AI Science Tracker
EN

Changzhou University

1 discovery from 2024

Discoveries

DNet: a depression recognition network combining residual network and vision transformer.

Source check: Source checked. Not independent scientific confirmation.

Finding: VOR reports MAE/RMSE 6.09/7.85 on AVEC2014 and 6.73/8.47 on CZ2023; first Research Square V1 contains the same severity-estimation task/result. Dual global/local facial feature modules, feature-pyramid fusion and ViT temporal representation predict BDI-II/HAMD scores. Testing: Held-out samples on public and hospital datasets, but no external-site test; AVEC multiple videos per person are split as sample units, so independence of test participants is not assured.. Primary BMC Psychiatry Methods/Results evaluate DNet against BDI-II/HAMD score labels on AVEC2014 and 373-person CZ2023. The model estimates questionnaire severity from facial video; it is not a depression diagnosis. AVEC videos from some participants are treated as independent samples, creating possible participant leakage. Source affiliation was not stated in the reviewed case checks and was unavailable in the local bibliographic cache.

Technology: Dual global/local facial feature modules, feature-pyramid fusion and ViT temporal representation predict BDI-II/HAMD scores.

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
Dual global/local facial feature modules, feature-pyramid fusion and ViT temporal representation predict BDI-II/HAMD scores.
Test and result
Held-out samples on public and hospital datasets, but no external-site test; AVEC multiple videos per person are split as sample units, so independence of test participants is not assured.
Limitation / still unknown
Generalizability beyond the reported study population, data, and protocol was not established in the reviewed material.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://link.springer.com/article/10.1186/s12888-025-07322-0

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open the interactive profile for the timeline, or browse all organizations and model families.