MétaCan
Menu
Back to cohort
Record W4413755129 · doi:10.1109/tce.2025.3603210

Improved Cross-Modal Retrieval Systems Using Self-Reinforcement and Quadruplet Alignment Hashing

2025· article· en· W4413755129 on OpenAlexaff
Xiaoqing Liu, Zhiwen Yu, Jun Jiang, Bin Wang, Fa Zhu, Xingchi Chen, Witold Pedrycz

Bibliographic record

VenueIEEE Transactions on Consumer Electronics · 2025
Typearticle
Languageen
FieldComputer Science
TopicAdvanced Image and Video Retrieval Techniques
Canadian institutionsUniversity of Alberta
FundersNational Natural Science Foundation of China
KeywordsComputer scienceModalHash functionReinforcementArtificial intelligenceComputer visionPattern recognition (psychology)Speech recognitionEngineeringStructural engineeringComputer security

Abstract

fetched live from OpenAlex

Cross-modal retrieval presents significant challenges for consumer technology applications, demanding innovative approaches to bridge semantic gaps between different data modalities while ensuring efficient information access. This paper introduces a novel Self-Reinforcement and Quadruplet Alignment Hashing (SRQA) framework specifically designed to enhance cross-modal retrieval systems for improved user experiences. Our approach distinguishes itself through three key contributions. First, we develop a dynamic unified similarity matrix that adaptively balances label-driven semantic information with modality-specific correlations, enabling more nuanced cross-modal representations than traditional fixed alignment strategies. Second, we propose a novel quadruplet-based hashing method that implements an efficient hard sample mining strategy through the refinement of both absolute and relative distance constraints between samples, thereby providing a more precise and efficient semantic alignment mechanism for cross-modal retrieval. Third, through extensive experiments conducted on three benchmark datasets—MIRFLICKR-25K, NUS-WIDE, and MS-COCO—our framework consistently outperforms ten state-of-the-art cross-modal retrieval methods across various hash code lengths, offering significant advancements for consumer technology applications requiring efficient multi-modal information retrieval.

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)0.002
metaresearch head score (Gemma)0.005
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.004
Threshold uncertainty score0.012

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0020.005
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0010.001
Scholarly communication0.0010.003
Open science0.0020.003
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0040.003

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 head0.014
GPT teacher head0.298
Teacher spread0.284 · 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 designSimulation or modeling
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

Citations2
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueIEEE Transactions on Consumer ElectronicsSame topicAdvanced Image and Video Retrieval TechniquesFrench-language works237,207