MétaCan
Menu
Back to cohort

Occluded Face Recognition Through Enhanced Self-Attention and Cross-Attention Mechanisms

2025· article· W7127350119 on OpenAlexaff
Elhamsadat Hejazi, Majid Ahmadi, Arash Ahmadi

Bibliographic record

Venuenot available
Typearticle
Language
FieldComputer Science
TopicFace recognition and analysis
Canadian institutionsCarleton UniversityUniversity of Windsor
Fundersnot available
KeywordsBiometricsFacial recognition systemFocus (optics)Face (sociological concept)Three-dimensional face recognitionPattern recognition (psychology)Identification (biology)Encoding (memory)

Abstract

fetched live from OpenAlex

Occluded face recognition remains a critical challenge in biometric systems and real-world applications, where obscured facial features can significantly hinder identification accuracy. To address this issue, we present an approach that enhances the ResNet18 architecture by integrating positional encoding (PE) with multi-head self-attention (MHSA) and crossattention (CAM) mechanisms. This hybrid design enables the model to selectively focus on critical facial regions while mitigating the effects of occlusions. Evaluated on the Extended Yale B dataset with synthetic occlusions and the AR dataset with real-world occlusions, the proposed model demonstrates remarkable improvements in accuracy and robustness. Our method surpasses state-of-the-art techniques, particularly in scenarios with partial facial occlusions. This work improves occluded face recognition and supports the development of reliable next-generation biometric systems.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.001
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.004
Threshold uncertainty score0.009

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.001
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.000
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0030.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.017
GPT teacher head0.287
Teacher spread0.269 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designBench or experimental
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicFace recognition and analysisFrench-language works237,207