Search

Visual question answering (VQA) has gained increasing attention in both natural language processing and computer vision. The attention mechanism plays a crucial role in relating the question to meaningful image regions for answer inference. However, most existing VQA methods: 1) learn the attention distribution either from free-form regions or detection boxes in the image, which is intractable in answering questions about the foreground object and background form, respectively and 2) neglect the prior knowledge of human attention and learn the attention distribution with an unguided strategy. To fully exploit the advantages of attention, the learned attention distribution should focus more on the question-related image regions, such as human attention for both the questions, about the foreground object and background form. To achieve this, this article proposes a novel VQA model, called adversarial learning of supervised attentions (ALSAs). Specifically, two supervised attention modules: 1) free form-based and 2) detection-based, are designed to exploit the prior knowledge for attention distribution learning. To effectively learn the correlations between the question and image from different views, that is, free-form regions and detection boxes, an adversarial learning mechanism is implemented as an interplay between two supervised attention modules. The adversarial learning reinforces the two attention modules mutually to make the learned multiview features more effective for answer inference. The experiments performed on three commonly used VQA datasets confirm the favorable performance of ALSA.

Background: Multi-objective optimization (MOO) involves optimization problems with multiple objectives. Generally, theose objectives is used to estimate very different aspects of the solutions, and these aspects are often in conflict with each other. MOO first gets a Pareto set, and then looks for both commonality and systematic variations across the set. For the large-scale data sets, heuristic search algorithms such as EA combined with MOO techniques are ideal. Newly DNA microarray technology may study the transcriptional response of a complete genome to different experimental conditions and yield a lot of large-scale datasets. Biclustering technique can simultaneously cluster rows and columns of a dataset, and hlep to extract more accurate information from those datasets. Biclustering need optimize several conflicting objectives, and can be solved with MOO methods. As a heuristics-based optimization approach, the particle swarm optimization (PSO) simulate the movements of a bird flock finding food. The shuffled frog-leaping algorithm (SFL) is a population-based cooperative search metaphor combining the benefits of the local search of PSO and the global shuffled of information of the complex evolution technique. SFL is used to solve the optimization problems of the large-scale datasets., Results: This paper integrates dynamic population strategy and shuffled frog-leaping algorithm into biclustering of microarray data, and proposes a novel multi-objective dynamic population shuffled frog-leaping biclustering (MODPSFLB) algorithm to mine maximum bicluesters from microarray data. Experimental results show that the proposed MODPSFLB algorithm can effectively find significant biological structures in terms of related biological processes, components and molecular functions., Conclusions: The proposed MODPSFLB algorithm has good diversity and fast convergence of Pareto solutions and will become a powerful systematic functional analysis in genome research.

Background: In the biomedical domain, there are immense data and tremendous increase of genomics and biomedical relevant publications. The wealth of information has led to an increasing amount of interest in and need for applying information retrieval techniques to access the scientific literature in genomics and related biomedical disciplines. In many cases, the desired information of a query asked by biologists is a list of a certain type of entities covering different aspects that are related to the question, such as cells, genes, diseases, proteins, mutations, etc. Hence, it is important of a biomedical IR system to be able to provide relevant and diverse answers to fulfill biologists' information needs. However traditional IR model only concerns with the relevance between retrieved documents and user query, but does not take redundancy between retrieved documents into account. This will lead to high redundancy and low diversity in the retrieval ranked lists., Results: In this paper, we propose an approach which employs a topic generative model called Latent Dirichlet Allocation (LDA) to promoting ranking diversity for biomedical information retrieval. Different from other approaches or models which consider aspects on word level, our approach assumes that aspects should be identified by the topics of retrieved documents. We present LDA model to discover topic distribution of retrieval passages and word distribution of each topic dimension, and then re-rank retrieval results with topic distribution similarity between passages based on N-size slide window. We perform our approach on TREC 2007 Genomics collection and two distinctive IR baseline runs, which can achieve 8% improvement over the highest Aspect MAP reported in TREC 2007 Genomics track., Conclusions: The proposed method is the first study of adopting topic model to genomics information retrieval, and demonstrates its effectiveness in promoting ranking diversity as well as in improving relevance of ranked lists of genomics search. Moreover, we proposes a distance measure to quantify how much a passage can increase topical diversity by considering both topical importance and topical coefficient by LDA, and the distance measure is a modified Euclidean distance.

In this paper, we present a context-sensitive approach to re-ranking retrieved documents for further improving the effectiveness of high-performance biomedical literature retrieval systems. For each topic, a two-dimensional positive context is learnt from the top N retrieved documents and a group of negative contexts are learnt from the last N' documents in initial retrieval ranked list. The contextual space contains lexical context and conceptual context. The probabilities that retrieved documents are generated within the contextual space are then computed for document re-ranking. Empirical evaluation on the TREC Genomics full-text collection and three high-performance biomedical literature retrieval runs demonstrates that the context-sensitive re-ranking approach yields better retrieval performance.

Background: Newly microarray technologies yield large-scale datasets. The microarray datasets are usually presented in 2D matrices, where rows represent genes and columns represent experimental conditions. Systematic analysis of those datasets provides the increasing amount of information, which is urgently needed in the post-genomic era. Biclustering, which is a technique developed to allow simultaneous clustering of rows and columns of a dataset, might be useful to extract more accurate information from those datasets. Biclustering requires the optimization of two conflicting objectives (residue and volume), and a multi-objective artificial immune system capable of performing a multi-population search. As a heuristic search technique, artificial immune systems (AISs) can be considered a new computational paradigm inspired by the immunological system of vertebrates and designed to solve a wide range of optimization problems. During biclustering several objectives in conflict with each other have to be optimized simultaneously, so multi-objective optimization model is suitable for solving biclustering problem., Results: Based on dynamic population, this paper proposes a novel dynamic multi-objective immune optimization biclustering (DMOIOB) algorithm to mine coherent patterns from microarray data. Experimental results on two common and public datasets of gene expression profiles show that our approach can effectively find significant localized structures related to sets of genes that show consistent expression patterns across subsets of experimental conditions. The mined patterns present a significant biological relevance in terms of related biological processes, components and molecular functions in a species-independent manner., Conclusions: The proposed DMOIOB algorithm is an efficient tool to analyze large microarray datasets. It achieves a good diversity and rapid convergence.

Background: High-throughput microarray technologies have generated and accumulated massive amounts of gene expression datasets that contain expression levels of thousands of genes under hundreds of different experimental conditions. The microarray datasets are usually presented in 2D matrices, where rows represent genes and columns represent experimental conditions. The analysis of such datasets can discover local structures composed by sets of genes that show coherent expression patterns under subsets of experimental conditions. It leads to the development of sophisticated algorithms capable of extracting novel and useful knowledge from a biomedical point of view. In the medical domain, these patterns are useful for understanding various diseases, and aid in more accurate diagnosis, prognosis, treatment planning, as well as drug discovery., Results: In this work we present the CMOPSOB (Crowding distance based Multi-objective Particle Swarm Optimization Biclustering), a novel clustering approach for microarray datasets to cluster genes and conditions highly related in sub-portions of the microarray data. The objective of biclustering is to find sub-matrices, i.e. maximal subgroups of genes and subgroups of conditions where the genes exhibit highly correlated activities over a subset of conditions. Since these objectives are mutually conflicting, they become suitable candidates for multi-objective modelling. Our approach CMOPSOB is based on a heuristic search technique, multi-objective particle swarm optimization, which simulates the movements of a flock of birds which aim to find food. In the meantime, the nearest neighbour search strategies based on crowding distance and -dominance can rapidly converge to the Pareto front and guarantee diversity of solutions. We compare the potential of this methodology with other biclustering algorithms by analyzing two common and public datasets of gene expression profiles. In all cases our method can find localized structures related to sets of genes that show consistent expression patterns across subsets of experimental conditions. The mined patterns present a significant biological relevance in terms of related biological processes, components and molecular functions in a species-independent manner., Conclusion: The proposed CMOPSOB algorithm is successfully applied to biclustering of microarray dataset. It achieves a good diversity in the obtained Pareto front, and rapid convergence. Therefore, it is a useful tool to analyze large microarray datasets.

Due to the outstanding performance of deep neural networks (DNNs), many researchers have begun to transfer deep learning techniques to their fields. To detect algorithmically generated domains (AGDs) generated by domain generation algorithm (DGA) in botnets, a long short-term memory (LSTM)-based DGA detector has achieved excellent performance. However, the previous DNNs have found various inherent vulnerabilities, so cyberattackers can use these drawbacks to deceive DNNs, misleading DNNs into making wrong decisions. Backdoor attack as one of the popular attack strategies strike against DNNs has attracted widespread attention in recent years. In this paper, to cheat the LSTM-based DGA detector, we propose BadDGA, a backdoor attack against the LSTM-based DGA detector. Specifically, we offer four backdoor attack trigger construction methods: TLD-triggers, Ngram-triggers, Word-triggers, and IDN-triggers. Finally, we evaluate BadDGA on ten popular DGA datasets. The experimental results show that under the premise of 1‰ poisoning rate, our proposed backdoor attack can achieve a 100% attack success rate to verify the effectiveness of our method. Meanwhile, the model's utility on clean data is influenced slightly. [ABSTRACT FROM AUTHOR]

Abstract Multi-view representation learning for social images has recently made remarkable achievements in many tasks, such as cross-view classification and cross-modal retrieval. Since social images usually contain link information besides the multi-modal contents (e.g., text description, and visual content), simply employing the data content may result in sub-optimal multi-view representation of the social images. In this paper, we propose a Deep Multi-View Embedding Model (DMVEM) to learn joint embeddings for the three views including the visual content, the associated text descriptions, and their relations. To effectively encode the link information, a weighted relation network is built based on the linkages between social images, which is then embedded into a low dimensional vector space using the Skip-Gram model. The learned vector is regarded as the third view besides the visual content and text description. To learn a joint representation from the three views, a deep learning model with three-branch nonlinear neural network is proposed. A three-view bi-directional loss function is used to capture the correlation between the three views. The stacked autoencoder is adopted to preserve the self-structure and reconstructability of the learned representation for each view. Comprehensive experiments are conducted in the tasks of image-to-text, text-to-image, and image-to-image searches. Compared to the state-of-the-art multi-view embedding methods, our approach achieves significant improvement of performance. Highlights • We investigate the problem of multi-view learning for the linkage-embedded social images using deep model. • The learned representation can effectively capture both the content and the network structure. • We propose a deep multi-view model DMVEM to effectively learn a joint representation from the three views of social image. • The experimental results demonstrate the superiority of the proposed model against the state-of-the-art baselines. [ABSTRACT FROM AUTHOR]

Automatic tagging can automatically label images and videos with semantic tags to significantly facilitate multimedia search and organization. However, most of existing tagging algorithms often don't differentiate between tags used to describe visual content, and neglect the semantic correlation of the assigned tag set. In this paper, we propose a novel automatic tagging algorithm which tags a test image or video with an Informative and Correlative Tag (ICTag) set. The assigned ICTag set can provide a more precise description of the multimedia object by exploring both the information capability of individual tags and the tag-to-set correlation. Measures to effectively estimate the information capability of individual tags and the correlation between a tag and the candidate tag set are designed. To reduce the computational complexity, we also introduce a heuristic method to achieve efficient automatic tagging. We conduct extensive experiments on the NUS-WIDE web image dataset downloaded from Flickr and the MCG-WEBV web video dataset downloaded from YouTube. The results confirm the efficiency and effectiveness of our proposed algorithm. [ABSTRACT FROM AUTHOR]

• Define three types of features extracted from URLs, domains, etc. • Exploit a method to balance the majority and minority class samples. • Adopt an improved DAE-based method to reduce the dimension of the dataset. • Boost the detection performance by using the improved ELM-based classifier. • Do experiments to verify the feasibility and effectiveness of the proposed approach. In this paper, a novel approach based on non-inverse matrix online sequence extreme learning machine (NIOSELM) for phishing detection is presented, which takes into account three types of features to comprehensively characterize a website. For the NIOSELM algorithm, we use Sherman Morriso Woodbury equation to avoid the matrix inversion operation, and introduce the idea of online sequence extreme learning machine (OSELM) to update the training model. In order to reduce the dependence of the detection model on the majority class, we use Adaptive Synthetic Sampling (ADASYN) algorithm to generate the synthetic minority class samples to balance the distribution between the samples of the majority and minority classes. Furthermore, an improved denoising auto-encoder (SDAE) is designed to reduce the dimension of the experimental dataset. The experimental results show the efficiency and feasibility of the proposed detection mechanism. Moreover, the overall detection performance of NIOSELM is better than that of other existing methods, especially in training speed and the detection accuracy. [ABSTRACT FROM AUTHOR]