This work develops a biologically inspired neural network for contour detection in natural images by combining the nonclassical receptive field modulation mechanism with a deep learning framework. The input image is first convolved with the local feature detectors to produce the classical receptive field responses, and then a corresponding modulatory kernel is constructed for each feature map to model the nonclassical receptive field modulation behaviors. The modulatory effects can activate a larger cortical area and thus allow cortical neurons to integrate a broader range of visual information to recognize complex cases. Additionally, to characterize spatial structures at various scales, a multiresolution technique is used to represent visual field information from fine to coarse. Different scale responses are combined to estimate the contour probability. Our method achieves state-of-the-art results among all biologically inspired contour detection models. This study provides a method for improving visual modeling of contour detection and inspires new ideas for integrating more brain cognitive mechanisms into deep neural networks.

In this paper, we propose a bioinspired model for human action recognition through modeling neural mechanisms of information processing in two visual cortical areas: the primary visual cortex (V1) and the middle temporal cortex (MT) dedicated to motion. This model, named V1-MT, is composed of V1 and MT models (layers) corresponding to their cortical areas, which are built with layered spiking neural networks (SNNs). Some neuron properties in V1 and MT, such as direction and speed selectivity, spatiotemporal inseparability, and center surround suppression, are integrated into SNNs. Based on speed and direction selectivity, V1 and MT models contain multiple SNN channels, each of which processes motion information in sequences with spatiotemporal tunings of neurons at a certain speed and different directions. Therefore, we propose two operations, input signal perceiving with 3-D Gabor filters and surround inhibition processing with 3-D differences of Gaussian functions, to perform this task according to the spatiotemporal inseparability and center surround suppression of neurons. Then, neurons are modeled with our simplified integrate-and-fire model and motion information is transformed into spike trains. Afterward, we define a new feature vector: a mean motion map computed from spike trains in all channels to represent human actions. Finally, a support vector machine is trained to classify actions represented by the feature vectors. We conducted extensive experiments on public action databases, and the results show that our model outperforms other bioinspired models and rivals the state-of-the-art approaches.

MOTIVATION: Genomic imprinting is regulated by lncRNAs and is important for embryogenesis, physiology and behaviour in mammals. Aberrant imprinting causes diseases and disorders. Experimental studies have examined genomic imprinting primarily in humans and mice, thus leaving some fundamental issues poorly addressed. The cost of experimentally examining imprinted genes in many tissues in diverse species makes computational analysis of lncRNAs' DNA binding sites valuable. RESULTS: We performed lncRNA/DNA binding analysis in imprinting clusters from multiple mammalian clades and discovered the following: (i) lncRNAs and imprinting sites show significant losses and gains and distinct lineage-specificity; (ii) binding of lncRNAs to promoters of imprinted genes may occur widely throughout the genome; (iii) a considerable number of imprinting sites occur in only evolutionarily more derived species; and (iv) multiple lncRNAs may bind to the same imprinting sites, and some lncRNAs have multiple DNA binding motifs. These results suggest that the occurrence of abundant lncRNAs in mammalian genomes makes genomic imprinting a mechanism of adaptive evolution at the epigenome level. AVAILABILITY AND IMPLEMENTATION: The data and program are available at the database LongMan at lncRNA.smu.edu.cn. CONTACT: [email protected]. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: In mammalian cells, many genes are silenced by genome methylation. DNA methyltransferases and polycomb repressive complexes, which both lack sequence-specific DNA-binding motifs, are recruited by long non-coding RNA (lncRNA) to specific genomic sites to methylate DNA and chromatin. Increasing evidence indicates that many lncRNAs contain DNA-binding motifs that can bind to DNA by forming RNA:DNA triplexes. The identification of lncRNA DNA-binding motifs and binding sites is essential for deciphering lncRNA functions and correct and erroneous genome methylation; however, such identification is challenging because lncRNAs may contain thousands of nucleotides. No computational analysis of typical lncRNAs has been reported. Here, we report a computational method and program (LongTarget) to predict lncRNA DNA-binding motifs and binding sites. We used this program to analyse multiple antisense lncRNAs, including those that control well-known imprinting clusters, and obtained results agreeing with experimental observations and epigenetic marks. These results suggest that it is feasible to predict many lncRNA DNA-binding motifs and binding sites genome-wide. AVAILABILITY AND IMPLEMENTATION: Website of LongTarget: lncrna.smu.edu.cn, or contact: [email protected]. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Human visual system is an effective recognition one. Based on information processing mechanism of visual cortex, a bio-inspired approach for the human action recognition from video sequences is proposed in this paper. The approach gives a hierarchical architecture of the feedforward spiking neural network modeling two visual cortical areas: primary visual cortex (VI) and middle temporal area (MT), neurobiologically dedicated to motion processing. We augment the operator of motion information processing with center surround interaction to model the nonclassical receptive field inhibitory effect based on horizontal connection of spiking neurons in each cortical area. The weight function of lateral connection between VI and MT areas is built based on a previous study that explained direction selectivity in MT area by a linear combination of normalized VI direction-tuned signals. Moreover, we propose a three-dimensional (3D) Gabor filter to model the spatiotemporal direction and speed tuning properties of time-dependent receptive fields of the VI cells. The conductance-driven integrate-and-fire (IF) neuron model is used to obtain spike trains generated by the spiking neurons in two cortical areas. Finally, in order to analyze spike trains, we consider a characteristic of the neural code: mean motion map based on the mean firing rates of neurons in MT, called action code, as feature vector representing human actions. The approach is carried out on the Weizmann and KTH action database. Experimental results show that our approach has higher recognition performance and computational efficiency than other bio-inspired ones.

A model for detecting contours in natural images is presented by combining the visual perceptual mechanisms and machine learning. The surround stimuli will enhance the response of the central stimulus if they can form a precise spatial configuration. On the other hand, surround inhibition will reduce the responses to homogeneous elements. Facilitation and inhibition activities in the primary visual cortex (V1) are used to enhance the well-organized structures and to reduce the non-meaningful distractors engendering from texture fields, respectively. We approach the task of facilitatory and inhibitory cue integration as a supervised learning problem using the logistic regression model. Our experiments demonstrate that the model can dramatically reduce texture edges and spurious contours, and meanwhile can to some extent avoid ground-truth contours missed by the detector.

An efficient moving object segmentation algorithm in the wavelet domain is proposed using two successive frames in this paper. The first, the change detection method with fuzzy clustering incorporating with motion features in four wavelet sub- bands is used to separate change detection masks in the wavelet domain from the background. The change detection masks in original resolution are then obtained with the inverse wavelet. Finally, further object shape information and accurate extraction of the moving object is obtained according to current object edge map. The experimental results demonstrate the algorithm effective. I. INTRODUCTION

In this paper, an efficient moving object segmentation algorithm in the wavelet domain is proposed using three successive frames. The change detection method, which employs fuzzy C-means clustering technique to classify motion features of four wavelet sub-bands, is used twice to separate significant change pixels in the wavelet domain from the background. After applying the intersect operation, the change detection masks are obtained in wavelet domain. Finally, further object shape information and accurate extraction of the moving object is obtained in original resolution according to current object edge map. The experimental results demonstrate the algorithm effective.

In block motion estimation, search patterns with different shapes or sizes have a large impact on the searching speed and quality of performance. In this paper, we propose an unsymmetrical dual cross search algorithm (UDCS), using a small cross-search pattern as the initial step for small motion vector estimation in according to center-biased characteristics of motion-vector distribution. In addition, the algorithm uses an unsymmetrical cross search patterns (UCSP) as the subsequent steps based on direction characteristics of motion vector distribution for large motion vectors search. The improvement of UDCS over DS and CDS can be up to a 70% and 40% gain on speedup, respectively. Experimental results show that the UDCS is much more robust, and provides faster searching than other popular fast block-matching algorithms with the comparative distortions.