Sheng-hua Zhong

Deep residual learning for image steganalysis

Image steganalysis is to discriminate innocent images and those suspected images with hidden messages. This task is very challenging for modern adaptive steganography, since modifications due to message hiding are extremely small. Recent studies show that Convolutional Neural Networks (CNN) have demonstrated superior performances than traditional steganalytic methods. Following this idea, we propose a novel CNN model for image steganalysis based on residual learning. The proposed Deep Residual learning based Network (DRN) shows two attractive properties than existing CNN based methods. First, the model usually contains a large number of network layers, which proves to be effective to capture the complex statistics of digital images. Second, the residual learning in DRN preserves the stego signal coming from secret messages, which is extremely beneficial for the discrimination of cover images and stego images. Comprehensive experiments on standard dataset show that the DRN model can detect the state of arts steganographic algorithms at a high accuracy. It also outperforms the classical rich model method and several recently proposed CNN based methods.

A solution of dynamic VMs placement problem for energy consumption optimization based on evolutionary game theory

The computational model of energy consumption is built to serve as an evaluation function.An algorithm based on evolutionary game theory is proposed to solve the problem of dynamic VMs placement.It is analyzed that the algorithm can theoretically reach the optimal solution of the dynamic VMs placement problem.The algorithm can take the initial mapping into account and generate an executable list of VMs live migrations from the initial state to the target state. Power saving of data centers has become an urgent problem in recent years. For a virtualized data center, optimizing the placement of virtual machines (VMs) dynamically is one of the most effective methods for power savings. Based on a deep study on VMs placement, a solution is proposed and described in this paper to solve the problem of dynamic placement of VMs toward optimization of their energy consumptions. A computational model of energy consumption is proposed and built. A novel algorithm based on evolutionary game theory is also presented, which successfully addresses the challenges faced by dynamic placement of VMs. It is proved that the proposed algorithm can reach the optimal solutions theoretically. Experimental results also demonstrate that, by adjusting VMs placement dynamically, the energy consumption can be reduced correspondingly. In comparison with the existing state of the arts, our proposed method outperforms other five algorithms tested and achieves savings of 30-40% on energy consumption.

Query-oriented unsupervised multi-document summarization via deep learning model

First attempt of deep learning for query-oriented multi-document summarization.Novel algorithm pushes out important concepts layer by layer effectively.Confirm excellent extraction ability under unsupervised learning framework. Capturing the compositional process from words to documents is a key challenge in natural language processing and information retrieval. Extractive style query-oriented multi-document summarization generates a summary by extracting a proper set of sentences from multiple documents based on pre-given query. This paper proposes a novel document summarization framework based on deep learning model, which has been shown outstanding extraction ability in many real-world applications. The framework consists of three parts: concepts extraction, summary generation, and reconstruction validation. A new query-oriented extraction technique is proposed to extract information distributed in multiple documents. Then, the whole deep architecture is fine-tuned by minimizing the information loss in reconstruction validation. According to the concepts extracted from deep architecture layer by layer, dynamic programming is used to seek most informative set of sentences for the summary. Experiment on three benchmark datasets (DUC 2005, 2006, and 2007) assess and confirm the effectiveness of the proposed framework and algorithms. Experiment results show that the proposed method outperforms state-of-the-art extractive summarization approaches. Moreover, we also provide the statistical analysis of query words based on Amazons Mechanical Turk (MTurk) crowdsourcing platform. There exists underlying relationships from topic words to the content which can contribute to summarization task.

Semi-supervised manifold ordinal regression for image ranking

In this paper, we present a novel algorithm called manifold ordinal regression (MOR) for image ranking. By modeling the manifold information in the objective function, MOR is capable of uncovering the intrinsically nonlinear structure held by the image data sets. By optimizing the ranking information of the training data sets, the proposed algorithm provides faithful rating to the new coming images. To offer more general solution for the real-word tasks, we further provide the semi-supervised manifold ordinal regression (SS-MOR). Experiments on various data sets validate the effectiveness of the proposed algorithms.

Object proposal on RGB-D images via elastic edge boxes

As a fundamental preprocessing of various multimedia applications, object proposal aims to detect the candidate windows possibly containing arbitrary objects in images with two typical strategies, window scoring and grouping. In this paper, we first analyze the feasibility of improving object proposal performance by integrating window scoring and grouping strategies. Then, we propose a novel object proposal method for RGB-D images, named elastic edge boxes. The initial bounding boxes of candidate object regions are efficiently generated by edge boxes, and further adjusted by grouping the super-pixels within elastic range to obtain more accurate candidate windows. To validate the proposed method, we construct the largest RGB-D image data set NJU1800 for object proposal with balanced object number distribution. The experimental results show that our method can effectively and efficiently generate the candidate windows of object regions and it outperforms the state-of-the-art methods considering both accuracy and efficiency.

A novel clustering method for static video summarization

Static video summarization is recognized as an effective way for users to quickly browse and comprehend large numbers of videos. In this paper, we formulate static video summarization as a clustering problem. Inspired by the idea from high density peaks search clustering algorithm, we propose an effective clustering algorithm by integrating important properties of video to gather similar frames into clusters. Finally, all clusters’ center will be collected as static video summarization. Compared with existing clustering-based video summarization approaches, our work can detect frames which are highly relevant and generate representative clusters automatically. We evaluate our proposed work by comparing it with several state-of-the-art clustering-based video summarization methods and some classical clustering algorithms. The experimental results evidence that our proposed method has better performance and efficiency.

Visual orientation inhomogeneity based scale-invariant feature transform

Provide the evidence of existence of the least important visual orientation.Novel algorithm with high efficiency is proposed to detect and describe local feature.Better performance for detection and matching, comparable performance for recognition. Scale-invariant feature transform (SIFT) is an algorithm to detect and describe local features in images. In the last fifteen years, SIFT plays a very important role in multimedia content analysis, such as image classification and retrieval, because of its attractive character on invariance. This paper intends to explore a new path for SIFT research by making use of the findings from neuroscience. We propose a more efficient and compact scale-invariant feature detector and descriptor by simulating visual orientation inhomogeneity in human system. We validate that visual orientation inhomogeneity SIFT (V-SIFT) can achieve better or at least comparable performance with less computation resource and time cost in various computer vision tasks under real world conditions, such as image matching and object recognition. This work also illuminates a wider range of opportunities for integrating the inhomogeneity of visual orientation with other local position-dependent detectors and descriptors.

A semantic no-reference image sharpness metric based on top-down and bottom-up saliency map modeling

This work presents a semantic level no-reference image sharpness/blurriness metric under the guidance of top-down & bottom-up saliency map, which is learned based on eye-tracking data by SVM. Unlike existing metrics focused on measuring the blurriness in vision level, our metric more concerns about the image content and humans intention. We integrate visual features, center priority, and semantic meaning from tag information to learn a top-down & bottom-up saliency model based on the eye-tracking data. Empirical validations on standard dataset demonstrate the effectiveness of the proposed model and metric.

Perception-oriented video saliency detection via spatio-temporal attention analysis

Human visual system actively seeks salient regions and movements in video sequences to reduce the search effort. Computational visual saliency detection model provides important information for semantic understanding in many real world applications. In this paper, we propose a novel perception-oriented video saliency detection model to detect the attended regions for both interesting objects and dominant motions in video sequences. Based on the visual orientation inhomogeneity of human perception, a novel spatial saliency detection technique called visual orientation inhomogeneous saliency model is proposed. In temporal saliency detection, a novel optical flow model is created based on the dynamic consistency of motion. We fused the spatial and the temporal saliency maps together to build the spatio-temporal attention analysis model toward a uniform framework. The proposed model is evaluated on three typical video datasets with six visual saliency detection algorithms and achieves remarkable performance. Empirical validations demonstrate the salient regions detected by the proposed model highlight the dominant and interesting objects effectively and efficiently. More importantly, the saliency regions detected by the proposed model are consistent with human subjective eye tracking data.

Face recognition from a single registered image for conference socializing

A novel face recognition framework is proposed.The framework is robust to large pose variations between training and test faces.The framework is applicable to conference socialization scenarios.Experiments on FERET, G20, and Oscars tested the effectiveness of the framework. Scientific conferences are primary venues for connecting with and forming relationships with fellow researchers and scientists. Thus, over the course of a conference participants often take advantage of the many opportunities to network. In this setting, it is desirable to quickly recognize the identity of the persons we see and wish to meet. In particular, it could be embarrassing to not recognize a prominent researcher. In this paper, we investigate a novel face recognition framework that is applicable to conference socialization scenarios. In the proposed framework, only frontal images are used as training images; and face recognition is possible from an arbitrary view of a subject. Our system prototype assumes that the conference participants have uploaded a frontal photo during the registration process. At the conference, the identity of a person can be recognized from a picture, taken from an arbitrary angle with a standard mobile phone. Our experimental results indicate that the proposed framework is robust to possible large pose variations between the non-frontal image captured impromptu and the training image of the same person. Experiments based upon standard face dataset and real conference socializing datasets are conducted to test the effectiveness of the proposed techniques.