mlsanityData to 7 Oct 2026

IMPACT-HOI: Supervisory Control for Onset-Anchored Partial HOI Event Construction

arXiv 2605.01666 ↗First posted 3 May 2026cs.CV cs.AI cs.ROcited by 2

Not on the map. Why?

Abstract (arXiv)

We present IMPACT-HOI, a mixed-initiative framework for annotating egocentric procedural video by constructing structured event graphs for Human-Object Interactions (HOI), motivated by the need for high-quality structured supervision for learning robot manipulation from human demonstration. IMPACT-HOI frames this task as the incremental resolution of a partially specified, onset-anchored event state. A trust-calibrated controller selects among direct queries, human-confirmed suggestions, and conservative completions based on empirical annotator behavior and evidence quality. A risk-bounded execution protocol, utilizing atomic rollback, ensures that human-confirmed decisions are preserved against conflicting automated updates. A user study with 9 participants shows a 13.5% reduction in manual annotation actions, a 46.67% event match rate, and zero confirmed-field violations under the studied protocol. The code will be made publicly available at https://github.com/541741106/IMPACT_HOI.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 34 of its 38 references that are in the map. First posted on arXiv 3 May 2026.

Builds on

34 of 38 references.

References · 34

  1. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,530
  2. 2020Rescaling Egocentric Visioncited by 529
  3. 2022HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interactioncited by 321
  4. 2022ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulationcited by 306
  5. 2022Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activitiescited by 284
  6. 2021HOTR: End-to-End Human-Object Interaction Detection with Transformerscited by 183
  7. 2019The VIA Annotation Software for Images, Audio and Videocited by 166
  8. 2024EgoMimic: Scaling Imitation Learning via Egocentric Videocited by 160
  9. 2021QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Informationcited by 147
  10. 2022EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relationscited by 139
  11. 2022GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detectioncited by 119
  12. 2022Anticipative Feature Fusion Transformer for Multi-Modal Action Anticipationcited by 41
22 more
  1. 2021ST-HOI: A Spatial-Temporal Baseline for Human-Object Interaction Detection in Videoscited by 20
  2. 2023Learning the What and How of Annotation in Video Object Segmentationcited by 19
  3. 2023Navigating Open Set Scenarios for Skeleton-based Action Recognitioncited by 17
  4. 2021Learning Asynchronous and Sparse Human-Object Interaction in Videoscited by 16
  5. 2024Referring Atomic Video Action Recognitioncited by 16
  6. 2025EgoNight: Towards Egocentric Vision Understanding at Night with a Challenging Benchmarkcited by 16
  7. 2020LIGHTEN: Learning Interactions with Graph and Hierarchical TEmporal Networks for HOI in videoscited by 14
  8. 2022Video-based Human-Object Interaction Detection from Tubelet Tokenscited by 13
  9. 2023Human-Object Interaction Prediction in Videos through Gaze Followingcited by 13
  10. 2021Spatio-Temporal Interaction Graph Parsing Networks for Human-Object Interaction Recognitioncited by 12
  11. 2023Semi-supervised Active Learning for Video Action Detectioncited by 10
  12. 2024Adapting the Segment Anything Model During Usage in Novel Situationscited by 9
  13. 2024Skeleton-Based Human Action Recognition with Noisy Labelscited by 8
  14. 2025MICA: Multi-Agent Industrial Coordination Assistantcited by 8
  15. 2026EgoSound: Benchmarking Sound Understanding in Egocentric Videoscited by 8
  16. 2026IMPACT: A Dataset for Multi-Granularity Human Procedural Action Understanding in Industrial Assemblycited by 8
  17. 2025Snap, Segment, Deploy: A Visual Data and Detection Pipeline for Wearable Industrial Assistantscited by 6
  18. 2025HopaDIFF: Holistic-Partial Aware Fourier Conditioned Diffusion for Referring Human Action Segmentation in Multi-Person Scenarioscited by 5
  19. 2025RoHOI: Robustness Benchmark for Human-Object Interaction Detectioncited by 3
  20. 2024Anticipating Object State Changes in Long Procedural Videoscited by 2
  21. 2026Rethinking Video Human-Object Interaction: Set Prediction over Time for Unified Detection and Anticipationcited by 2
  22. 2026Live Interactive Training for Video Segmentationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026PROVIA: Procedure State Tracking for Online Mistake Detection in Egocentric Videoscited by 1
  2. 2026Hand-Aware Transition Modeling for Bimanual Procedural Anomaly Detectioncited by 0