Metraipolis › archive › dc_dd6ea0452d93

Toward Low-Burden Image-Based Dietary Assessment Through Human-AI Collaborative Correction — arXiv:2610.41300

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41300
License (as archived)
CC0-1.0
Archived
2026-11-02T04:51:05.798Z
SHA-256 of the archived text
38844aadec29cf2c93d998b4914e0b208deafaa287df6231b4e99006981576b3
Stable URL of this page
https://metraipolis.com/documento/dc_dd6ea0452d93

How to cite

Toward Low-Burden Image-Based Dietary Assessment Through Human-AI Collaborative Correction — arXiv:2610.41300 — arXiv (en), https://arxiv.org/abs/2610.41300 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dd6ea0452d93 (Metraipolis archive dc_dd6ea0452d93, sha256 38844aadec29cf2c93d998b4914e0b208deafaa287df6231b4e99006981576b3)
BibTeX
@misc{dcdd6ea0452d93,
  title = {Toward Low-Burden Image-Based Dietary Assessment Through Human-AI Collaborative Correction — arXiv:2610.41300},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41300},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dd6ea0452d93; sha256 38844aadec29cf2c93d998b4914e0b208deafaa287df6231b4e99006981576b3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41300. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Image-based dietary assessment can automate initial food logging, but meal photographs often leave food identity, hidden ingredients, preparation, and portion uncertain, making correction a recurring part of use. We introduce Human-AI Collaborative Correction, which reframes correction as communicate intent $\rightarrow$ regenerate $\rightarrow$ verify: users express what should change through text, voice, or guided clarification, the AI regenerates the linked dietary record, and users verify the result. In a within-participant study with 30 participants, compared with conventional Manual Search-and-Edit Correction, collaborative correction was associated with lower workload (Raw TLX: 35.83 vs. 55.00; p < .001), 21.0% lower recorded usage time, 51.1% fewer recorded clicks, and more favorable user-experience ratings; 90.0% preferred it overall. An exploratory nutrient analysis also found lower energy MAE. These findings support intent-driven regeneration as a promising interaction pattern for reducing correction burden while preserving user verification and making image-based dietary tracking easier to sustain.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.HC, nuovi lavori del giorno).
Categorie arXiv: Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2610.41300 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-02T04:44:57.631Z dalla pagina https://arxiv.org/list/cs.HC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).