EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Human–AI Divergence in Ego-Centric Action Recognition Under Spatial and Spatiotemporal Manipulations

Sadegh Rahmaniboldaji, Filip Rybansky, Quoc C. Vuong, Anya C. Hurlbert, Frank Guerin, Andrew Gilbert

International Journal of Computer Vision · 2026-12 · 134 (12)

DOI: 10.1007/s11263-026-03077-7 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Computer Vision, online erschienen am 19.11.2026. Verfasst von Sadegh Rahmaniboldaji und 5 weiteren Autor:innen. Die Arbeit nennt 95 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Leverhulme Trust.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Humans consistently outperform state-of-the-art AI models in action recognition, particularly in challenging real-world conditions involving low resolution, occlusion, and visual clutter.e those utilised by humans Understanding the sources of this performance gap is essential for developing more robust and human-aligned models. In this paper, we present a large-scale human AI comparative study of egocentric action recognition using human-defined Minimal Identifiable Recognition Crops (MIRCs), defined as the smallest spatial or spatiotemporal regions sufficient for reliable human recognition. We used our previously introduced, Epic-ReduAct, a systematically spatially reduced and temporally scrambled dataset derived from 36 EPIC-KITCHENS videos, spanning multiple spatial reduction levels and temporal conditions. Recognition performance is evaluated using over 3,000 human participants, Side4Video, and Qwen 3.5 9B models. Our analysis combines quantitative metrics, Average Reduction Rate and Recognition Gap, with qualitative analyses of spatial (high-, mid-, and low-level visual features) and spatiotemporal factors, including a categorisation of actions into Low Temporal Actions (LTA) and High Temporal Actions (HTA). Results show that human performance exhibits sharp declines when transitioning from MIRCs to sub-MIRCs, reflecting a strong reliance on sparse, semantically critical cues such as hand object interactions. In contrast, the model degrades more gradually and often relies on contextual and mid- to low-level features, sometimes even exhibiting increased confidence under spatial reduction. Temporally, humans remain robust to scrambling when key spatial cues are preserved, whereas the model often shows insensitivity to temporal disruption, revealing class-dependent temporal sensitivities. Overall, our findings demonstrate that strong benchmark performance can obscure fundamental human AI misalignment and highlight limitations in current spatial and spatiotemporal representations, suggesting concrete directions for more efficient and human-aligned action recognition systems.

Förderung

  • Leverhulme Trust

Zitieren

APA

Rahmaniboldaji, S., Rybansky, F., Vuong, Q. C., Hurlbert, A. C., Guerin, F., & Gilbert, A. (2026). Human–AI Divergence in Ego-Centric Action Recognition Under Spatial and Spatiotemporal Manipulations. International Journal of Computer Vision, 134(12). https://doi.org/10.1007/s11263-026-03077-7

Vancouver

Rahmaniboldaji S, Rybansky F, Vuong QC, Hurlbert AC, Guerin F, Gilbert A. Human–AI Divergence in Ego-Centric Action Recognition Under Spatial and Spatiotemporal Manipulations. International Journal of Computer Vision. 2026;134(12). doi:10.1007/s11263-026-03077-7

BibTeX
@article{Rahmaniboldaji2026,
  author = {Rahmaniboldaji, Sadegh and Rybansky, Filip and Vuong, Quoc C. and Hurlbert, Anya C. and Guerin, Frank and Gilbert, Andrew},
  title = {Human–AI Divergence in Ego-Centric Action Recognition Under Spatial and Spatiotemporal Manipulations},
  journal = {International Journal of Computer Vision},
  year = {2026},
  volume = {134},
  number = {12},
  doi = {10.1007/s11263-026-03077-7}
}
Kostenlos starten →