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

Wang, Lianzhong; Zheng, Zhe; Chen, Ning; Chi, Yingying; Liu, Yong; Zhu, Hailong; Zhang, Peiying; Kumar, Neeraj

doi:10.1109/access.2023.3251698

Cited by 6 publications

(1 citation statement)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The unsupervised methods preserve the similarity between heterogeneous data through the co-occurrence information of different modal data without the supervised information such as semantic labels, then project the data into the joint embedding space [31]. To explore the correlation of multimodal data from different media, Inter-Media Hashing (IMH) [32] obtains a more effective hash-code by calculating the similarity between the modal and within the modal in the public Hamming space.…”

Section: ) Unsupervisedmentioning

confidence: 99%

Transformer-Based Discriminative and Strong Representation Deep Hashing for Cross-Modal Retrieval

Zhou,

Han,

Chen

et al. 2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

Cross-modal hashing retrieval has attracted extensive attention due to its low storage requirements as well as high retrieval efficiency. In particular, how to more fully exploit the correlation of different modality data and generate a more distinguished representation is the key to improving the performance of this method. Moreover, Transformer-based models have been widely used in various fields, including natural language processing, due to their powerful contextual information processing capabilities. Based on these motivations, we propose a Transformer-based Distinguishing Strong Representation Deep Hashing (TDSRDH). For text modality, since the sequential relations between words imply semantic relations that are not independent relations, we thoughtfully encode them using a transformer-based encoder to obtain a strong representation. In addition, we propose a triple-supervised loss based on the commonly used pairwise loss and quantization loss. The latter two ensure the learned features and hash-codes can preserve the similarity of the original data during the learning process. The former ensures that the distance between similar instances is closer and the distance between dissimilar instances is farther. So that TDSRDH can generate more discriminative representations while preserving the similarity between modalities. Finally, experiments on the three datasets MIRFLICKR-25K, IAPR TC-12, and NUS-WIDE demonstrated the superiority of TDSRDH over the other baselines. Moreover, the effectiveness of the proposed idea was demonstrated by ablation experiments.

show abstract

Section: ) Unsupervisedmentioning

confidence: 99%