Datasets › Assembly101

Assembly101

Introduced by Fadime Sener et al. in Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities28 Mar 2022 archive 2025-07-28

Assembly101 is a new procedural activity dataset featuring 4321 videos of people assembling and disassembling 101 "take-apart" toy vehicles. Participants work without fixed instructions, and the sequences feature rich and natural variations in action ordering, mistakes, and corrections. Assembly101 is the first multi-view action dataset, with simultaneous static (8) and egocentric (4) recordings. Sequences are annotated with more than 100K coarse and 1M fine-grained action segments, and 18M 3D hand poses. We benchmark on three action understanding tasks: recognition, anticipation and temporal segmentation. Additionally, we propose a novel task of detecting mistakes. The unique recording format and rich set of annotations allow us to investigate generalization to new toys, cross-view transfer, long-tailed distributions, and pose vs. appearance. We envision that Assembly101 will serve as a new challenge to investigate various activity understanding problems.

Image Source: https://assembly-101.github.io/

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.

Papers archive 2025-07-28

17 shown of 17 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 57. 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
CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition 1 1 9 Oct 2024 ran 2 of 2 samples (0 unverified)
ASQuery: A Query-based Model for Action Segmentation 1 1 30 Sep 2024 not harvested
On the Utility of 3D Hand Poses for Action Recognition 1 1 14 Mar 2024 ran 8 of 13 samples (5 unverified)
Progress-Aware Online Action Segmentation for Egocentric Procedural Task Videos 1 1 1 Jan 2024 not harvested
Opening the Vocabulary of Egocentric Actions 1 1 22 Aug 2023 not harvested
How Much Temporal Long-Term Context is Needed for Action Segmentation? 1 1 22 Aug 2023 ran 6 of 6 samples (0 unverified; 6 pointer-only for licence)
Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action Recognition 1 1 14 Jul 2023 ran 1 of 1 samples (0 unverified)
Action Anticipation with Goal Consistency 1 1 26 Jun 2023 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)
ASFormer: Transformer for Action Segmentation 1 1 16 Oct 2021 ran 1 of 1 samples (0 unverified)
Coarse to Fine Multi-Resolution Temporal Convolutional Network 1 1 23 May 2021 not harvested
Revisiting Skeleton-based Action Recognition 4 1 28 Apr 2021 not harvested
MS-TCN++: Multi-Stage Temporal Convolutional Network for Action Segmentation 1 1 16 Jun 2020 not harvested
Temporal Aggregate Representations for Long-Range Video Understanding 2 1 1 Jun 2020 not harvested
Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition 3 1 31 Mar 2020 ran 3 of 3 samples (0 unverified)
TSM: Temporal Shift Module for Efficient Video Understanding 13 1 20 Nov 2018 ran 6 of 16 samples (10 unverified; 4 pointer-only for licence)
Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition 4 1 20 May 2018 not harvested

Dataset loaders archive 2025-07-28

1 loader as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

No licence recorded in the archive. Absence here is not a statement about the dataset's terms.

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • Assembly101

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