Recognizing occluded facial expressions in the wild poses a significant challenge. However, most previous approaches rely solely on either global or local feature-based methods, leading to the loss of relevant expression features. To address these issues, a feature fusion residual attention network (FFRA-Net) is proposed. FFRA-Net consists of a multi-scale module, a local attention module, and a feature fusion module. The multi-scale module divides the intermediate feature map into several sub-feature maps in an equal manner along the channel dimension. Then, a convolution operation is applied to each of these feature maps to obtain diverse global features. The local attention module divides the intermediate feature map into several sub-feature maps along the spatial dimension. Subsequently, a convolution operation is applied to each of these feature maps, resulting in the extraction of local key features through the attention mechanism. The feature fusion module plays a crucial role in integrating global and local expression features while also establishing residual links between inputs and outputs to compensate for the loss of fine-grained features. Last, two occlusion expression datasets (FM_RAF-DB and SG_RAF-DB) were constructed based on the RAF-DB dataset. Extensive experiments demonstrate that the proposed FFRA-Net achieves excellent results on four datasets: FM_RAF-DB, SG_RAF-DB, RAF-DB, and FERPLUS, with accuracies of 77.87%, 79.50%, 88.66%, and 88.97%, respectively. Thus, the approach presented in this paper demonstrates strong applicability in the context of occluded facial expression recognition (FER).

This paper proposes a fractional order optimization method of a fractional order multi-variable Grey model (GM( $r$ ,2)) based on a full transfer learning LSTM network. Firstly, a GM( $r$ ,2) was built with adhesion coefficient as input variable, namely, correlation factor sequence, and driving intention as output variable, namely, system behaviour characteristic sequence. Secondly, a long short-term memory (LSTM) network was trained by means of driving intention dataset, which is defined as source domain dataset. Adhesion coefficient, which is selected as test dataset, is defined as target domain dataset. By utilizing relative degree of grey incidence, it is proved that source domain dataset is extremely similar with target domain dataset. The LSTM network trained by driving intention dataset can be transferred fully to calculate optimization data. Finally, with the optimization data predicted by the LSTM network, an optimized fractional order of GM( $r$ ,2) can be calculated by fractional-order accumulation matrix calculation and least square fitting. Comparing with particle swarm optimization (PSO), the proposed optimization method can effectively improve the convergence of fractional order optimization values. The optimized GM( $r_{opt}$ ,2) was applied in inferring diving intention for an active safety driving system of electric vehicles. Simulation experiments are performed in car-following and lane-changing processes, respectively. The driving intention inferred by GM( $r_{opt}$ ,2) can change not only longitudinal safety distance, but also lane-changing trajectory with different road conditions. It can ensure vehicle driving safety. Experimental data can demonstrate that the proposed optimization method of fractional order is effective, and the optimized GM( $r_{opt}$ ,2) is appropriate to infer driving intention.

Most unsupervised methods of person re-identification (Re-ID) obtain pseudo-labels through clustering. However, in the process of clustering, the hard quantization loss caused by clustering errors will make the model produce false pseudo-labels. In order to solve this problem, an unsupervised model based on softened labels training method is proposed. The innovation of this method is that the correlation among image features is used to find the reliable positive samples and train them in a smooth manner. To further explore the correlation among image features, some modules are carefully designed in this article. The dynamic adaptive label allocation (DALA) method which generates pseudo-labels of adaptive size according to different metric relationships among features is proposed. The channel attention and transformer architecture (CATA) auxiliary module is designed, which, associated with convolutional neural network (CNN), functioned as the feature extractor of the model aimed to capture long range dependencies and acquire more distinguishable features. The proposed model is evaluated on the Market-1501 and the DukeMTMC-reID. The experimental results of the proposed method achieve 60.8 mAP on Market-1501 and 49.6 mAP on DukeMTMC-reID respectively, which outperform most state-of-the-art models in fully unsupervised Re-ID task.

Learning discriminative features for facial expression recognition (FER) in the wild is a challenging task due to the significant intra-class variations, inter-class similarities, and extreme class imbalances. In order to solve these issues, a contrastive-learning-based extra-contrast affinity network (ECAN) method is proposed. The ECAN consists of a feature processing network and two proposed loss functions, namely extra negative supervised contrastive loss (ENSC loss) and multi-view affinity loss (MVA loss). The feature processing network provides current and historical deep features to satisfy the necessary conditions for these loss functions. Specifically, the ENSC loss function simultaneously considers many positive samples and extra negative samples from other minibatches to maximize intra-class similarity and the inter-class separation of deep features, while also automatically turning the attention of the model to majority and minority classes to alleviate the class imbalance issue. The MVA loss function improves upon the center loss function by leveraging additional deep feature groups from other minibatches to dynamically learn more accurate class centers and further enhance the intra-class compactness of deep features. The numerical results obtained using two public wild FER datasets (RAFDB and FER2013) indicate that the proposed method outperforms most state-of-the-art models in FER.