Hashing Model Research Articles

A Dual-Module System for Copyright-Free Image Recommendation and Infringement Detection in Educational Materials

Images are extensively utilized in educational materials due to their efficacy in conveying complex concepts. However, unauthorized use of images frequently results in legal issues related to copyright infringement. To mitigate this problem, we introduce a dual-module system specifically designed for educators. The first module, a copyright infringement detection system, employs deep learning techniques to verify the copyright status of images. It utilizes a Convolutional Variational Autoencoder (CVAE) model to extract significant features from copyrighted images and compares them against user-provided images. If infringement is detected, the second module, an image retrieval system, recommends alternative copyright-free images using a Vision Transformer (ViT)-based hashing model. Evaluation on benchmark datasets demonstrates the system’s effectiveness, achieving a mean Average Precision (mAP) of 0.812 on the Flickr25k dataset. Additionally, a user study involving 65 teachers indicates high satisfaction levels, particularly in addressing copyright concerns and ease of use. Our system significantly aids educators in creating educational materials that comply with copyright regulations.

A novel Deep High-level Concept-mining Jointing Hashing Model for unsupervised cross-modal retrieval

Unsupervised cross-modal hashing has achieved great success in various information retrieval applications owing to its efficient storage usage and fast retrieval speed. Recent studies have primarily focused on training the hash-encoded networks by calculating a sample-based similarity matrix to improve the retrieval performance. However, there are two issues remain to solve: (1) The current sample-based similarity matrix only considers the similarity between image-text pairs, ignoring the different information densities of each modality, which may introduce additional noise and fail to mine key information for retrieval; (2) Most existing unsupervised cross-modal hashing methods only consider alignment between different modalities, while ignoring consistency between each modality, resulting in semantic conflicts. To tackle these challenges, a novel Deep High-level Concept-mining Jointing Hashing (DHCJH) model for unsupervised cross-modal retrieval is proposed in this study. DHCJH is able to capture the essential high-level semantic information from image modalities and integrate into the text modalities to improve the accuracy of guidance information. Additionally, a new hashing loss with a regularization term is introduced to avoid the cross-modal semantic collision and false positive pairs problems. To validate the proposed method, extensive comparison experiments on benchmark datasets are conducted. Experimental findings reveal that DHCJH achieves superior performance in both accuracy and efficiency. The code of DHCJH is available at Github.

Retraction Note: Bilateral hashing model of ECG signal encryption system using downhill peak follow (DPF)-based encryption technique

Retraction Note: Bilateral hashing model of ECG signal encryption system using downhill peak follow (DPF)-based encryption technique

DSCEH: Dual-Stream Correlation-Enhanced Deep Hashing for Image Retrieval

Deep Hashing is widely used for large-scale image-retrieval tasks to speed up the retrieval process. Current deep hashing methods are mainly based on the Convolutional Neural Network (CNN) or Vision Transformer (VIT). They only use the local or global features for low-dimensional mapping and only use the similarity loss function to optimize the correlation between pairwise or triplet images. Therefore, the effectiveness of deep hashing methods is limited. In this paper, we propose a dual-stream correlation-enhanced deep hashing framework (DSCEH), which uses the local and global features of the image for low-dimensional mapping and optimizes the correlation of images from the model architecture. DSCEH consists of two main steps: model training and deep-hash-based retrieval. During the training phase, a dual-network structure comprising CNN and VIT is employed for feature extraction. Subsequently, feature fusion is achieved through a concatenation operation, followed by similarity evaluation based on the class token acquired from VIT to establish edge relationships. The Graph Convolutional Network is then utilized to enhance correlation optimization between images, resulting in the generation of high-quality hash codes. This stage facilitates the development of an optimized hash model for image retrieval. In the retrieval stage, all images within the database and the to-be-retrieved images are initially mapped to hash codes using the aforementioned hash model. The retrieval results are subsequently determined based on the Hamming distance between the hash codes. We conduct experiments on three datasets: CIFAR-10, MSCOCO, and NUSWIDE. Experimental results show the superior performance of DSCEH, which helps with fast and accurate image retrieval.

Deep Attention Fusion Hashing (DAFH) Model for Medical Image Retrieval.

To address this, we propose a novel deep learning-based hashing model, the Deep Attention Fusion Hashing (DAFH) model, which integrates advanced attention mechanisms with medical imaging data. The DAFH model enhances retrieval performance by integrating multi-modality medical imaging data and employing attention mechanisms to optimize the feature extraction process. Utilizing multimodal medical image data from the Cancer Imaging Archive (TCIA), this study constructed and trained a deep hashing network that achieves high-precision classification of various cancer types. At hash code lengths of 16, 32, and 48 bits, the model respectively attained Mean Average Precision (MAP@10) values of 0.711, 0.754, and 0.762, highlighting the potential and advantage of the DAFH model in medical image retrieval. The DAFH model demonstrates significant improvements in the efficiency and accuracy of medical image retrieval, proving to be a valuable tool in clinical settings.

An improved deep hashing model for image retrieval with binary code similarities

The exponential growth of data raises an unprecedented challenge in data analysis: how to retrieve interesting information from such large-scale data. Hash learning is a promising solution to address this challenge, because it may bring many potential advantages, such as extremely high efficiency and low storage cost, after projecting high-dimensional data to compact binary codes. However, traditional hash learning algorithms often suffer from the problem of semantic inconsistency, where images with similar semantic features may have different binary codes. In this paper, we propose a novel end-to-end deep hashing method based on the similarities of binary codes, dubbed CSDH (Code Similarity-based Deep Hashing), for image retrieval. Specifically, it extracts deep features from images to capture semantic information using a pre-trained deep convolutional neural network. Additionally, a hidden and fully connected layer is attached at the end of the deep network to derive hash bits by virtue of an activation function. To preserve the semantic consistency of images, a loss function has been introduced. It takes the label similarities, as well as the Hamming embedding distances, into consideration. By doing so, CSDH can learn more compact and powerful hash codes, which not only can preserve semantic similarity but also have small Hamming distances between similar images. To verify the effectiveness of CSDH, we evaluate CSDH on two public benchmark image collections, i.e., CIFAR-10 and NUS-WIDE, with five classic shallow hashing models and six popular deep hashing ones. The experimental results show that CSDH can achieve competitive performance to the popular deep hashing algorithms.

Effective Comparative Prototype Hashing for Unsupervised Domain Adaptation

Unsupervised domain adaptive hashing is a highly promising research direction within the field of retrieval. It aims to transfer valuable insights from the source domain to the target domain while maintaining high storage and retrieval efficiency. Despite its potential, this field remains relatively unexplored. Previous methods usually lead to unsatisfactory retrieval performance, as they frequently directly apply slightly modified domain adaptation algorithms to hash learning framework, or pursue domain alignment within the Hamming space characterized by limited semantic information. In this paper, we propose a simple yet effective approach named Comparative Prototype Hashing (CPH) for unsupervised domain adaptive image retrieval. We establish a domain-shared unit hypersphere space through prototype contrastive learning and then obtain the Hamming hypersphere space via mapping from the shared hypersphere. This strategy achieves a cohesive synergy between learning uniformly distributed and category conflict-averse feature representations, eliminating domain discrepancies, and facilitating hash code learning. Moreover, by leveraging dual-domain information to supervise the entire hashing model training process, we can generate hash codes that retain inter-sample similarity relationships within both domains. Experimental results validate that our CPH significantly outperforms the state-of-the-art counterparts across multiple cross-domain and single-domain retrieval tasks. Notably, on Office-Home and Office-31 datasets, CPH achieves an average performance improvement of 19.29% and 13.85% on cross-domain retrieval tasks compared to the second-best results, respectively. The source codes of our method are available at: https://github.com/christinecui/CPH.

Structure-aware contrastive hashing for unsupervised cross-modal retrieval

Cross-modal hashing has attracted a lot of attention and achieved remarkable success in large-scale cross-media similarity retrieval applications because of its superior computational efficiency and low storage overhead. However, constructing similarity relationship among samples in cross-modal unsupervised hashing is challenging because of the lack of manual annotation. Most existing unsupervised methods directly use the representations extracted from the backbone of their respective modality to construct instance similarity matrices, leading to inaccurate similarity matrices and resulting in suboptimal hash codes. To address this issue, a novel unsupervised hashing model, named Structure-aware Contrastive Hashing for Unsupervised Cross-modal Retrieval (SACH), is proposed in this paper. Specifically, we concurrently employ both high-dimensional representations and discriminative representations learned by the network to construct a more informative semantic correlative matrix across modalities. Moreover, we design a multimodal structure-aware alignment network to minimize heterogeneous gap in the high-order semantic space of each modality, effectively reducing disparities within heterogeneous data sources and enhancing the consistency of semantic information across modalities. Extensive experimental results on two widely utilized datasets demonstrate the superiority of our proposed SACH method in cross-modal retrieval tasks over existing state-of-the-art methods.

Joint Heterogeneous PUF-Based Security-Enhanced IoT Authentication

This study proposes a novel authentication scheme that provides enhanced security for Internet of Things (IoT) applications by integrating a radio frequency (RF) physical unclonable function (PUF) with a device PUF. While traditional PUF-based authentication methods are lightweight, they are vulnerable to replay attacks because challenge-response pairs (CRPs) are exposed to adversaries over wireless channels. To prevent CRP exposure, we propose a joint scheme that integrates the physical layer features of wireless channels with those of the device PUF. Our authentication process consists of two stages: an enrollment stage and an authentication stage. During the enrollment stage, the physical features of the static random-access memory (SRAM) in the IoT devices are shared with the server, which generates a hashing model using the amplitudes of channel state information (CSI) as the RF-PUF and transfers it to the IoT device. In the authentication stage, the server and IoT devices exchange pilot signals to estimate the shared CSI. Both parties then generate the challenge information using the hashing model, which depends on the CSI. The challenge information is mapped to the response of the device PUF as the cryptographic key. If both parties are legitimate, the proposed model is updated through CSI amplitudes. We evaluated the proposed authentication protocol using a testbed based on Raspberry Pi and acquired a CSI dataset and SRAM-PUF using universal software radio peripheral and Arduino, respectively. Numerical results demonstrate that our method effectively defends against diverse attacks, even in critical CRP exposure scenarios.

A novel Siamese deep hashing model for histopathology image retrieval

A novel Siamese deep hashing model for histopathology image retrieval

Robust Authentication Analysis of Copyright Images through Deep Hashing Models with Self-supervision

The increased usage of the internet and ICT has posed a significant challenge to protect copyrighted content due to advanced image forgery techniques that make image authentication extremely difficult. The aim of this paper is to establish a binary classification method for determining copyright images from copyright-free ones. A deep hashing model is introduced for an image authentication system, which uses deep learning-based perceptual hashing. Hash codes from a deep hashing model trained with a copyright image dataset are used to identify images. The deep learning model is able to learn features that represent the implicit meaning or structural information of an image. The copyright dataset, which lacks class labels, is trained with deep hashing models with self-supervision. The proposed model is based on an autoencoder or variational autoencoder model and is improved by including convolutional filters, residual blocks, and vision transformer blocks. Experimental results show that the proposed model performs a one-to-one mapping with most stored images and can retrieve related images using image features in hash collisions. The model can find the query image among the top 5 images with comparable hash codes. The results indicate that the proposed deep hashing approach is robust and applicable.

Editorial

Dear Readers,  It gives me great pleasure to announce the eighth regular issue of 2023. In this issue, five papers by 24 authors from nine countries cover various topical aspects of computer science. In an ongoing effort to further strengthen our journal, I would like to expand the editorial board: If you are a tenured associate professor or above with a strong publication record, you are welcome to apply to join our editorial board. We are also interested in high-quality proposals for special issues on new topics and trends.  As always, I would like to thank all the authors for their sound research and the editorial board for their extremely valuable review effort and suggestions for improvements. These contributions, together with the generous support of the consortium members, sustain the quality of our journal.  As we want to secure the financial support also for the years to come, we are looking for institutions and libraries to financially support our diamond open access journal as consortium members, who will then benefit from the research community, international visibility, and the opportunity to manage special issues and focused topics within the journal. Please think about the possibility of such financial participation of your institution, we would be very grateful for any kind of support.  In this regular issue, I am very pleased to introduce the following 5 accepted articles: In a collaborative research effort between Jordan and Qatar, Ahmad Abusukhon, Ala Al-Fuqaha and Belal Hawashin present their technique for detecting underground water pipeline leakage based on an Internet of Things approach. In another collaboration between researchers from Croatia and Bosnia and Herzegovina, Ani Grubišić, Slavomir Stankov, Branko Žitko, Ines Šarić-Grgić, Angelina Gašpar, Emil Brajković, and Daniel Vasić describe and evaluate the performance of a semiautomatic authoring tool for knowledge extraction in the AC&NL Tutor and discuss strengths and weaknesses. Also in a collaboration between researchers from the United States and United Arab Emirates, Longhao Li, Taieb Znati, and Rami Melhem propose an energy-aware fault-tolerance model for silent error detection and mitigation in heterogeneous extreme-scale computing environments, referred to diffReplication, which is associated with one replica that executes at the same rate as the main process, and one diffReplica that is executed at a fraction of the execution rate of the main process. In a collaboration between researchers form China and Japan, Xiaojuan Liao, Hui Zhang, Miyuki Koshimura, Rong Huang, and Fagen Li propose in their paper an optimized strategy for solving restricted preemptive scheduling on parallel machines applying Partial Maximum Satisfiability (PMS), an optimized version of a Boolean Satisfiability (SAT) solver. Finally, in a collaboration between researchers from South Korea and the USA, Jaeyoung Yang, Sooin Kim, Sangwoo Lee, Won-gyum Kim, Donghoon Kim, and Doosung Hwang aim in their paper to establish a binary classification method for distinguishing copyrighted and noncopyrighted images by introducing a deep hashing model for an image authentication system, which uses deep learning-based perceptual hashing.  Enjoy Reading!  Cordially, Christian Gütl, Managing Editor 

One for more: Structured Multi-Modal Hashing for multiple multimedia retrieval tasks

Hashing has been widely studied in support of efficient multimedia retrieval due to its high computation and storage efficiency. However, existing multimedia hashing models are designed only for specific multimedia retrieval tasks, e.g., cross-modal retrieval and composite multi-modal retrieval. To simultaneously support multiple multimedia retrieval tasks, multiple different hashing models should be equipped in a multimedia retrieval system. This paper proposes a Structured Multi-Modal Hashing (SMMH) method, which can learn only a hash model for multiple multimedia retrieval tasks. Specifically, we generate structured hash codes by independently projecting the modality data into the Hamming space, where each part of hash codes preserves the specific characteristic of the specific modality data, and they are collaborated to represent the whole multi-modal data. To bridge the heterogeneous gap between multiple modalities, a fusion multi-modal space is constructed based on structured hash codes with label and pair-wise semantic supervision. Besides, we learn hash functions for composite multi-modal retrieval by projecting heterogeneous modalities into the collaborative multi-modal features. Finally, we develop a discrete hash optimization strategy to efficiently solve binary hash codes. Extensive experiments show that our model outperforms the strong baseline methods on multiple multimedia retrieval tasks. Source codes are available at https://github.com/ChaoqunZheng/SMMH.

Contrastive Masked Autoencoders for Self-Supervised Video Hashing

Self-Supervised Video Hashing (SSVH) models learn to generate short binary representations for videos without ground-truth supervision, facilitating large-scale video retrieval efficiency and attracting increasing research attention. The success of SSVH lies in the understanding of video content and the ability to capture the semantic relation among unlabeled videos. Typically, state-of-the-art SSVH methods consider these two points in a two-stage training pipeline, where they firstly train an auxiliary network by instance-wise mask-and-predict tasks and secondly train a hashing model to preserve the pseudo-neighborhood structure transferred from the auxiliary network. This consecutive training strategy is inflexible and also unnecessary. In this paper, we propose a simple yet effective one-stage SSVH method called ConMH, which incorporates video semantic information and video similarity relationship understanding in a single stage. To capture video semantic information for better hashing learning, we adopt an encoder-decoder structure to reconstruct the video from its temporal-masked frames. Particularly, we find that a higher masking ratio helps video understanding. Besides, we fully exploit the similarity relationship between videos by maximizing agreement between two augmented views of a video, which contributes to more discriminative and robust hash codes. Extensive experiments on three large-scale video datasets (i.e., FCVID, ActivityNet and YFCC) indicate that ConMH achieves state-of-the-art results. Code is available at https://github.com/huangmozhi9527/ConMH.

Bilateral hashing model of ECG signal encryption system using downhill peak follow (DPF)-based encryption technique

Bilateral hashing model of ECG signal encryption system using downhill peak follow (DPF)-based encryption technique

PLDH: Pseudo-Labels Based Deep Hashing

Deep hashing has received a great deal of attraction in large-scale data analysis, due to its high efficiency and effectiveness. The performance of deep hashing models heavily relies on label information, which is very expensive to obtain. In this work, a novel end-to-end deep hashing model based on pseudo-labels for large-scale data without labels is proposed. The proposed hashing model consists of two major stages, where the first stage aims to obtain pseudo-labels based on deep features extracted by a pre-training deep convolution neural network. The second stage generates hash codes with high quality by the same neural network in the previous stage, coupled with an end-to-end hash layer, whose purpose is to encode data into a binary representation. Additionally, a quantization loss is introduced and interwound within these two stages. Evaluation experiments were conducted on two frequently-used image collections, CIFAR-10 and NUS-WIDE, with eight popular shallow and deep hashing models. The experimental results show the superiority of the proposed method in image retrieval.

An optimized deep supervised hashing model for fast image retrieval

As multimedia data grows exponentially, searching for and retrieving a relevant image is becoming a challenge for researchers. Hashing is a widely adopted method because of its high performance in image retrieval with deep neural networks and multiple convolutional layers. Even so, most hashing methods ignore the computational cost and memory storage consumption. When the deep hashing model size is large, it leads to a slowdown in the response time of the model compared to the small model. Addressing these issues, a novel optimized deep supervised hashing based on a teacher-student approach for swift and precise image retrieval is proposed in this paper. In this work, the small student model is trained using the knowledge distillation from the large teacher model and the information from the one-hot labels. Therefore, a weight allocation loss function based on the teacher and student models is defined. Meanwhile, we apply model pruning to decrease the amount of the student model further to increase the response time. Therefore, knowledge distillation is performed on the pruned model. After that, the remaining weights are quantized to reach the smaller size of the model. Extensive experimental outcomes on two widely used datasets prove the outstanding efficiency of our proposed method.

An Online Hashing Algorithm for Image Retrieval Based on Optical-Sensor Network.

Online hashing is a valid storage and online retrieval scheme, which is meeting the rapid increase in data in the optical-sensor network and the real-time processing needs of users in the era of big data. Existing online-hashing algorithms rely on data tags excessively to construct the hash function, and ignore the mining of the structural features of the data itself, resulting in a serious loss of the image-streaming features and the reduction in retrieval accuracy. In this paper, an online hashing model that fuses global and local dual semantics is proposed. First, to preserve the local features of the streaming data, an anchor hash model, which is based on the idea of manifold learning, is constructed. Second, a global similarity matrix, which is used to constrain hash codes is built by the balanced similarity between the newly arrived data and previous data, which makes hash codes retain global data features as much as possible. Then, under a unified framework, an online hash model that integrates global and local dual semantics is learned, and an effective discrete binary-optimization solution is proposed. A large number of experiments on three datasets, including CIFAR10, MNIST and Places205, show that our proposed algorithm improves the efficiency of image retrieval effectively, compared with several existing advanced online-hashing algorithms.

Adaptive hash code balancing for remote sensing image retrieval

ABSTRACT Remote sensing image retrieval (RSIR) refers to finding images from an image database that contain the same instance as the query image, which is an essential task in remote sensing applications. Traditional depth-based hashing algorithms usually convert the image library into a hash matrix with a specified number of digits. On the one hand, the quality of hash matrices generated by traditional methods is low and cannot guarantee good clustering between pictures of the same class. On the other hand, the ability to extract features using backbone networks must be improved. This paper proposes a deep hashing model called adaptive hash code balancing (AHCB) to solve two existing problems. The model introduces a balanced binary method to maximize the hash value entropy so that the generated hash has better clustering. Graph convolutional networks(GCNs) are introduced to automatically detect relevant data points in the graph, perform back-propagation, and propagate the updated network feedback to the feature extraction layer to improve the ability to extract features. It enables the model to learn the intrinsic data structure between remote sensing images. Experimental results on three public datasets show that the proposed method outperforms the current state-of-the-art deep hashing remote sensing image retrieval algorithms by a large margin.

Unsupervised Adaptive Feature Selection with Binary Hashing.

Unsupervised feature selection chooses a subset of discriminative features to reduce feature dimension under the unsupervised learning paradigm. Although lots of efforts have been made so far, existing solutions perform feature selection either without any label guidance or with only single pseudo label guidance. They may cause significant information loss and lead to semantic shortage of the selected features as many real-world data, such as images and videos are generally annotated with multiple labels. In this paper, we propose a new Unsupervised Adaptive Feature Selection with Binary Hashing (UAFS-BH) model, which learns binary hash codes as weakly-supervised multi-labels and simultaneously exploits the learned labels to guide feature selection. Specifically, in order to exploit the discriminative information under the unsupervised scenarios, the weakly-supervised multi-labels are learned automatically by specially imposing binary hash constraints on the spectral embedding process to guide the ultimate feature selection. The number of weakly-supervised multi-labels (the number of "1" in binary hash codes) is adaptively determined according to the specific data content. Further, to enhance the discriminative capability of binary labels, we model the intrinsic data structure by adaptively constructing the dynamic similarity graph. Finally, we extend UAFS-BH to multi-view setting as Multi-view Feature Selection with Binary Hashing (MVFS-BH) to handle the multi-view feature selection problem. An effective binary optimization method based on the Augmented Lagrangian Multiple (ALM) is derived to iteratively solve the formulated problem. Extensive experiments on widely tested benchmarks demonstrate the state-of-the-art performance of the proposed method on both single-view and multi-view feature selection tasks. For the purpose of reproducibility, we provide the source codes and testing datasets at https://github.com/shidan0122/UMFS.git..