ClusterE-ZSL: A Novel Cluster-Based Embedding for Enhanced Zero-Shot Learning in Contrastive Pre-Training Cross-Modal Retrieval

ClusterE-ZSL: A Novel Cluster-Based Embedding for Enhanced Zero-Shot Learning in Contrastive Pre-Training Cross-Modal Retrieval

Zero-shot learning (ZSL) in a multi-model environment presents significant challenges and opportunities for improving cross-modal retrieval and object detection in unseen data. This study introduced a novel embedding approach of vector space clustering to address image-to-text and text-to-image retr...

Full description

Saved in:
Bibliographic Details
Main Authors: Umair Tariq, Zonghai Hu, Khawaja Tauseef Tasneem, Md Belal Bin Heyat, Muhammad Shahid Iqbal, Kamran Aziz
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Contrastive learning
embedded
cluster
self-supervised learning
embedded computing
cross-modal retrieval
Online Access:https://ieeexplore.ieee.org/document/10707265/
Tags: Add Tag
No Tags, Be the first to tag this record!

Internet

https://ieeexplore.ieee.org/document/10707265/

Similar Items