Although existing object detectors achieve encouraging performance of object detection and localisation under real ideal conditions, the detection performance in adverse weather conditions (snowy) is very poor and not enough to cope with the detection task in adverse weather conditions. Existing methods do not deal well with the effect of snow on the identity of object features or usually ignore or even discard potential information that can help improve the detection performance. To this end, the authors propose a novel and improved end‐to‐end object detection network joint image restoration. Specifically, in order to address the problem of identity degradation of object detection due to snow, an ingenious restoration‐detection dual branch network structure combined with a Multi‐Integrated Attention module is proposed, which can well mitigate the effect of snow on the identity of object features, thus improving the detection performance of the detector. In order to make more effective use of the features that are beneficial to the detection task, a Self‐Adaptive Feature Fusion module is introduced, which can help the network better learn the potential features that are beneficial to the detection and eliminate the effect of heavy or large local snow in the object area on detection by a special feature fusion, thus improving the network's detection capability in snowy. In addition, the authors construct a large‐scale, multi‐size snowy dataset called Synthetic and Real Snowy Dataset (SRSD), and it is a good and necessary complement and improvement to the existing snowy‐related tasks. Extensive experiments on a public snowy dataset (Snowy‐weather Datasets) and SRSD indicate that our method outperforms the existing state‐of‐the‐art object detectors.

To improve the accuracy of human pose estimation, a novel method based on the deep high-resolution network (HRNet) and equipped with double attention residual blocks is proposed. Firstly, the channel attention and spatial attention modules are added to the residual block of feature extraction, resulting in the network paying more attention to the target area which needs to be extracted important information and suppressed unimportant information. Moreover, this paper proposes a novel module, Parallel Residual Attention Block (PRAB), which parallels the 3x3 group convolution of ResNeXt to the 3x3 convolution layer in the Bottleneck of ResNet, and then adds channel attention and spatial attention modules to these two branches respectively. In this way, the network can further improve the accuracy of human keypoint detection without significantly increasing the computation overhead. To demonstrate the effectiveness of our method, a series of comparative experiments are conducted on the MPII Human Pose dataset and the COCO2017 keypoint detection dataset. Experimental results illustrate that the attention mechanism is effective to improve the accuracy of human pose estimation and the proposed PRAB obtained the best results 90.5% on MPII which outperforms the existing methods.

Crowd counting is a task that aims to estimate the number of people in an image. Recent crowd counting methods make significant progress by employing convolutional neural networks to regress crowd density maps. One of the most challenging problems in this task is the drastic scale variation of the region of interest in images. In this paper, a Feature Fusion Attention Network (FFANet) is proposed for crowd counting. Firstly, the VGG16 network is adapted as the backbone of the FFANet to extract the features of crowd images. Then, the extracted features are fused by the subsequent two stages. Specifically, the information enhancement operations on the multi-levels features are conducted by Feature Fusion Attention Module (FFAM), which are further refined by the Residual Block (RB). Finally, the features are processed by the Compression Module (CM) to generate a density map. To demonstrate the effectiveness, the proposed algorithm is verified on three benchmark datasets. Evaluation of the algorithm performances in comparison with other state-of-the-art methods indicates the proposed FFANet outperforms the existing methods.

The training of fully supervised semantic segmentation (FSSS) networks relies on a large amount of data with pixel-level class labels, which limits semantic segmentation's application in practical scenarios. Weakly supervised semantic segmentation (WSSS) based on image-level class labels has become a new research hotspot in the field of image semantic segmentation. In this paper, the WSSS algorithms with image-level class labels are classified and sorted out according to two critical steps of the generic pipeline: seed generation and mask refinement. Different ways of seed generation can be divided into three categories: Multiple-Instance Learning-based methods, Class Activation Maps-based methods, and other generation methods. Different seed mask refinement methods can be divided into affinity-based mask refinement methods, additional supervision-based mask refinement methods, and other mask refinement methods. In addition, this paper analyzes the principles, key ideas, primary contributions, and advantages and disadvantages of various methods. Then, the segmentation performance of different WSSS algorithms on different datasets are compared, and the current state-of-the-art segmentation algorithms are labeled. Finally, the main challenges currently faced in the field and possible future directions have been prospected.

In human society, opinion evolution and guidance for opinion evolution are useful for maintaining social stability, business development, and so on. To tackle these issues, we propose an opinion evolution and guidance model based on social networks and information networks (namded EGSDCN) for the first time. Firstly, we develop an opinion evolution model based on the information networks and social networks (ISOE). Specifically, we first update the individual’s opinion by judging the quality of the information obtained by individual from the information network. Then, we filter the trusted neighbor set for individuals by quantifying individuals’ attributes and update individual’s opinion after weighting analysis of the trusted neighbor set. Finally, we conduct information exchange between the social and information networks. For guiding opinion evolution, we develop a group opinion guidance strategy based on individual stubbornness differences (termed PDGM). Specifically, we first divide the guided individuals into stubborn and non-stubborn groups. Then, for the non-stubborn group, a linear function model is used to intervene individual stubbornness. For the stubborn group, we propose the interest and opinion change functions to dynamically adjust individuals’ opinion. Extensive simulation experiments have been conducted and proved that our proposed model is effective.

Crowd counting is an important research topic in computer vision. Its goal is to estimate the people's number in an image. Researchers have dramatically improved counting accuracy in recent years by regressing density maps. However, because of the inherent domain shift, the model trained on an expensive manually labelled dataset (source domain) does not perform well on a dataset with scarce labels (target domain). For this issue, a novel dynamic scale aggregation network (DSANet) is proposed to reduce the gaps in style and cross‐domain head scale variations. Specifically, a practical style transfer layer is introduced to reduce the appearance discrepancy between the source and target domains. Then, the translated source and target domain samples are encoded by a generator consisting of the VGG16 network and the dynamic scale aggregation modules (DSA Modules) and produce corresponding density maps. The DSA module can adaptively adjust parameters according to the input features and effectively fuse multi‐scale information to overcome the cross‐domain head scale variations. Next, a discriminator judges the input density map from the source or target domain. Last, domain distributions are aligned through adversarial between the generator and the discriminator. The experiments show that our network outperforms the current state‐of‐the‐art methods and can improve the target domain's performance while maintaining the source domain's performance without significant degradation.