MétaCan
Menu
Back to cohort
Record W4406203409 · doi:10.61091/jcmcc123-12

A Text-Free Training Method for Generating Face Images Based on Chinese Text

2024· article· en· W4406203409 on OpenAlexvenueno aff
Songlin Tong, Meiling Liu, Jiyun Zhou

Bibliographic record

VenueJournal of Combinatorial Mathematics and Combinatorial Computing · 2024
Typearticle
Languageen
FieldComputer Science
TopicFace recognition and analysis
Canadian institutionsnot available
FundersNatural Science Foundation of Heilongjiang ProvinceNational Natural Science Foundation of China
KeywordsComputer scienceGenerator (circuit theory)Face (sociological concept)Artificial intelligenceEmbeddingImage (mathematics)Generative adversarial networkNatural language processingConstruct (python library)Word (group theory)Pattern recognition (psychology)Semantics (computer science)Word embeddingFeature (linguistics)Feature extractionMathematics

Abstract

fetched live from OpenAlex

Generative adversarial network (GAN) technology has enabled the automatic synthesis of realistic face images from text. This paper proposes a model for generating face images from Chinese text by integrating a text mapping module with the StyleGAN generator. The text mapping module utilizes the CLIP model for pre-training Chinese text, employs a convolutional-inverse convolutional structure to enhance feature extraction, and incorporates a BiLSTM model to construct complete sentences as inputs for the StyleGAN generator. The generator interprets semantic features to generate face images. Validation on Face2Text and COCO datasets yields F1 values of 83.43% and 84.97%, respectively, while achieving the lowest FID and FSD scores of 103.25 and 1.26. The combination of CLIP pre-training and word-level semantic embedding improves image quality, offering a novel approach for face recognition applications in public safety.

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 distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.003
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Scholarly communication
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.704
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0030.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0010.000
Open science0.0010.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

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 head0.021
GPT teacher head0.301
Teacher spread0.279 · 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 teacher head, not a consensus.

Study designTheoretical or conceptual
Domainnot available
GenreMethods

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
Published2024
Admission routes1
Has abstractyes

Explore more

Same venueJournal of Combinatorial Mathematics and Combinatorial ComputingSame topicFace recognition and analysisFrench-language works237,207