The human attention mechanism can be understood and simulated by closely associating the saliency prediction task to neuroscience and psychology. Furthermore, saliency prediction is widely used in computer vision and interdisciplinary subjects. In recent years, with the rapid development of deep learning, deep models have made amazing achievements in saliency prediction. Deep learning models can automatically learn features, thus solving many drawbacks of the classic models, such as handcrafted features and task settings, among others. Nevertheless, the deep models still have some limitations, for example in tasks involving multi-modality and semantic understanding. This study focuses on summarizing the relevant achievements in the field of saliency prediction, including the early neurological and psychological mechanisms and the guiding role of classic models, followed by the development process and data comparison of classic and deep saliency prediction models. This study also discusses the relationship between the model and human vision, as well as the factors that cause the semantic gaps, the influences of attention in cognitive research, the limitations of the saliency model, and the emerging applications, to provide new saliency predictions for follow-up work and the necessary help and advice.

Permutation network plays an important role in the reconfigurable QC-LDPC decoder for most modern wireless communication systems with multiple code rates and various code lengths. In this paper, we propose the variation Banyan network (VBN) based permutation network architecture for the reconfigurable QC-LDPC decoders and give the control signal generating algorithm for cyclic shift. Through introducing the bypass network, we put forward the nonblocking scheme for any input number and shift number. In addition, the optimized VBN is proposed for WiMAX and WiFi standard, which can shift at most 4 groups of input data, and greatly reduce the hardware complexity. The synthesis results using the 90 nm technology demonstrate that the proposed permutation network can be implemented with the gate count of 18.3 k and the frequency of 600 MHz.

Target tracking has always been a popular research area in computer vision, and many important methods have been proposed. However, most methods can only solve partial and slight occlusion. If the target is lost, a common solution is to keep detecting, reidentify the target when it reappears, and then link the broken tracks together, but this makes tracking discontinuous. There are two key points in this problem: continuous tracking and occlusion judgment. In this paper, we propose a target tracking method with a short-time prediction function to solve this problem. For continuous tracking, we establish a 3D dynamic model to estimate the motion state of the target in each frame. For occlusion judgment, we use a depth prediction network to estimate the depth of the target and then determine whether the target is occluded by the depth. Without relying on depth sensors or multiple cameras, we achieve depth estimation using only a single monocular image, which greatly expands the application of our method. Benefit from the introduction of motion estimation and depth prediction, the tracking accuracy of our method has been significantly improved, especially for better robustness to occlusion. Even when the target is completely occluded, it can be tracked for a short time without reidentification. In addition, we improve the speed of depth prediction through knowledge distillation by 2.08 times, and the final tracking speed reaches 52.6 Hz on GPU, which meets the real-time tracking requirements.

This paper applies machine learning technology to the Satir theory model and intelligently classifies the communication stances of the second layer according to the language and behaviour information of the first layer. We arranged a large number of dialogical language materials from a TV interview programme and used the ICTCLAS Chinese word segmentation system to create a ‘psychological consultation database’. We construct the word training set by part of making use of speech filtering and text word vectorisation, and construct the semantic training set by annotating the original data with the Satir model. These two sets form the Satir communication posture classification training set. Experimental results show that the success rate of classification of four inconsistent coping stances reached 70.37%, 75.92%, 83.33%, and 77.78%.

Gaze tracking is basic research in the era of the Internet of Things. This study attempts to improve the performance of gaze tracking in an active infrared source gaze-tracking system. Owing to unavoidable noise interference, the estimated points of regard (PORs) tend to fluctuate within a certain range. To reduce the fluctuation range and obtain more stable results, we introduced a Kalman filter (KF) to filter the gaze parameters. Considering that the effect of filtering is relevant to the motion state of the gaze, we design the measurement noise that varies with the speed of the gaze. In addition, we used a correlation filter-based tracking method to quickly locate the pupil, instead of the detection method. Experiments indicated that the variance of the estimation error decreased by 73.83%, the size of the extracted pupil image decreased by 93.75%, and the extraction speed increased by 1.84 times. We also comprehensively discussed the advantages and disadvantages of the proposed method, which provides a reference for related research. It must be pointed out that the proposed algorithm can also be adopted in any eye camera-based gaze tracker.

Target tracking is an important application of unmanned aerial vehicles (UAVs). The template is the identity of the target and has a great impact on the performance of target tracking. Most methods only keep the latest template of the target, which is intuitive and convenient but has poor ability to resist the change of target appearance, especially to reidentify a target that has disappeared for a long time. In this paper, we propose a practical multiobject tracking (MOT) method, which uses historical information of targets for better adapting to appearance variations during tracking. To preserve the spatial-temporal information of the target, we introduce a memory pool to store masked feature maps at different moments, and precise masks are generated by a segmentation network. Meanwhile, we fuse the feature maps at different moments by calculating the pixel-level similarity between the current feature map and the masked historical feature maps. Benefiting from the powerful segmentation features and the utilization of historical information, our method can generate more accurate bounding boxes of the targets. Extensive experiments and comparisons with many trackers on MOTS, MOT17, and MOT20 demonstrate that our method is competitive. The ablation study showed that the introduction of memory improves the multiobject tracking accuracy (MOTA) by 2.1.