mlsanityData to 7 Oct 2026

The IKEA ASM Dataset: Understanding People Assembling Furniture through Actions, Objects and Pose

arXiv 2007.00394 ↗First posted 1 Jul 2020cs.CVcited by 95

Not on the map. Why?

Abstract (arXiv)

The availability of a large labeled dataset is a key requirement for applying deep learning methods to solve various computer vision tasks. In the context of understanding human activities, existing public datasets, while large in size, are often limited to a single RGB camera and provide only per-frame or per-clip action annotations. To enable richer analysis and understanding of human activities, we introduce IKEA ASM -- a three million frame, multi-view, furniture assembly video dataset that includes depth, atomic actions, object segmentation, and human pose. Additionally, we benchmark prominent methods for video action recognition, object segmentation and human pose estimation tasks on this challenging dataset. The dataset enables the development of holistic methods, which integrate multi-modal and multi-view data to better perform on these tasks.

Key facts. Cited by 95 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 8; 2023: 21; 2024: 20; 2025: 23; 2026: 17.

95 papers.

Sort:

By area:

  1. 2023Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectivescited by 477
  2. 2022Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activitiescited by 284
  3. 2023BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motioncited by 229
  4. 2024EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real Worldcited by 93
  5. 2022Temporal Action Segmentation: An Analysis of Modern Techniquescited by 85
  6. 2022Can Foundation Models Perform Zero-Shot Task Specification For Robot Manipulation?cited by 70
  7. 2024Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimationcited by 57
  8. 2022Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton Formatscited by 50
  9. 2021Learning by Aligning Videos in Timecited by 47
  10. 2023Learning Fine-grained View-Invariant Representations from Unpaired Ego-Exo Videos via Temporal Alignmentcited by 46
  11. 2023IndustReal: A Dataset for Procedure Step Recognition Handling Execution Errors in Egocentric Videos in an Industrial-Like Settingcited by 46
  12. 2024MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videoscited by 43
38 more
  1. 2021JRDB-Act: A Large-scale Dataset for Spatio-temporal Action, Social Group and Activity Detectioncited by 38
  2. 2024PREGO: online mistake detection in PRocedural EGOcentric videoscited by 36
  3. 2021Video Pose Distillation for Few-Shot, Fine-Grained Sports Action Recognitioncited by 29
  4. 2023Learning and Verification of Task Structure in Instructional Videoscited by 26
  5. 2021Learning to Align Sequential Actions in the Wildcited by 19
  6. 2025WorldPrediction: A Benchmark for High-level World Modeling and Long-horizon Procedural Planningcited by 19
  7. 2023HA-ViD: A Human Assembly Video Dataset for Comprehensive Assembly Knowledge Understandingcited by 18
  8. 2023Every Mistake Counts in Assemblycited by 18
  9. 2025Memory-efficient Streaming VideoLLMs for Real-time Procedural Video Understandingcited by 18
  10. 2023ATTACH Dataset: Annotated Two-Handed Assembly Actions for Human Action Understandingcited by 14
  11. 2023STEPs: Self-Supervised Key Step Extraction and Localization from Unlabeled Procedural Videoscited by 13
  12. 2025Context-Enhanced Memory-Refined Transformer for Online Action Detectioncited by 13
  13. 2022Weakly-Supervised Online Action Segmentation in Multi-View Instructional Videoscited by 12
  14. 2022Context-Aware Sequence Alignment using 4D Skeletal Augmentationcited by 11
  15. 2022OpenPack: A Large-scale Dataset for Recognizing Packaging Works in IoT-enabled Logistic Environmentscited by 11
  16. 2023A Survey of Deep Learning in Sports Applications: Perception, Comprehension, and Decisioncited by 11
  17. 2024IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videoscited by 11
  18. 2025Joint Self-Supervised Video Alignment and Action Segmentationcited by 11
  19. 2021Motion Guided Attention Fusion to Recognize Interactions from Videoscited by 10
  20. 20233DInAction: Understanding Human Actions in 3D Point Cloudscited by 10
  21. 2023Aligning Step-by-Step Instructional Diagrams to Video Demonstrationscited by 10
  22. 2024TI-PREGO: Chain of Thought and In-Context Learning for Online Mistake Detection in PRocedural EGOcentric Videoscited by 10
  23. 2023From Cooking Recipes to Robot Task Trees -- Improving Planning Correctness and Task Efficiency by Leveraging LLMs with a Knowledge Networkcited by 9
  24. 2023Weakly Supervised Video Representation Learning with Unaligned Text for Sequential Videoscited by 8
  25. 2024Simultaneous Detection and Interaction Reasoning for Object-Centric Action Recognitioncited by 8
  26. 2024A Survey on Computational Solutions for Reconstructing Complete Objects by Reassembling Their Fractured Partscited by 8
  27. 2026IMPACT: A Dataset for Multi-Granularity Human Procedural Action Understanding in Industrial Assemblycited by 8
  28. 20243D Pose-Based Temporal Action Segmentation for Figure Skating: A Fine-Grained and Jump Procedure-Aware Annotation Approachcited by 7
  29. 2024Understanding Spatio-Temporal Relations in Human-Object Interaction using Pyramid Graph Convolutional Networkcited by 7
  30. 2021IKEA Object State Dataset: A 6DoF object pose estimation dataset and benchmark for multi-state assembly objectscited by 6
  31. 2023How Object Information Improves Skeleton-based Human Action Recognition in Assembly Taskscited by 6
  32. 2023ProBio: A Protocol-guided Multimodal Dataset for Molecular Biology Labcited by 6
  33. 2024Egocentric and Exocentric Methods: A Short Surveycited by 6
  34. 2024Manual-PA: Learning 3D Part Assembly from Instruction Diagramscited by 6
  35. 20253D Skeleton-Based Action Recognition: A Reviewcited by 6
  36. 2022FutureHuman3D: Forecasting Complex Long-Term 3D Human Behavior from Video Observationscited by 5
  37. 2023Learning Human Action Recognition Representations Without Real Humanscited by 5
  38. 2025ProMQA-Assembly: Multimodal Procedural QA Dataset on Assemblycited by 5

50 most cited of 95 All 95 (JSON)