sets of size 1.4M, 50K and 50K clips, which are sampled from 492K, 6K and 6K videos, respectively.

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
Temporal Action Localization HACS RDFA-S6 (InternVideo2-6B) Average-mAP 45.8 Enhancing Temporal Action Localization: Advanced S6... lsy0882/RDFA-S6 12 Compare
Action Recognition HACS InternVideo2-6B Top 1 Accuracy 97.0 InternVideo2: Scaling Foundation Models for Multimodal... opengvlab/internvideo +1 8 Compare

Papers archive 2025-07-28

papers with a benchmark row: 12 · with a code link: 11 · where Syntology ran a sample: 5 (3 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument) Syntology

Show: all papers with a benchmark rowonly where code ran (5 of 12 with a benchmark row: 3 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 12 of 12 with a leaderboard row on this dataset's benchmarks, newest first by the archive's date (ties by slug; undated papers last).

The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset, not that list; the archive's count for this dataset is 75. The Syntology column is from Syntology's graph, stated per sample; it is not part of any archive number. A line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified” (C is a part of N, never taken away from it); the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. When the archive marks a repository official for the paper, the cell starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

PaperCodeResultsDateSamples run Syntology
Enhancing Temporal Action Localization: Advanced S6 Modeling with Recurrent Mechanism 1 1 18 Jul 2024 not harvested
DyFADet: Dynamic Feature Aggregation for Temporal Action Detection 1 1 3 Jul 2024 official (archive's flag): 12 ran · 12 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 8 where Syntology's instrument failed) · 0 unverified (12 pointer-only for licence)
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding 2 3 22 Mar 2024 not harvested
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding 1 1 14 Mar 2024 official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (2 pointer-only for licence)
Temporal Action Localization with Enhanced Instant Discriminability 3 1 11 Sep 2023 not harvested
TriDet: Temporal Action Detection with Relative Boundary Modeling 1 2 13 Mar 2023 official (archive's flag): 12 ran · 12 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified (12 pointer-only for licence)
InternVideo: General Video Foundation Models via Generative and Discriminative Learning 2 1 6 Dec 2022 official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified
UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer 2 1 22 Sep 2022 not harvested
Low-Fidelity Video Encoder Optimization for Temporal Action Localization 0 1 1 Dec 2021 not harvested
End-to-end Temporal Action Detection with Transformer 1 1 18 Jun 2021 official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified
Learn to cycle: Time-consistent feature discovery for action recognition 1 6 15 Jun 2020 not harvested
HACS: Human Action Clips and Segments Dataset for Recognition and Temporal Localization 2 1 26 Dec 2017 0 ran · 1 unverified

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

License archive 2025-07-28

BSD 3-Clause

Modalities archive 2025-07-28

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • HACS

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