Although the light field has been recently recognized helpful in saliency detection, it is not comprehensively explored yet. In this work, we propose a new saliency detection model with light field data. The idea behind the proposed model originates from the following observations. (1) People can distinguish regions at different depth levels via adjusting the focus of eyes. Similarly, a light field image can generate a set of focal slices focusing at different depth levels, which suggests that a background can be weighted by selecting the corresponding slice. We show that background priors encoded by light field focusness have advantages in eliminating background distraction and enhancing the saliency by weighting the light field contrast. (2) Regions at closer depth ranges tend to be salient, while far in the distance mostly belong to the backgrounds. We show that foreground objects can be easily separated from similar or cluttered backgrounds by exploiting their light field depth. Extensive evaluations on the recently introduced Light Field Saliency Dataset (LFSD) [Li et al., 2014], including studies of different light field cues and comparisons with Li et al.'s method (the only reported light field saliency detection approach to our knowledge) and the 2D/3D state-of-the-art approaches extended with light field depth/focusness information, show that the investigated light field properties are complementary with each other and lead to improvements on 2D/3D models, and our approach produces superior results in comparison with the state-of-the-art.

In this paper, we investigate the problem of face clustering in real-world videos. In many cases, the distribution of the face data is unbalanced. In movies or TV series videos, the leading casts appear quite often and the others appear much less. However, many clustering algorithms cannot well handle such severe unbalance between the data distribution, resulting in that the large class is split apart, and the small class is merged into the large ones and thus missing. On the other hand, the data distribution proportion information may be known beforehand. For example, we can obtain such information by counting the spoken lines of the characters in the script text. Hence, we propose to make use of the proportion prior to regularize the clustering. A Hidden Conditional Random Field(HCRF) model is presented to incorporate the proportion prior. In experiments on a public data set from real-world videos, we observe improvements on clustering performance against state-of-the-art methods.

In this paper, we formulate the image classification problem in a multi-task learning framework. We propose a novel method to adaptively share information among tasks (classes). Different from imposing strong assumptions or discovering specific structures, the key insight in our method is to selectively extract and exploit the shared information among classes while capturing respective disparities simultaneously. It is achieved by estimating a composite of two sets of parameters with different regularization. Besides applying it for learning classifiers on pre-computed features, we also integrate the adaptive sharing with deep neural networks, whose discriminative power can be augmented by encoding class relationship. We further develop two strategies for solving the optimization problems in the two scenarios. Empirical results demonstrate that our method can significantly improve the classification performance by transferring knowledge appropriately.

In this paper, we propose using augmented hypotheses which consider objectness, foreground and compactness for salient object detection. Our algorithm consists of four basic steps. First, our method generates the objectness map via objectness hypotheses. Based on the objectness map, we estimate the foreground margin and compute the corresponding foreground map which prefers the foreground objects. From the objectness map and the foreground map, the compactness map is formed to favor the compact objects. We then derive a saliency measure that produces a pixelaccurate saliency map which uniformly covers the objects of interest and consistently separates foreand background. We finally evaluate the proposed framework on two challenging datasets, MSRA-1000 and iCoSeg. Our extensive experimental results Figure 1: From top to bottom: original images, the objectness show that our method outperforms state-ofthe-art hypotheses, results of our saliency computation, and ground approaches.

Recent advances in imaging and multimedia technologies have paved the way for automatic analysis of visual art. Despite notable attempts, extracting relevant patterns from paintings is still a challenging task. Different painters, born in different periods and places, have been influenced by different schools of arts. However, each individual artist also has a unique signature, which is hard to detect with algorithms and objective features. In this paper we propose a novel dictionary learning approach to automatically uncover the artistic style from paintings. Specifically, we present a multi-task learning algorithm to learn a style-specific dictionary representation. Intuitively, our approach, by automatically decoupling style-specific and artist-specific patterns, is expected to be more accurate for retrieval and recognition tasks than generic methods. To demonstrate the effectiveness of our approach, we introduce the DART dataset, containing more than 1.5K images of paintings representative of different styles. Our extensive experimental evaluation shows that our approach significantly outperforms state-of-the-art methods.

Part deformation has been a longstanding challenge for object parsing, of which the primary difficulty lies in modeling the highly diverse object structures. To this end, we propose a novel structure parsing model to capture deformable object structures. The proposed model consists of two de-formable layers: the top layer is an undirected graph that incorporates inter-part deformations to infer object structures; the base layer is consisted of various independent nodes to characterize local intra-part deformations. To learn this two-layer model, we design a layer-wise learning algorithm,which employs matching pursuit and belief propagation for a low computational complexity inference. Specifically, active basis sparse coding is leveraged to build the nodes at the base layer, while the edge weights are estimated by a structural support vector machine. Experimental results on two benchmark datasets (i.e., faces and horses) demonstrate that the proposed model yields superior parsing performance over state-of-the-art models.

In this paper, we propose a new local spatio-temporal descriptor for videos and we propose a new approach for action recognition in videos based on the introduced descriptor. The new descriptor is called the Video Covariance Matrix Logarithm (VCML). The VCML descriptor is based on a covariance matrix representation, and it models relationships between different low-level features, such as intensity and gradient. We apply the VCML descriptor to encode appearance information of local spatio-temporal video volumes, which are extracted by the Dense Trajectories. Then, we present an extensive evaluation of the proposed VCML descriptor with the Fisher vector encoding and the Support Vector Machines on four challenging action recognition datasets. We show that the VCML descriptor achieves better results than the state-of-the-art appearance descriptors. Moreover, we present that the VCML descriptor carries complementary information to the HOG descriptor and their fusion gives a significant improvement in action recognition accuracy. Finally, we show that the VCML descriptor improves action recognition accuracy in comparison to the state-of-the-art Dense Trajectories, and that the proposed approach achieves superior performance to the state-of-the-art methods.

This paper addresses the task of time separated aerial image registration. The ability to solve this problem accurately and reliably is important for a variety of subsequent image understanding applications. The principal challenge lies in the extent and nature of transient appearance variation that a land area can undergo, such as that caused by the change in illumination conditions, seasonal variations, or the occlusion by non-persistent objects (people, cars). Our work introduces several novelties: (i) unlike all previous work on aerial image registration, we approach the problem using a set-based paradigm; (ii) we show how local, pair-wise constraints can be used to enforce a globally good registration using a constraints graph structure; (iii) we show how a simple holistic representation derived from raw aerial images can be used as a basic building block of the constraints graph in a manner which achieves both high registration accuracy and speed. We demonstrate: (i) that the proposed method outperforms the state-of-the-art for pair-wise registration already, achieving greater accuracy and reliability, while at the same time reducing the computational cost of the task; and (ii) that the increase in the number of available images in a set consistently reduces the average registration error.

To enjoy more social network services, users nowadays are usually involved in multiple online social media sites at the same time. Across these social networks, users can be connected by both intra-network links (i.e., social links) and inter-network links (i.e., anchor links) simultaneously. In this paper, we want to predict the formation of social links among users in the target network as well as anchor links aligning the target network with other external social networks. The problem is formally defined as the “collective link identification” problem. To solve the collective link identification problem, a unified link prediction framework, CLF (Collective Link Fusion) is proposed in this paper, which consists of two phases: step (1) collective link prediction of anchor and social links, and step (2) propagation of predicted links across the partially aligned “probabilistic networks” with collective random walk. Extensive experiments conducted on two real-world partially aligned networks demonstrate that CLF can perform very well in predicting social and anchor links concurrently.

Representation learning has shown its effectiveness in many tasks such as image classification and text mining. Network representation learning aims at learning distributed vector representation for each vertex in a network, which is also increasingly recognized as an important aspect for network analysis. Most network representation learning methods investigate network structures for learning. In reality, network vertices contain rich information (such as text), which cannot be well applied with algorithmic frameworks of typical representation learning methods. By proving that DeepWalk, a state-of-the-art network representation method, is actually equivalent to matrix factorization (MF), we propose text-associated DeepWalk (TADW). TADW incorporates text features of vertices into network representation learning under the framework of matrix factorization. We evaluate our method and various baseline methods by applying them to the task of multi-class classification of vertices. The experimental results show that, our method outperforms other baselines on all three datasets, especially when networks are noisy and training ratio is small.