An overview of cross-media retrieval: Concepts, methodologies, benchmarks, and challenges

Y Peng, X Huang, Y Zhao - … on circuits and systems for video …, 2017 - ieeexplore.ieee.org
Multimedia retrieval plays an indispensable role in big data utilization. Past efforts mainly
focused on single-media retrieval. However, the requirements of users are highly flexible …

A comprehensive survey on cross-modal retrieval

K Wang, Q Yin, W Wang, S Wu, L Wang - arXiv preprint arXiv:1607.06215, 2016 - arxiv.org
In recent years, cross-modal retrieval has drawn much attention due to the rapid growth of
multimodal data. It takes one type of data as the query to retrieve relevant data of another …

Channel augmented joint learning for visible-infrared recognition

M Ye, W Ruan, B Du, MZ Shou - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
This paper introduces a powerful channel augmented joint learning strategy for the visible-
infrared recognition problem. For data augmentation, most existing methods directly adopt …

An end-to-end steel surface defect detection approach via fusing multiple hierarchical features

Y He, K Song, Q Meng, Y Yan - IEEE transactions on …, 2019 - ieeexplore.ieee.org
A complete defect detection task aims to achieve the specific class and precise location of
each defect in an image, which makes it still challenging for applying this task in practice …

A decade survey of content based image retrieval using deep learning

SR Dubey - IEEE Transactions on Circuits and Systems for …, 2021 - ieeexplore.ieee.org
The content based image retrieval aims to find the similar images from a large scale dataset
against a query image. Generally, the similarity between the representative features of the …

Deep supervised cross-modal retrieval

L Zhen, P Hu, X Wang, D Peng - Proceedings of the IEEE …, 2019 - openaccess.thecvf.com
Cross-modal retrieval aims to enable flexible retrieval across different modalities. The core
of cross-modal retrieval is how to measure the content similarity between different types of …

RGB-infrared cross-modality person re-identification

A Wu, WS Zheng, HX Yu, S Gong… - Proceedings of the …, 2017 - openaccess.thecvf.com
Person re-identification (Re-ID) is an important problem in video surveillance, aiming to
match pedestrian images across camera views. Currently, most works focus on RGB-based …

Dual-path convolutional image-text embeddings with instance loss

Z Zheng, L Zheng, M Garrett, Y Yang, M Xu… - ACM Transactions on …, 2020 - dl.acm.org
Matching images and sentences demands a fine understanding of both modalities. In this
article, we propose a new system to discriminatively embed the image and text to a shared …

Visible-infrared person re-identification via homogeneous augmented tri-modal learning

M Ye, J Shen, L Shao - IEEE Transactions on Information …, 2020 - ieeexplore.ieee.org
Matching person images between the daytime visible modality and night-time infrared
modality (VI-ReID) is a challenging cross-modality pedestrian retrieval problem. Existing …

A survey of multi-view representation learning

Y Li, M Yang, Z Zhang - IEEE transactions on knowledge and …, 2018 - ieeexplore.ieee.org
Recently, multi-view representation learning has become a rapidly growing direction in
machine learning and data mining areas. This paper introduces two categories for multi …