摘要：
Differential evolution (DE) has been a popular algorithm for its simple structure and few control parameters. However, there are some open issues in DE regrading its mutation strategies. An interesting one is how to balance the exploration and exploitation behaviour when performing mutation, and this has attracted a growing number of research interests over a decade. To address this issue, this paper presents a triangular Gaussian mutation strategy. This strategy utilizes the physical positions and the fitness differences of the vertices in the triangular structure. Based on this strategy, a triangular Gaussian mutation to DE and its improved version (ITGDE) are suggested. Empirical studies are carried out on the 20 benchmark functions and show that, in comparison with several state-of-the-art DE variants, ITGDE obtains significantly better or at least comparable results, suggesting the proposed mutation strategy is promising for DE.
摘要：
Dense motion estimations obtained from optical flow techniques play a significant role in many image processing and computer vision tasks. Remarkable progress has been made in both theory and its application in practice. In this paper, we provide a systematic review of recent optical flow techniques with a focus on the variational method and approaches based on Convolutional Neural Networks (CNNs). These two categories have led to state-of-the-art performance. We discuss recent modifications and extensions of the original model, and highlight remaining challenges. For the first time, we provide an overview of recent CNN-based optical flow methods and discuss their potential and current limitations.
摘要：
This paper addresses the issue of video-based action recognition by exploiting an advanced multi-stream Convolutional Neural Network (CNN) to fully use semantics-derived multiple modalities in both spatial (appearance) and temporal (motion) domains, since the performance of the CNN-based action recognition methods heavily relate to two factors: semantic visual cues and the network architecture. Our work consists of two major parts. First, to extract useful human-related semantics accurately, we propose a novel spatiotemporal saliency based video object segmentation (STS-VOS) model. By fusing different distinctive saliency maps, which are computed according to object signatures of complementary object detection approaches, a refined spatiotemporal saliency maps can be obtained. In this way, various challenges in the realistic video can be handled jointly. Based on the estimated saliency maps, an energy function is constructed to segment two semantic cues: the actor and one distinctive acting part of the actor. Second, we modify the architecture of the two-stream network (TS-Net) to design a multi-stream network (MS-Net) that consists of three TS-Nets with respect to the extracted semantics, which is able to use deeper abstract visual features of multi-modalities in multi-scale spatiotemporally. Importantly, the performance of action recognition is significantly boosted when integrating the captured human-related semantics into our framework. Experiments on four public benchmarks JHMDB, HMDB51, UCF-Sports and UCF101 demonstrate that the proposed method outperforms the state of the art algorithms.
摘要：
In order to avoid the problem that the color distortion and the details are not obvious, this paper presents an improved defogging algorithm. It uses the dark channel prior to estimate the atmospheric light and the transmission and proposes a new gradient domain filtering to refine the transmission. Then, the intensity compensation is used to enhance the image color information. At the same time, the atmospheric light value is estimated and boundary constrains is used to roughly estimate the transmission, and, weights is added to define the transmission. So the scene transmission of both is refined, the image is reduced by atmospheric scattering model and two images are fused with the fusion strategy. The fusion of image uses the auto white balance to fine tune to get the final image. According to the experimental results, the algorithm effectively solves the problem of color distortion and loss of detail information in the defog image.
摘要：
The most successful video-based human action recognition methods rely on feature representations extracted using Convolutional Neural Networks (CNNs). Inspired by the two-stream network (TS-Net), we propose a multi-stream Convolutional Neural Network (CNN) architecture to recognize human actions. We additionally consider human-related regions that contain the most informative features. First, by improving foreground detection, the region of interest corresponding to the appearance and the motion of an actor can be detected robustly under realistic circumstances. Based on the entire detected human body, we construct one appearance and one motion stream. In addition, we select a secondary region that contains the major moving part of an actor based on motion saliency. By combining the traditional streams with the novel human-related streams, we introduce a human-related multi-stream CNN (HR-MSCNN) architecture that encodes appearance, motion, and the captured tubes of the human-related regions. Comparative evaluation on the JHMDB, HMDB51, UCF Sports and UCF101 datasets demonstrates that the streams contain features that complement each other. The proposed multi-stream architecture achieves state-of-the-art results on these four datasets. (C) 2018 Elsevier Ltd. All rights reserved.
作者机构：
[Jiang, Xingpeng; Xie, Wei; Yang, Jincai; He, Tingting; Shen, Xianjun; Hu, Po; Hu, Xiaohua; Yi, Li] Cent China Normal Univ, Sch Comp, Wuhan, Hubei, Peoples R China.;[Yi, Li] Letv Cloud Comp Co Ltd, Beijing, Peoples R China.;[Hu, Xiaohua] Drexel Univ, Coll Comp & Informat, Philadelphia, PA 19104 USA.
通讯机构：
[Shen, Xianjun] C;Cent China Normal Univ, Sch Comp, Wuhan, Hubei, Peoples R China.
关键词：
Protein complexes;Algorithms;Protein interaction networks;Gene expression;Protein interactions;Forecasting;Genetic networks;Yeast
摘要：
How to identify protein complex is an important and challenging task in proteomics. It would make great contribution to our knowledge of molecular mechanism in cell life activities. However, the inherent organization and dynamic characteristic of cell system have rarely been incorporated into the existing algorithms for detecting protein complexes because of the limitation of protein-protein interaction (PPI) data produced by high throughput techniques. The availability of time course gene expression profile enables us to uncover the dynamics of molecular networks and improve the detection of protein complexes. In order to achieve this goal, this paper proposes a novel algorithm DCA (Dynamic Core-Attachment). It detects protein-complex core comprising of continually expressed and highly connected proteins in dynamic PPI network, and then the protein complex is formed by including the attachments with high adhesion into the core. The integration of core-attachment feature into the dynamic PPI network is responsible for the superiority of our algorithm. DCA has been applied on two different yeast dynamic PPI networks and the experimental results show that it performs significantly better than the state-of-the-art techniques in terms of prediction accuracy, hF-measure and statistical significance in biology. In addition, the identified complexes with strong biological significance provide potential candidate complexes for biologists to validate.
摘要：
In this paper, a novel and effective algorithm is proposed for noise reduction and contrast enhancement in low light images based on luminance map and haze removal model. The proposed method is divided into two steps: i) A combined denoising method using the improved guided filtering based on gradient information and median filtering is proposed to obtain the initial denoised image. ii)Considering that an inverted low light image presents quite similar to a haze image, the haze removal model is used to enhance the denoised low light image. The luminance component L is extracted to obtain the transmission map with the adaptive weight from the inverted denoised image which is applied to Lab color space. Then the classical quad-tree subdivision is utilized to estimate the atmospheric light, and then the de-hazed image is recovered by the haze removal model. At last, we can get the final enhanced image by inverting the de-hazed image back. The experimental results show that the proposed algorithm reduces the noise and enhances the contrast of the low light image more effectively and robustly than the conventional and the state-of-the-art algorithms.
摘要：
Differential evolution (DE) is one of the most powerful and effective evolutionary algorithms for the global optimization problems. However, the performance of DE highly depends on control parameters. To solve this problem, dissipative differential evolution with self-adaptive control parameters (DSDE) is proposed in this paper. In DSDE approach, the values of control parameters are adjusted by the fitness information between the target vector and trial vector. Because the population diversity is a key to avoid falling into the local optima, DSDE develops dissipative scheme to make the population far away equilibrium state. Experimental studies on comprehensive set of benchmark functions show DSDE achieves better results for the majority of test cases.
关键词：
Dynamics;Forecasting;Intelligent systems;Linear transformations;Mathematical transformations;Random processes;Roads and streets;Social networking (online);Taxicabs;Traffic control;Transportation;Travel time;Conditional random field;Dynamic patterns;Environmental information;Environmental resources;Intelligent transportation systems;Temporal transformations;Traffic conditions;Travel time prediction;Transportation routes
摘要：
Finding fastest driving routes is significant for the intelligent transportation system. While predicting the online traffic conditions of road segments entails a variety of challenges, it contributes much to travel time prediction accuracy. In this paper, we propose O-Sense, an innovative online-traffic-prediction based route finding mechanism, which organically utilizes large scale taxi GPS traces and environmental information. O-Sense firstly exploits a deep learning approach to process spatial and temporal taxi GPS traces shown in dynamic patterns. Meanwhile, we model the traffic flow state for a given road segment using a linear-chain conditional random field (CRF), a technique that well forecasts the temporal transformation if provided with further supplementary environmental resources. O-Sense then fuses previously obtained outputs with a dynamic weighted classifier and generates a better traffic condition vector for each road segment at different prediction time. Finally, we perform online route computing to find the fastest path connecting consecutive road segments in the route based on the vectors. Experimental results show that O-Sense can estimate the travel time for driving routes more accurately.
摘要：
Traffic flow condition prediction is a basic problem in the transportation field. It is challenging to play out full potential of temporally-related information and overcome the problem of data sparsity existed in the traffic flow prediction. In this paper, we propose a novel urban traffic prediction mechanism namely C-Sense consisting of two parts: CRF-based temporal feature learning and sequence segments matching. CRF-based temporal feature learning exploits a linear-chain condition random field (CRF) to explore the temporal transformation rule in the traffic flow state sequence with supplementary environmental resources. Sequence segments matching is utilized to match the obtained state sequence segments with historical condition to get the ultimate prediction results. Experiments are evaluated based on datasets obtained in Wuhan and the results show that our mechanism can achieve good performance, which prove that it is a potential approach in transportation field.
