</> Code with Papers by Syntology

Datasets › MultiTHUMOS

MultiTHUMOS

Introduced by Serena Yeung et al. in Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos1 Jan 2018 archive 2025-07-28

The MultiTHUMOS dataset contains dense, multilabel, frame-level action annotations for 30 hours across 400 videos in the THUMOS'14 action detection dataset. It consists of 38,690 annotations of 65 action classes, with an average of 1.5 labels per frame and 10.5 action classes per video.

Source: http://ai.stanford.edu/~syyeung/everymoment.html Image Source: http://ai.stanford.edu/~syyeung/everymoment.html

HomepageBenchmarksPapers JSON

Benchmarks archive 2025-07-28

All 3 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 Detection Multi-THUMOS MLAD mAP 51.5 Modeling Multi-Label Action Dependencies for Temporal... ptirupat/MLAD 8 Compare
Temporal Action Localization MultiTHUMOS TriDet (VideoMAEv2) Average mAP 37.5 Temporal Action Localization with Enhanced Instant... dingfengshi/tridet +2 8 Compare
Action Detection MultiTHUMOS PAT mAP 44.6 PAT: Position-Aware Transformer for Dense Multi-Label... — 1 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 58. 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
Dual DETRs for Multi-Label Temporal Action Detection 0 1 31 Mar 2024 not harvested
Temporal Action Localization with Enhanced Instant Discriminability 3 2 11 Sep 2023 not harvested
PAT: Position-Aware Transformer for Dense Multi-Label Action Detection 0 1 9 Aug 2023 not harvested
TemporalMaxer: Maximize Temporal Context with only Max Pooling for Temporal Action Localization 1 1 16 Mar 2023 not harvested
PointTAD: Multi-Label Temporal Action Detection with Learnable Query Points 1 1 20 Oct 2022 ran 6 of 8 samples (2 unverified)
MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection 1 2 7 Dec 2021 ran 1 of 1 samples (0 unverified; 1 pointer-only for licence)
CTRN: Class-Temporal Relational Network for Action Detection 0 1 26 Oct 2021 not harvested
Modeling Multi-Label Action Dependencies for Temporal Action Localization 1 2 4 Mar 2021 ran 5 of 5 samples (0 unverified; 5 pointer-only for licence)
PDAN: Pyramid Dilated Attention Network for Action Detection 1 2 5 Jan 2021 not harvested
Temporal Gaussian Mixture Layer for Videos 1 1 16 Mar 2018 not harvested
Learning Latent Super-Events to Detect Multiple Activities in Videos 2 1 5 Dec 2017 not harvested
Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos 1 2 21 Jul 2015 not harvested

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

Action RecognitionTemporal Action LocalizationAction Detection

License archive 2025-07-28

CC BY 4.0

Modalities archive 2025-07-28

Videos

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • Multi-THUMOS
  • MultiTHUMOS

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