Quan-Sen Sun

Multi-view Latent Hashing for Efficient Multimedia Search

Hashing techniques have attracted broad research interests in recent multimedia studies. However, most of existing hashing methods focus on learning binary codes from data with only one single view, and thus cannot fully utilize the rich information from multiple views of data. In this paper, we propose a novel unsupervised hashing approach, dubbed multi-view latent hashing (MVLH), to effectively incorporate multi-view data into hash code learning. Specifically, the binary codes are learned by the latent factors shared by multiple views from an unified kernel feature space, where the weights of different views are adaptively learned according to the reconstruction error with each view. We then propose to solve the associate optimization problem with an efficient alternating algorithm. To obtain high-quality binary codes, we provide a novel scheme to directly learn the codes without resorting to continuous relaxations, where each bit is efficiently computed in a closed form. We evaluate the proposed method on several large-scale datasets and the results demonstrate the superiority of our method over several other state-of-the-art methods.

Semi-Paired Discrete Hashing: Learning Latent Hash Codes for Semi-Paired Cross-View Retrieval

Due to the significant reduction in computational cost and storage, hashing techniques have gained increasing interests in facilitating large-scale cross-view retrieval tasks. Most cross-view hashing methods are developed by assuming that data from different views are well paired, e.g., text-image pairs. In real-world applications, however, this fully-paired multiview setting may not be practical. The more practical yet challenging semi-paired cross-view retrieval problem, where pairwise correspondences are only partially provided, has less been studied. In this paper, we propose an unsupervised hashing method for semi-paired cross-view retrieval, dubbed semi-paired discrete hashing (SPDH). In specific, SPDH explores the underlying structure of the constructed common latent subspace, where both paired and unpaired samples are well aligned. To effectively preserve the similarities of semi-paired data in the latent subspace, we construct the cross-view similarity graph with the help of anchor data pairs. SPDH jointly learns the latent features and hash codes with a factorization-based coding scheme. For the formulated objective function, we devise an efficient alternating optimization algorithm, where the key binary code learning problem is solved in a bit-by-bit manner with each bit generated with a closed-form solution. The proposed method is extensively evaluated on four benchmark datasets with both fully-paired and semi-paired settings and the results demonstrate the superiority of SPDH over several other state-of-the-art methods in term of both accuracy and scalability.

Laplacian multiset canonical correlations for multiview feature extraction and image recognition

Multiset canonical correlation analysis (MCCA) aims at revealing the linear correlations among multiple sets of high-dimensional data. Therefore, it is only a linear multiview dimensionality reduction technique and such a linear model is insufficient to discover the nonlinear correlation information hidden in multiview data. In this paper, we incorporate the local structure information into MCCA and propose a novel algorithm for multiview dimensionality reduction, called Laplacian multiset canonical correlations (LapMCCs), which simultaneously considers local within-view and local between-view correlations by using nearest neighbor graphs. This makes LapMCC capable of discovering the nonlinear correlation information among multiview data by combining many locally linear problems together. Moreover, we also develop an orthogonal version of LapMCC to preserve the metric structure. The proposed LapMCC method is applied to face and object image recognition. The experimental results on AR, Yale-B, AT&T, and ETH-80 databases demonstrate the superior performance of LapMCC compared to existing multiview dimensionality reduction methods.

Robust Cross-view Hashing for Multimedia Retrieval

Hashing techniques have been widely applied to large-scale cross-view retrieval tasks due to the significant advantage of binary codes in computation and storage efficiency. However, most existing cross-view hashing methods learn binary codes with continuous relaxations, which cause large quantization loss across views. To address this problem, in this letter, we propose a novel cross-view hashing method, where a common Hamming space is learned such that binary codes from different views are consistent and comparable. The quantization loss across views is explicitly reduced by two carefully designed regression terms from original spaces to the Hamming space. In our method, the l2,1-norm regularization is further exploited for discriminative feature selection. To obtain high-quality binary codes, we propose to jointly learn the codes and hash functions, for which an efficient iterative algorithm is presented. We evaluate the proposed method, dubbed Robust Cross-view Hashing (RCH), on two benchmark datasets and the results demonstrate the superiority of RCH over many other state-of-the-art methods in terms of retrieval performance and cross-view consistency.

Multiview Correlation Feature Learning with Multiple Kernels

Recent researches have shown the necessity to consider multiple kernels rather than a single fixed kernel in real-world applications. The learning performance can be significantly improved if multiple kernel functions or kernel matrices are considered. Motivated by the recent progress, in this paper we present a multiple kernel multiview correlation feature learning method for multiview dimensionality reduction. In our proposed method, the input data of each view are mapped into multiple higher dimensional feature spaces by implicitly nonlinear mappings. Three experiments on face and handwritten digit recognition have demonstrated the effectiveness of the proposed method.

Multilabel Prediction via Cross-View Search

Embedding methods have shown promising performance in multilabel prediction, as they are able to discover the label dependence. However, most methods ignore the correlations between the input and output, such that their learned embeddings are not well aligned, which leads to degradation in prediction performance. This paper presents a formulation for multilabel learning, from the perspective of cross-view learning, that explores the correlations between the input and the output. The proposed method, called Co-Embedding (CoE), jointly learns a semantic common subspace and view-specific mappings within one framework. The semantic similarity structure among the embeddings is further preserved, ensuring that close embeddings share similar labels. Additionally, CoE conducts multilabel prediction through the cross-view <inline-formula> <tex-math notation=LaTeX>

A Content-Adaptively Sparse Reconstruction Method for Abnormal Events Detection With Low-Rank Property

k

Discrete Network Embedding

</tex-math></inline-formula> nearest neighborhood (<inline-formula> <tex-math notation=LaTeX>

Compressed K - Means for large-scale clustering

k

Compact Multi-label Learning

</tex-math></inline-formula>NN) search among the learned embeddings, which significantly reduces computational costs compared with conventional decoding schemes. A hashing-based model, i.e., Co-Hashing (CoH), is further proposed. CoH is based on CoE, and imposes the binary constraint on continuous latent embeddings. CoH aims to generate compact binary representations to improve the prediction efficiency by benefiting from the efficient <inline-formula> <tex-math notation=LaTeX>