Collective Reconstructive Embeddings for Cross-Modal Hashing

Hu, Mengqiu; Yang, Yang; Shen, Fumin; Xie, Ning; Hong, Richang; Shen, Heng Tao

doi:10.1109/tip.2018.2890144

Cited by 143 publications

(63 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As mentioned previously, existing cross-modal hashing methods can be divided into unsupervised and supervised ones. For unsupervised methods, the intra-and inter-modality relations are exploited to generate hash codes without any supervised information [11,17,24]. [14] is a representative deep learning framework which can perform feature learning and hash-code learning simultaneously.…”

Section: Related Workmentioning

confidence: 99%

Supervised Hierarchical Deep Hashing for Cross-Modal Retrieval

Zhan

Luo

Wang

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Cross-modal hashing has attracted much attention in the large-scale multimedia search area. In many real applications, labels of samples have hierarchical structure which also contains much useful information for learning. However, most existing methods are originally designed for non-hierarchical labeled data and thus fail to exploit the rich information of the label hierarchy. In this paper, we propose an effective cross-modal hashing method, named Supervised Hierarchical Deep Cross-modal Hashing, SHDCH for short, to learn hash codes by explicitly delving into the hierarchical labels. Specifically, both the similarity at each layer of the label hierarchy and the relatedness across different layers are implanted into the hash-code learning. Besides, an iterative optimization algorithm is proposed to directly learn the discrete hash codes instead of relaxing the binary constraints. We conducted extensive experiments on two real-world datasets and the experimental results show the superior performance of SHDCH over several state-of-the-art methods. CCS CONCEPTS • Information systems → Multimedia and multimodal retrieval; • Computing methodologies → Visual content-based indexing and retrieval; Learning paradigms.

show abstract

Section: Related Workmentioning

confidence: 99%

Supervised Hierarchical Deep Hashing for Cross-Modal Retrieval

Zhan

Luo

Wang

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

show abstract

“…In a manner different from BRE that measures data similarity by Euclidean distance, the Angular Reconstructive Embedding (ARE) (Hu et al, 2018) method uses cosine similarity. Collective Reconstructive Embedding (CRE) (Hu et al, 2019), on the other hand, uses both cosine-based and Euclidean-based similarity simultaneously to address the crossmodel hashing problem. In 2015, Liong et al proposed Deep Hashing (DH) (Erin Liong et al, 2015) that first utilizes a multilayer neural network as the hash function to preserve nonlinear neighborhood relationships.…”

Section: Hashingmentioning

confidence: 99%

Deep supervised hashing using symmetric relative entropy

Zhang

Zhou

Bai

et al. 2019

Pattern Recognition Letters

View full text Add to dashboard Cite

This is a PDF file of an unedited manuscript that has been accepted for publication. As a service to our customers we are providing this early version of the manuscript. The manuscript will undergo copyediting, typesetting, and review of the resulting proof before it is published in its final form. Please note that during the production process errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain. Highlights • We propose a symmetric relative entropy based deep hashing method. • Our method can decrease the information loss during hashing embedding.

show abstract

“…e.g., using texts to search images. Consequently, cross-modal hashing [15,36,38] has gained more and more attention. Many cross-modal hashing methods have been proposed and achieved promising performance.…”

Section: Introductionmentioning

confidence: 99%

Label Embedding Online Hashing for Cross-Modal Retrieval

Wang

Luo

2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Supervised cross-modal hashing has gained a lot of attention recently. However, most existing methods learn binary codes or hash functions in a batch-based scheme, which is inefficient in an online scenario, i.e., data points come in a streaming fashion. Online hashing is a promising solution; however, there still exist several challenges, e.g., how to effectively exploit semantic information, how to discretely solve the binary optimization problem, how to efficiently update hash codes and hash functions. To address these issues, in this paper, we propose a novel supervised online cross-modal hashing method, i.e., Label EMbedding ONline hashing, LEMON for short. It builds a label embedding framework including label similarity preserving and label reconstructing, which may generate discriminative binary codes and reduce the computational complexity. Furthermore, it not only preserves the pairwise similarity of incoming data, but also establishes a connection between newly coming data and existing data by the inner product minimization on a block similarity matrix. In the light of this, it can exploit more similarity information and make the optimization less sensitive to incoming data, leading to effective binary codes. In addition, we design a discrete optimization algorithm to solve the binary optimization problem without relaxation. Therefore, the quantization error can be reduced. Moreover, its computational complexity is only relevant to the size of incoming data, making it very efficient and scalable to large-scale datasets. Extensive experimental results on three benchmark datasets demonstrate that LEMON outperforms some state-of-the-art offline and online cross-modal hashing methods in terms of accuracy and efficiency. CCS CONCEPTS • Computing methodologies → Learning paradigms; • Information systems → Multimedia and multimodal retrieval.

show abstract

Collective Reconstructive Embeddings for Cross-Modal Hashing

Cited by 143 publications

References 53 publications

Supervised Hierarchical Deep Hashing for Cross-Modal Retrieval

Supervised Hierarchical Deep Hashing for Cross-Modal Retrieval

Deep supervised hashing using symmetric relative entropy

Label Embedding Online Hashing for Cross-Modal Retrieval

Contact Info

Product

Resources

About