MS<mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" altimg="si1.svg"><mml:msup><mml:mrow/><mml:mn>2</mml:mn></mml:msup></mml:math>GAH: Multi-label semantic supervised graph attention hashing for robust cross-modal retrieval

Duan, Youxiang; Chen, Ning; Zhang, Peiying; Kumar, Neeraj; Chang, Lunjie

doi:10.1016/j.patcog.2022.108676

Cited by 34 publications

(7 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In DL algorithms, artificially constructed neural networks are mainly used to solve high-dimensional decision-making problems [18]. The main idea of RL is to use an agent to learn a decision-making policy in the process of interacting with the environment, to obtain the optimal reward [19].…”

Section: Work Motivationsmentioning

confidence: 99%

Multi-Target-Aware Energy Orchestration Modeling for Grid 2.0: A Network Virtualization Approach

et al. 2023

Self Cite

View full text Add to dashboard Cite

Smart Grid -Grid 2.0, is a promising grid scenario due to its low cost, high reliability, and high security. However, the high-intensity complex task interaction and the differentiated quality of service (QoS) requirements pose challenges to the energy orchestration of the dynamic and time-varying smart grid. In addition, Network Virtualization (NV) technology is widely utilized to decouple physical network resources. In this work, based on Virtual Network Embedding (VNE), we propose an energy orchestration strategy to better support the operation and maintenance of Grid 2.0. Specifically, a series of constraint indicators for energy orchestration is first formulated. Second, based on the advantages of deep reinforcement learning (DRL), a five-layer architecture energy orchestration model is proposed. It frequently extracts the grid energy matrix as the state input, adopts two-stage actions to reasonably orchestrate the grid energy, and combines the reward mechanism of DRL to effectively interact with the environment. Finally, we conduct experiments in a simulation environment and demonstrate the advantages of the proposed strategy through analysis and comparison.

show abstract

Section: Work Motivationsmentioning

confidence: 99%

Multi-Target-Aware Energy Orchestration Modeling for Grid 2.0: A Network Virtualization Approach

et al. 2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…The basic idea of cross-modal hash retrieval [ 4 , 5 ] is to use the sample pair information of different modalities, learn the hash transform of different modalities and map the data of different modalities to a Hamming binary space [ 6 ] while keeping the similarity of the data in the process of mapping. (Data with more similar original semantics are projected into the Hamming common space, and the distance between their hash codes is closer.)…”

Section: Introductionmentioning

confidence: 99%

CLIP-Based Adaptive Graph Attention Network for Large-Scale Unsupervised Multi-Modal Hashing Retrieval

et al. 2023

Sensors

View full text Add to dashboard Cite

With the proliferation of multi-modal data generated by various sensors, unsupervised multi-modal hashing retrieval has been extensively studied due to its advantages in storage, retrieval efficiency, and label independence. However, there are still two obstacles to existing unsupervised methods: (1) As existing methods cannot fully capture the complementary and co-occurrence information of multi-modal data, existing methods suffer from inaccurate similarity measures. (2) Existing methods suffer from unbalanced multi-modal learning and data semantic structure being corrupted in the process of hash codes binarization. To address these obstacles, we devise an effective CLIP-based Adaptive Graph Attention Network (CAGAN) for large-scale unsupervised multi-modal hashing retrieval. Firstly, we use the multi-modal model CLIP to extract fine-grained semantic features, mine similar information from different perspectives of multi-modal data and perform similarity fusion and enhancement. In addition, this paper proposes an adaptive graph attention network to assist the learning of hash codes, which uses an attention mechanism to learn adaptive graph similarity across modalities. It further aggregates the intrinsic neighborhood information of neighboring data nodes through a graph convolutional network to generate more discriminative hash codes. Finally, this paper employs an iterative approximate optimization strategy to mitigate the information loss in the binarization process. Extensive experiments on three benchmark datasets demonstrate that the proposed method significantly outperforms several representative hashing methods in unsupervised multi-modal retrieval tasks.

show abstract

“…Blockchain technology has gained widespread acceptance as a security solution as it ensures security, efficiency, and reduces fraud in CNNs [ 26 , 27 , 28 ]. Blockchain technology can prevent the manipulation of object labels by incorporating critical features such as security, authenticity, data privacy, and de-tracking [ 29 ]. To prevent manipulation within CNN architectures, the input parameters of each layer should be verified.…”

Section: Introductionmentioning

confidence: 99%

Malicious Vehicle Detection Using Layer-Based Paradigm and the Internet of Things

Razaque,

Bektemyssova,

Yoo

et al. 2023

Sensors

View full text Add to dashboard Cite

Deep learning algorithms have a wide range of applications, including cancer diagnosis, face and speech recognition, object recognition, etc. It is critical to protect these models since any changes to them can result in serious losses in a variety of ways. This article proposes the consortium blockchain-enabled conventional neural network (CBCNN), a four-layered paradigm for detecting malicious vehicles. Layer-1 is a convolutional neural network-enabled Internet-of-Things (IoT) model for the vehicle; Layer-2 is a spatial pyramid polling layer for the vehicle; Layer-3 is a fully connected layer for the vehicle; and Layer-4 is a consortium blockchain for the vehicle. The first three layers accurately identify the vehicles, while the final layer prevents any malicious attempts. The primary goal of the four-layered paradigm is to successfully identify malicious vehicles and mitigate the potential risks they pose using multi-label classification. Furthermore, the proposed CBCNN approach is employed to ensure tamper-proof protection against a parameter manipulation attack. The consortium blockchain employs a proof-of-luck mechanism, allowing vehicles to save energy while delivering accurate information about the vehicle’s nature to the “vehicle management system.” C++ coding is employed to implement the approach, and the ns-3.34 platform is used for simulation. The ns3-ai module is specifically utilized to detect anomalies in the Internet of Vehicles (IoVs). Finally, a comparative analysis is conducted between the proposed CBCNN approach and state-of-the-art methods. The results confirm that the proposed CBCNN approach outperforms competing methods in terms of malicious label detection, average accuracy, loss ratio, and cost reduction.

show abstract

MS2GAH: Multi-label semantic supervised graph attention hashing for robust cross-modal retrieval

Cited by 34 publications

References 17 publications

Multi-Target-Aware Energy Orchestration Modeling for Grid 2.0: A Network Virtualization Approach

Multi-Target-Aware Energy Orchestration Modeling for Grid 2.0: A Network Virtualization Approach

CLIP-Based Adaptive Graph Attention Network for Large-Scale Unsupervised Multi-Modal Hashing Retrieval

Malicious Vehicle Detection Using Layer-Based Paradigm and the Internet of Things

Contact Info

Product

Resources

About