Anomaly detection on attributed networks has received an increasing amount of attention in recent years. Despite the success, most of the existing methods only focus on detecting the abnormal nodes while fail to detect the abnormal subgraphs. In this paper, we define a new problem of hybrid-order anomaly detection on attributed networks, which aims to detect both of the abnormal nodes and subgraphs. To this end, a new deep learning model called Hybrid-Order Graph Attention Network (HO-GAT) is developed, which is able to simultaneously detect the abnormal nodes and motif instances in an attributed network. In order to model the mutual influence between nodes and motif instances, the learning procedures of the node representation and the motif instance representation are integrated into a unified graph attention network with a novel hybrid-order self-attention mechanism. After learning the node representation and the motif instance representation, two decoders are respectively designed to reconstruct the attribute information of the nodes and motif instances, and the hybrid-order topological structure among nodes and motif instances. And finally, the reconstruction errors are utilized as the abnormal score of nodes and motif instances respectively. Extensive experiments conducted on real-world datasets have confirmed the effectiveness of the HO-GAT method.

In precision dairy farming, computer vision-based approaches have been widely employed to monitor the cattle conditions (e.g., the physical, physiology, health and welfare). To this end, the accurate and effective identification of individual cow is a prerequisite. In this paper, a deep learning re-identification network model, Global and Part Network (GPN), is proposed to identify individual cow face. The GPN model, with ResNet50 as backbone network to generate a pooling of feature maps, builds three branch modules (Middle branch, Global branch and Part branch) to learn more discriminative and robust feature representation from the maps. Specifically, the Middle branch and the Global branch separately extract the global features of middle dimension and high dimension from the maps, and the Part branch extracts the local features in the unified block, all of which are integrated to act as the feature representation for cow face re-identification. By performing such strategies, the GPN model not only extracts the discriminative global and local features, but also learns the subtle differences among different cow faces. To further improve the performance of the proposed framework, a Global and Part Network with Spatial Transform (GPN-ST) model is also developed to incorporate an attention mechanism module in the Part branch. Additionally, to test the efficiency of the proposed approach, a large-scale cow face dataset is constructed, which contains 130,000 images with 3000 cows under different conditions (e.g., occlusion, change of viewpoints and illumination, blur, and background clutters). The results of various contrast experiments show that the GPN outperforms the representative re-identification methods, and the improved GPN-ST model has a higher accuracy rate (up by 2.8% and 2.2% respectively) in Rank-1 and mAP, compared with the GPN model. In conclusion, using the Global and Part feature deep network with attention mechanism can effectively ameliorate the efficiency of cow face re-identification.

Domain shift poses a significant challenge in Cross-Domain Facial Expression Recognition (CD-FER) due to the distribution variation between the source and target domains. Current algorithms mainly focus on learning domain-invariant features through global feature adaptation, while neglecting the transferability of local features across different domains. Additionally, these algorithms lack discriminative supervision during training on target datasets, resulting in deteriorated feature representation in the target domain. To address these limitations, we propose an Adaptive Global-Local Representation Learning and Selection (AGLRLS) framework. The framework incorporates global-local adversarial adaptation and semantic-aware pseudo label generation to enhance the learning of domain-invariant and discriminative feature representation during training. Meanwhile, a global-local prediction consistency learning is introduced to improve classification results during inference. Specifically, the framework consists of separate global-local adversarial learning modules that learn domain-invariant global and local features independently. We also design a semantic-aware pseudo label generation module, which computes semantic labels based on global and local features. Moreover, a novel dynamic threshold strategy is employed to learn the optimal thresholds by leveraging independent prediction of global and local features, ensuring filtering out the unreliable pseudo labels while retaining reliable ones. These labels are utilized for model optimization through the adversarial learning process in an end-to-end manner. During inference, a global-local prediction consistency module is developed to automatically learn an optimal result from multiple predictions. To validate the effectiveness of our framework, we conduct comprehensive experiments and analysis based on a fair evaluation benchmark. The results demonstrate that the proposed framework outperforms the current competing methods by a substantial margin.

Recently, Deep Neural Networks (DNNs) have been largely utilized in Collaborative Filtering (CF) to produce more accurate recommendation results due to their ability of extracting the nonlinear relationships in the user-item pairs. However, the DNNs-based models usually encounter high computational complexity, i.e., consuming very long training time and storing huge amount of trainable parameters. To address these problems, we develop a novel broad recommender system named Broad Collaborative Filtering (BroadCF), which is an efficient nonlinear collaborative filtering approach. Instead of DNNs, Broad Learning System (BLS) is used as a mapping function to learn the nonlinear matching relationships in the user-item pairs, which can avoid the above issues while achieving very satisfactory rating prediction performance. Contrary to DNNs, BLS is a shallow network that captures nonlinear relationships between input features simply and efficiently. However, directly feeding the original rating data into BLS is not suitable due to the very large dimensionality of the original rating vector. To this end, a new preprocessing procedure is designed to generate user-item rating collaborative vector, which is a low-dimensional user-item input vector that can leverage quality judgments of the most similar users/items. Convincing experimental results on seven datasets have demonstrated the effectiveness of the BroadCF algorithm.

Cross-Domain Facial Expression Recognition (CD-FER) aims to develop a facial expression recognition model that can be trained in one domain and deliver consistent performance in another. CD-FER poses a significant challenges due to changes in marginal and class distributions between source and target domains. Existing methods primarily emphasize achieving domain-invariant features through global feature adaptation, often neglecting the potential benefits of transferable local features across different domains. To address this issue, we propose a novel framework for CD-FER that combines reliable global–local representation learning and dynamic label weighting. Our framework incorporates two key modules: the Pseudo-Complementary Label Generation (PCLG) module, which leverages pseudo-labels and complementary labels obtained using a credibility threshold to learn domain-invariant global and local features, and the Label Dynamic Weight Matching (LDWM) module, which assesses the learning difficulty of each category and adaptively assigns corresponding label weights, thereby enhancing the classification performance in the target domain. We evaluate our approach through extensive experiments and analyses on multiple public datasets, including RAF-DB, FER2013, CK+, JAFFE, SFW2.0, and ExpW. The experimental results demonstrate that our proposed model outperforms state-of-the-art methods, with an average accuracy improvement of 3.5% across the five datasets.

Broiler weighing is essential in the broiler farming industry. Camera-based systems can economically weigh various broiler types without expensive platforms. However, existing computer vision methods for weight estimation are less mature, as they focus on young broilers. In effect, the estimation error increases with the age of the broiler. To tackle this, this paper presents a novel framework. First, it employs Mask R-CNN for instance segmentation of depth images captured by 3D cameras. Next, once the images of either a single broiler or multiple broilers are segmented, the extended artificial features and the learned features extracted by Customized Resnet50 (C-Resnet50) are fused by a feature fusion module. Finally, the fused features are adopted to estimate the body weight of each broiler employing gradient boosting decision tree (GBDT). By integrating diverse features with GBTD, the proposed framework can effectively obtain the broiler instance among many depth images of multiple broilers in the visual field despite the complex background. Experimental results show that this framework significantly boosts accuracy and robustness. With an MAE of 0.093 kg and an R² of 0.707 in a test set of 240 63-day-old bantam chicken images, it outperforms other methods.