Results 51 to 60 of about 517 (175)

Category-Level Contrastive Learning for Unsupervised Hashing in Cross-Modal Retrieval

open access: yesData Science and Engineering
Unsupervised hashing for cross-modal retrieval has received much attention in the data mining area. Recent methods rely on image-text paired data to conduct unsupervised cross-modal hashing in batch samples.
Mengying Xu   +3 more
doaj   +1 more source

Unsupervised Contrastive Graph Kolmogorov–Arnold Networks Enhanced Cross-Modal Retrieval Hashing

open access: yesMathematics
To address modality heterogeneity and accelerate large-scale retrieval, cross-modal hashing strategies generate compact binary codes that enhance computational efficiency.
Hongyu Lin   +3 more
doaj   +1 more source

LLM‐Powered Data Synthesis on Blockchain for Fusion Isomerism Learning in Heterogeneous Federated Systems

open access: yesCAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Severe data starvation, architectural heterogeneity and Byzantine vulnerabilities fundamentally impede the deployment of robust multiclass classification models in decentralised edge environments. To address these intertwined challenges, we propose fusion isomerism learning (FusionIL), a secure and domain‐agnostic framework that ...
Zhihao Hao   +5 more
wiley   +1 more source

Online Adaptive Supervised Hashing for Large-Scale Cross-Modal Retrieval

open access: yesIEEE Access, 2020
In recent years, with the continuous growth of multimedia data on the Internet, multimodal hashing has attracted increasing attention for its efficiency in large-scale cross-modal retrieval.
Ruoqi Su   +4 more
doaj   +1 more source

Intelligent Real‐Time Medical Image Transmission for Healthcare‐IoT via Dual‐Stage Probabilistic Restoration and Lightweight Nonlinear Encryption

open access: yesCAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Telemedicine and healthcare‐IoT require medical image transmission that preserves diagnostic quality and confidentiality under noise, packet loss and cyber threats. Existing methods often separate restoration from security and lack real‐time efficiency.
Mohamed Amine Midoun   +5 more
wiley   +1 more source

Unsupervised Contrastive Hashing With Autoencoder Semantic Similarity for Cross-Modal Retrieval in Remote Sensing

open access: yesIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
In large-scale multimodal remote sensing data archives, the application of cross-modal technology to achieve fast retrieval between different modalities has attracted great attention.
Na Liu   +5 more
doaj   +1 more source

3D Gaussian splatting for forensic autopsy documentation: Influence of image acquisition strategy on reconstruction quality

open access: yesJournal of Forensic Sciences, EarlyView.
Abstract Three‐dimensional (3D) documentation is an integral part of recording postmortem findings and reconstructing crime scenes. While photogrammetry is well established in forensic routine practice, deep learning‐based view synthesis has introduced 3D Gaussian splatting (3DGS) as a promising technique for fast and photorealistic 3D reconstruction ...
Constantin Lux   +7 more
wiley   +1 more source

Hierarchical Expert Fusion Hashing for Cross-Modal Retrieval

open access: yesIEEE Access
With the rapid growth of multimodal data, cross-modal hashing has become critical for efficient retrieval and storage. However, existing methods primarily emphasize similarity preservation in a shared embedding space while neglecting semantic ...
Xiyuan Wang, Yixin Zhu
doaj   +1 more source

Aligning Transnational due Diligence: The EU Deforestation Regulation and Brazil's Fragmented Beef Governance

open access: yesGlobal Policy, EarlyView.
ABSTRACT Transnational due diligence regulations, such as the European Union Regulation on Deforestation‐Free Products (EUDR), are reshaping sustainability governance by transforming voluntary norms into binding global rules. Yet, their effectiveness depends on how well they align with domestic governance systems and on the power asymmetries that ...
John James Loomis   +2 more
wiley   +1 more source

‘Can I keep myself safe?’ in a system lacking support: A qualitative study on overdose risk perceptions by people who co‐use benzodiazepine receptor agonists and opioids

open access: yesAddiction, EarlyView.
Abstract Background and aims Co‐use of benzodiazepines and z‐drugs [collectively termed benzodiazepine receptor agonists (BZRA)] with opioids is involved in a large proportion of drug‐related deaths. Historical and contemporary service provision rarely address the intersection between sociologically inherited disadvantage and current unmet treatment ...
Gabriele Vojt   +16 more
wiley   +1 more source

Home - About - Disclaimer - Privacy