Skip to content
AI News HubLIVE
Original source2 min read

EgoPass-Bench: Identifying Objects That May Affect the Wearer's Passage in Egocentric Video

Summary

Researchers introduce EgoPass-Bench, a benchmark of real-world egocentric video recorded with Ray-Ban Meta smart glasses, to evaluate whether multimodal foundation models understand how surrounding entities affect the wearer's passage. The strongest model, GPT-6 Astra, recognizes object motion in 91.37% of comparisons but identifies changes in passage constraints only 66.50% of the time, and trails a two-person human baseline by 23.65 percentage points on entity-discovery questions.

SourcearXiv Computer VisionAuthor: Hongyu Wang, Chuhan Li, Congjin Xu, Xuandong Zhao, Hua Shen
EgoPass-Bench: Identifying Objects That May Affect the Wearer's Passage in Egocentric Video
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 18 Nov 2026]

Title:EgoPass-Bench: Identifying Objects That May Affect the Wearer's Passage in Egocentric Video

View a PDF of the paper titled EgoPass-Bench: Identifying Objects That May Affect the Wearer's Passage in Egocentric Video, by Hongyu Wang and 4 other authors

View PDF HTML (experimental)

Abstract:Understanding an egocentric environment requires reasoning about how surrounding entities affect the observer's actions. Existing evaluations of multimodal foundation models (MFMs) examine observer localization, motion trajectories, and action feasibility, but leave the discovery and interpretation of evolving observer-entity interactions insufficiently assessed. We introduce EgoPass-Bench, a benchmark for observer-relative interaction understanding in real-world egocentric video. EgoPass-Bench comprises 284 manually reviewed evaluation clips recorded using Ray-Ban Meta (Gen 2) smart glasses and 2,201 distinct questions across five tasks assessing motion perception, interaction judgments about specified entities, and relevant-entity discovery without target cues. Our evaluation of eight frame-based and six native-video configurations reveals a pronounced discrepancy between motion perception and interaction understanding. The strongest evaluated model, GPT-6 Astra, correctly recognizes object motion in 91.37% of 394 comparisons involving the same targets, but correctly identifies changes in passage constraints in only 66.50%. Across all 574 entity-discovery questions, it trails the two-person human baseline by $23.65 \pm 7.45$ percentage points (paired 95% CI), while exceeding the always-empty baseline (36.76%) by at least 18.9 percentage points. Further analysis reveals frequent inclusion of entities that neither pose a plausible physical conflict nor constrain passage, showing that accurate motion recognition does not ensure reliable relevant-entity discovery.

Subjects:

Computer Vision and Pattern Recognition (cs.CV)

Cite as: arXiv:2611.24995 [cs.CV]

(or arXiv:2611.24995v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2611.24995

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Hongyu Wang [view email] [v1] Wed, 18 Nov 2026 14:16:38 UTC (9,457 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled EgoPass-Bench: Identifying Objects That May Affect the Wearer's Passage in Egocentric Video, by Hongyu Wang and 4 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.CV

new | recent | 2026-11

Change to browse by:

cs

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

InvestorsAdvanced

Key points

  • EgoPass-Bench includes 284 manually reviewed egocentric clips and 2,201 questions across five tasks.
  • Eight frame-based and six native-video configurations were evaluated, revealing a gap between motion perception and interaction understanding.
  • GPT-6 Astra scores 91.37% on object motion recognition but only 66.50% on passage-constraint changes.
  • On entity discovery, the model lags the human baseline by 23.65 percentage points and often includes irrelevant entities.

Highlights and analysis are generated automatically and may contain errors. Check the original source.