Due to the storage and retrieval efficiency, hashing has been widely deployed to approximate nearest neighbor search for large-scale multimedia retrieval. Supervised hashing, which improves the quality of hash coding by exploiting the semantic similarity on data pairs, has received increasing attention recently. For most existing supervised hashing methods for image retrieval, an image is first represented as a vector of hand-crafted or machine-learned features, followed by another separate quantization step that generates binary codes. However, suboptimal hash coding may be produced, because the quantization error is not statistically minimized and the feature representation is not optimally compatible with the binary coding. In this paper, we propose a novel Deep Hashing Network (DHN) architecture for supervised hashing, in which we jointly learn good image representation tailored to hash coding and formally control the quantization error. The DHN model constitutes four key components: (1) a sub-network with multiple convolution-pooling layers to capture image representations; (2) a fully-connected hashing layer to generate compact binary hash codes; (3) a pairwise cross-entropy loss layer for similarity-preserving learning; and (4) a pairwise quantization loss for controlling hashing quality. Extensive experiments on standard image retrieval datasets show the proposed DHN model yields substantial boosts over latest state-of-the-art hashing methods.

Multiple kernel k-means (MKKM) clustering aims to optimally combine a group of pre-specified kernels to improve clustering performance. However, we observe that existing MKKM algorithms do not sufficiently consider the correlation among these kernels. This could result in selecting mutually redundant kernels and affect the diversity of information sources utilized for clustering, which finally hurts the clustering performance. To address this issue, this paper proposes an MKKM clustering with a novel, effective matrix-induced regularization to reduce such redundancy and enhance the diversity of the selected kernels. We theoretically justify this matrix-induced regularization by revealing its connection with the commonly used kernel alignment criterion. Furthermore, this justification shows that maximizing the kernel alignment for clustering can be viewed as a special case of our approach and indicates the extendability of the proposed matrix-induced regularization for designing better clustering algorithms. As experimentally demonstrated on five challenging MKL benchmark data sets, our algorithm significantly improves existing MKKM and consistently outperforms the state-of-the-art ones in the literature, verifying the effectiveness and advantages of incorporating the proposed matrix-induced regularization.

Parsing human into semantic parts is crucial to human-centric analysis. In this paper, we propose a human parsing pipeline that uses pose cues, i.e., estimates of human joint locations, to provide pose-guided segment proposals for semantic parts. These segment proposals are ranked using standard appearance cues, deep-learned semantic feature, and a novel pose feature called pose-context. Then these proposals are selected and assembled using an And-Or graph to output a parse of the person. The And-Or graph is able to deal with large human appearance variability due to pose, choice of clothes, etc. We evaluate our approach on the popular Penn-Fudan pedestrian parsing dataset, showing that it significantly outperforms the state-of-the-arts, and perform diagnostics to demonstrate the effectiveness of different stages of our pipeline.

Socio-economic maps contain important information regarding the population of a country. Computing these maps is critical given that policy makers often times make important decisions based upon such information. However, the compilation of socio-economic maps requires extensive resources and becomes highly expensive. On the other hand, the ubiquitous presence of cell phones, is generating large amounts of spatiotemporal data that can reveal human behavioral traits related to specific socio-economic characteristics. Traditional inference approaches have taken advantage of these datasets to infer regional socio-economic characteristics. In this paper, we propose a novel approach whereby topic models are used to infer socio-economic levels from large-scale spatio-temporal data. Instead of using a pre-determined set of features, we use latent Dirichlet Allocation (LDA) to extract latent recurring patterns of co-occurring behaviors across regions, which are then used in the prediction of socio-economic levels. We show that our approach improves state of the art prediction results by 9%.

Metric learning has become a critical tool in many machine learning tasks. This paper focuses on learning an optimal Mahalanobis distance matrix (parameterized by a positive semi-definite matrix W ) in the setting of supervised learning. Recently, particular research attention has been attracted by low-rank metric learning, which requires that matrix W is dominated by a few large singular values. In the era of high feature dimensions, low-rank metric learning effectively reduces the storage and computation overheads. However, existing low-rank metric learning algorithms usually adopt sophisticated regularization (such as LogDet divergence) for encouraging matrix low-rankness, which unfortunately incur iterative computations of matrix SVD. In this paper, we tackle low-rank metric learning by enforcing fixed-rank constraint on the matrix W. We harness the Riemannian manifold geometry of the collection of fixed-rank matrices and devise a novel second-order Riemannian retraction operator. The proposed operator is efficient and ensures that W always resides on the manifold. Comprehensive numerical experiments conducted on benchmarks clearly suggest that the proposed algorithm is substantially superior or on par with the state-of-the-art in terms of k -NN classification accuracy. Moreover, the proposed manifold retraction operator can be also naturally applied in generic rank-constrained machine learning algorithms.

The human visual system can spot an abnormal image, and reason about what makes it strange. This task has not received enough attention in computer vision. In this paper we study various types of atypicalities in images in a more comprehensive way than has been done before. We propose a new dataset of abnormal images showing a wide range of atypicalities. We design human subject experiments to discover a coarse taxonomy of the reasons for abnormality. Our experiments reveal three major categories of abnormality: object-centric, scene-centric, and contextual. Based on this taxonomy, we propose a comprehensive computational model that can predict all different types of abnormality in images and outperform prior arts in abnormality recognition.

We consider the problem of approximating order-constrained transitive distance (OCTD) and its clustering applications. Given any pairwise data, transitive distance (TD) is defined as the smallest possible "gap" on the set of paths connecting them. While such metric definition renders significant capability of addressing elongated clusters, it is sometimes also an over-simplified representation which loses necessary regularization on cluster structure and overfits to short links easily. As a result, conventional TD often suffers from degraded performance given clusters with "thick" structures. Our key intuition is that the maximum (path) order, which is the maximum number of nodes on a path, controls the level of flexibility. Reducing this order benefits the clustering performance by finding a trade-off between flexibility and regularization on cluster structure. Unlike TD, finding OCTD becomes an intractable problem even though the number of connecting paths is reduced. We therefore propose a fast approximation framework, using random samplings to generate multiple diversified TD matrices and a pooling to output the final approximated OCTD matrix. Comprehensive experiments on toy, image and speech datasets show the excellent performance of OCTD, surpassing TD with significant gains and giving state-of-the-art performance on several datasets.

Briggs et al. (2012b) proposed to represent audio Bioacoustic monitoring is a rapidly growing field, where the recordings of bird sound in the multi-instance multi-label goal is to learn about organisms such as birds and marine (MIML) framework (Zhou et al. 2012). In this formulation, mammals, by applying signal processing and machine learning an audio recording is transformed to a spectrogram, to audio recordings. In this paper, we consider the problem then automatically segmented into a collection of regions of class discovery from bird bioacoustics data. Given believed to be distinct utterances of bird sound. Each segment a large collection of audio recordings of birds (and other is then described by a feature vector that characterizes sounds in the environment), our goal is to automatically select its shape, texture, and time/frequency profiles. A recording a subset of recordings to be manually labeled by human is represented as a set of segment feature vectors (instances).

In many personalised recommendation problems, there are examples of items users prefer or like, but no examples of items they dislike. A state-of-the-art method for such implicit feedback, or one-class collaborative filtering (OC-CF), problems is SLIM, which makes recommendations based on a learned item-item similarity matrix. While SLIM has been shown to perform well on implicit feedback tasks, we argue that it is hindered by two limitations: first, it does not produce user-personalised predictions, which hampers recommendation performance; second, it involves solving a constrained optimisation problem, which impedes fast training. In this paper, we propose LRec, a variant of SLIM that overcomes these limitations without sacrificing any of SLIM's strengths.At its core, LRec employs linear logistic regression; despite this simplicity, LRec consistently and significantly outperforms all existing methods on a range of datasets. Our results thus illustrate that the OC-CF problem can be effectively tackled via linear classification models.

Binary code learning, a.k.a., hashing, has been recently popular due to its high efficiency in large-scale similarity search and recognition. It typically maps high-dimensional data points to binary codes, where data similarity can be efficiently computed via rapid Hamming distance. Most existing unsupervised hashing schemes pursue binary codes by reducing the quantization error from an original real-valued data space to a resulting Hamming space. On the other hand, most existing supervised hashing schemes constrain binary code learning to correlate with pairwise similarity labels. However, few methods consider ordinal relations in the binary code learning process, which serve as a very significant cue to learn the optimal binary codes for similarity search. In this paper, we propose a novel hashing scheme, dubbed Ordinal Embedding Hashing (OEH), which embeds given ordinal relations among data points to learn the ranking-preserving binary codes. The core idea is to construct a directed unweighted graph to capture the ordinal relations, and then train the hash functions using this ordinal graph to preserve the permutation relations in the Hamming space. To learn such hash functions effectively, we further relax the discrete constraints and design a stochastic gradient decent algorithm to obtain the optimal solution. Experimental results on two large-scale benchmark datasets demonstrate that the proposed OEH method can achieve superior performance over the state-of-the-arts approaches.At last, the evaluation on query by humming dataset demonstrates the OEH also has good performance for music retrieval by using user's humming or singing.