Hetero-Manifold Regularisation for Cross-Modal Hashing

Zheng, Feng; Tang, Yi; Shao, Ling

doi:10.1109/tpami.2016.2645565

Cited by 67 publications

(23 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Bai et al [9] proposed to boost the performance by manifold-based affinity learning on the training set, which has a negative impact on the time and space complexity of algorithm, because of the need for training a model. In [24], the pairwise similarity is measured by three order random walks on the hetero-manifold: from the probe to its neighbor, from the probe's neighbor to the gallery's neighbor, and from the gallery's neighbor to the gallery. Essentially, it is similar to the methods [12], [4], [13] in which the pairwise similarity is computed by the set-to-set comparison.…”

Section: A Post-processing Person Re-id Methodsmentioning

confidence: 99%

Progressive Bilateral-Context Driven Model for Post-Processing Person Re-Identification

Cao

Chen

Dou

et al. 2021

IEEE Trans. Multimedia

View full text Add to dashboard Cite

Most existing person re-identification methods compute pairwise similarity by extracting robust visual features and learning the discriminative metric. Owing to visual ambiguities, these content-based methods that determine the pairwise relationship only based on the similarity between them, inevitably produce a suboptimal ranking list. Instead, the pairwise similarity can be estimated more accurately along the geodesic path of the underlying data manifold by exploring the rich contextual information of the sample. In this paper, we propose a lightweight post-processing person re-identification method in which the pairwise measure is determined by the relationship between the sample and the counterpart's context in an unsupervised way. We translate the point-to-point comparison into the bilateral point-to-set comparison. The sample's context is composed of its neighbor samples with two different definition ways: the first order context and the second order context, which are used to compute the pairwise similarity in sequence, resulting in a progressive post-processing model. The experiments on four large-scale person re-identification benchmark datasets indicate that (1) the proposed method can consistently achieve higher accuracies by serving as a post-processing procedure after the content-based person re-identification methods, showing its stateof-the-art results, (2) the proposed lightweight method only needs about 6 milliseconds for optimizing the ranking results of one sample, showing its high-efficiency.

show abstract

Section: A Post-processing Person Re-id Methodsmentioning

confidence: 99%

Progressive Bilateral-Context Driven Model for Post-Processing Person Re-Identification

Cao

Chen

Dou

et al. 2021

IEEE Trans. Multimedia

View full text Add to dashboard Cite

show abstract

“…RFDH [37] utilizes a discrete matrix decomposition technique, coupled with an 2,1 -norm, to minimize the quantization errors among multimodal data and then projects data into effective binary codes with two hash functions. Zheng et al [38] measured the similarities between each pair of modalities by three order random walks and then transformed into the problem of regularized support vector learning for the sake of efficiency.…”

Section: Related Workmentioning

confidence: 99%

Adaptive Hashing With Sparse Matrix Factorization

Liu

Zhang

2020

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

Hashing offers a desirable and effective solution for efficiently retrieving the nearest neighbors from large-scale data because of its low storage and computation costs. One of the most appealing techniques for hashing learning is matrix factorization. However, most hashing methods focus only on building the mapping relationships between the Euclidean and Hamming spaces and, unfortunately, underestimate the naturally sparse structures of the data. In addition, parameter tuning is always a challenging and head-scratching problem for sparse hashing learning. To address these problems, in this article, we propose a novel hashing method termed adaptively sparse matrix factorization hashing (SMFH), which exploits sparse matrix factorization to explore the parsimonious structures of the data. Moreover, SMFH adopts an orthogonal transformation to minimize the quantization loss while deriving the binary codes. The most distinguished property of SMFH is that it is adaptive and parameter-free, that is, SMFH can automatically generate sparse representations and does not require human involvement to tune the regularization parameters for the sparse models. Empirical studies on four publicly available benchmark data sets show that the proposed method can achieve promising performance and is competitive with a variety of state-of-the-art hashing methods.

show abstract

“…matching across resolutions, modalities, or domains. [28][29][30]). Given associated HF image feature sets, X h and Y h , corresponding to both paired and unpaired training image data sets, X P , X U , Y P and Y U , CMIM represents an ensemble of paired and unpaired cross-modality matching sub-problems.…”

Section: Weak Coupling and Geometry Co-regularizationmentioning

confidence: 99%

Cross-Modality Image Synthesis via Weakly Coupled and Geometry Co-Regularized Joint Dictionary Learning

Huang

Shao

Frangi

2018

IEEE Trans. Med. Imaging

Self Cite

View full text Add to dashboard Cite

Multi-modality medical imaging is increasingly used for comprehensive assessment of complex diseases in either diagnostic examinations or as part of medical research trials. Different imaging modalities provide complementary information about living tissues. However, multi-modal examinations are not always possible due to adversary factors, such as patient discomfort, increased cost, prolonged scanning time, and scanner unavailability. In additionally, in large imaging studies, incomplete records are not uncommon owing to image artifacts, data corruption or data loss, which compromise the potential of multi-modal acquisitions. In this paper, we propose a weakly coupled and geometry co-regularized joint dictionary learning method to address the problem of cross-modality synthesis while considering the fact that collecting the large amounts of training data is often impractical. Our learning stage requires only a few registered multi-modality image pairs as training data. To employ both paired images and a large set of unpaired data, a cross-modality image matching criterion is proposed. Then, we propose a unified model by integrating such a criterion into the joint dictionary learning and the observed common feature space for associating cross-modality data for the purpose of synthesis. Furthermore, two regularization terms are added to construct robust sparse representations. Our experimental results demonstrate superior performance of the proposed model over state-of-the-art methods.

show abstract

Hetero-Manifold Regularisation for Cross-Modal Hashing

Cited by 67 publications

References 50 publications

Progressive Bilateral-Context Driven Model for Post-Processing Person Re-Identification

Progressive Bilateral-Context Driven Model for Post-Processing Person Re-Identification

Adaptive Hashing With Sparse Matrix Factorization

Cross-Modality Image Synthesis via Weakly Coupled and Geometry Co-Regularized Joint Dictionary Learning

Contact Info

Product

Resources

About