Recently, there has been rapid growth in the number of people who own companion pets (cats and dogs) due to low birth rates, an increasingly aging population, and an increasing number of single-person households. This trend has resulted in a growing interest in problems requiring solutions, such as missing pets and false insurance claims. Traditional non-biometric-based methods cannot address these problems. This paper proposes a novel deep-learning model that can extract discriminative features through dog nose-print patterns for individual identification. We present a robust baseline for how individual dogs can be identified. The proposed dog nose network (DNNet) is a convolutional neural network (CNN)-based Siamese network structure comprising feature extraction and self-attention modules. Moreover, there is no need for a separate scanning device because it uses popular mobile devices to acquire the dataset. Besides high recognition performance, the proposed method also ensures simplicity and efficiency. The proposed method achieves better recognition performance than state-of-the-art methods for the collected dog nose-print dataset. It achieves recognition performance superior to state-of-the-art methods for the collected dog nose-print dataset. Using multiple datasets through cross-validation, we acquired an average identification accuracy of 98.972% with the Rank-1 approach. Additional performance benefits were demonstrated through the receiver operating characteristic (ROC) curve, t-distributed stochastic neighbor embedding (t-SNE), and confusion matrix.

Reducing the cross-modality gap between two different domains is a challenging problem for heterogeneous face recognition (HFR). The current visual domain face recognition system is not easy to solve the discrepancy of cross-modality when two comparing domains are heterogeneous. Moreover, the amount of HFR dataset is significantly insufficient, making it considerable difficulty in training. This paper proposes a novel two-step framework that consists of the image translation module and the feature learning module to obtain an enhanced cross-modality matching system for heterogeneous datasets. First, the image translation module consists of a Preprocessing Chain (PC) method, CycleGAN, and the Siamese network. It enables to meet the conditions for preserving contents along with changing the styles from the source domain to the target domain. Second, in the feature learning module, the training dataset and its translated images are used together for fine-tuning the pre-trained backbone model in the visual domain. This allows for discriminative and robust feature matching of the probe and gallery test datasets in the visual domain. The experimental results are evaluated with two scenarios, using the CUHK Face Sketch FERET (CUFSF) dataset and the CASIA NIR-VIS 2.0 dataset. The proposed method achieves a better recognition performance in comparison to the state-of-the-art methods.

The wheels of railway vehicles are of paramount importance in relation to railroad operations and safety. Currently, the management of railway vehicle wheels is restricted to post-event inspections of the wheels whenever physical phenomena, such as abnormal vibrations and noise, occur during the operation of railway vehicles. To address this issue, this paper proposes a method for predicting abnormalities in railway wheels in advance and enhancing the learning and prediction performance of machine learning algorithms. Data were collected during the operation of Line 4 of the Busan Metro in South Korea by directly attaching sensors to the railway vehicles. Through the analysis of key factors in the collected data, factors that can be used for tire condition classification were derived. Additionally, through data distribution analysis and correlation analysis, factors for classifying tire conditions were identified. As a result, it was determined that the z-axis of acceleration has a significant impact, and machine learning techniques such as SVM (Linear Kernel, RBF Kernel) and Random Forest were utilized based on acceleration data to classify tire conditions into in-service and defective states. The SVM (Linear Kernel) yielded the highest recognition rate at 98.70%.

Most facial analysis methods perform well in standardized testing but not in real-world testing. The main reason is that training models cannot easily learn various human features and background noise, especially for facial landmark detection and head pose estimation tasks with limited and noisy training datasets. To alleviate the gap between standardized and real-world testing, we propose a pseudo-labeling technique using a face recognition dataset consisting of various people and background noise. The use of our pseudo-labeled training dataset can help to overcome the lack of diversity among the people in the dataset. Our integrated framework is constructed using complementary multitask learning methods to extract robust features for each task. Furthermore, introducing pseudo-labeling and multitask learning improves the face recognition performance by enabling the learning of pose-invariant features. Our method achieves state-of-the-art (SOTA) or near-SOTA performance on the AFLW2000-3D and BIWI datasets for facial landmark detection and head pose estimation, with competitive face verification performance on the IJB-C test dataset for face recognition. We demonstrate this through a novel testing methodology that categorizes cases as soft, medium, and hard based on the pose values of IJB-C. The proposed method achieves stable performance even when the dataset lacks diverse face identifications.

Video-based person re-identification (ReID) aims to exploit relevant features from spatial and temporal knowledge. Widely used methods include the part- and attention-based approaches for suppressing irrelevant spatial–temporal features. However, it is still challenging to overcome inconsistencies across video frames due to occlusion and imperfect detection. These mismatches make temporal processing ineffective and create an imbalance of crucial spatial information. To address these problems, we propose the Spatiotemporal Multi-Granularity Aggregation (ST-MGA) method, which is specifically designed to accumulate relevant features with spatiotemporally consistent cues. The proposed framework consists of three main stages: extraction, which extracts spatiotemporally consistent partial information; augmentation, which augments the partial information with different granularity levels; and aggregation, which effectively aggregates the augmented spatiotemporal information. We first introduce the consistent part-attention (CPA) module, which extracts spatiotemporally consistent and well-aligned attentive parts. Sub-parts derived from CPA provide temporally consistent semantic information, solving misalignment problems in videos due to occlusion or inaccurate detection, and maximize the efficiency of aggregation through uniform partial information. To enhance the diversity of spatial and temporal cues, we introduce the Multi-Attention Part Augmentation (MA-PA) block, which incorporates fine parts at various granular levels, and the Long-/Short-term Temporal Augmentation (LS-TA) block, designed to capture both long- and short-term temporal relations. Using densely separated part cues, ST-MGA fully exploits and aggregates the spatiotemporal multi-granular patterns by comparing relations between parts and scales. In the experiments, the proposed ST-MGA renders state-of-the-art performance on several video-based ReID benchmarks (i.e., MARS, DukeMTMC-VideoReID, and LS-VID).

The need for stress recognition research is increasing with the increase in the need for proactively managing stress, which greatly impacts overall health. If stress levels can be measured through these stress perception studies, it is thought that the repulsion that stress measurement equipment can give can be minimized, and efficient management can be performed as an auxiliary means of disease management through stress. Although many studies are being conducted on stress recognition using physiological signals, the equipment required to acquire these signals generates additional costs and is inconvenient for the wearer when worn continuously. By contrast, studies using facial images for recognizing stress use noncontact methods. However, these methods have a disadvantage, that is, if a subject does not demonstrate major changes in their facial expressions, recognizing their stress state is difficult. In this study, we propose a stress-recognition method using both facial images and speech to overcome the aforementioned problems. By using speech signals, the problems that occur when using facial images only can be overcome. In the proposed method, the modality models of image and speech are optimized to be suitable for stress recognition. Then, in the network of each modality model, the feature maps of the middle layer are combined with a multimodal neglecting mask module. The two models are efficiently combined by learning the parts to be neglected. The experimental results confirm that the proposed method exhibits the highest performance of 78.1246%, among those exhibited by other reported methods when classifying the stress states into three classes, namely, neutral, low stress, and high stress.