Xin Li

Visible-infrared person re-identification faces great challenges due to the inherent cross-modality discrepancy. The key of reducing the discrepancy is to filter out the interference of modality information and project the pedestrian features in the two modalities into a shared feature space. However, previous works mainly focus on the application of high-level information, and pay less attention to the middle-level features exploration. This limits the accuracy and generalization ability of cross-modality recognition. To address this shortcoming, we propose a novel Fine-grained Semantic Representation Learning (FSRL) network to explore the identity information in middle-level features for VI-ReID task. Specifically, we first propose a plug-and-play modality normalization and compensation (MNC) module, which reduces the modality discrepancy, while compensating the missing identity information caused by modal elimination. Second, we propose an intermediate feature aggregation (IFA) module to obtain rich fine-grained identity information in the middle layer, which guides the model to accurately extract more identity-related features for recognition. Finally, we also introduce the semantic-aligned feature learning (SAFL) module to further extract potential semantic part features from the feature map shared by the modalities to achieve cross-modality semantic alignment. Extensive experiments on the SYSU-MM01, RegDB and LLCM datasets demonstrate the effectiveness and superiority of our proposed method.

Existing person re-identification methods utilizing CLIP (Contrastive Language-Image Pre-training) mostly suffer from coarse-grained alignment issues. This is primarily due to the original design intention of the CLIP model, which aims at broad and global alignment between images and texts to support a wide range of image–text matching tasks. However, in the specific domain of person re-identification, local features and fine-grained information are equally important in addition to global features. This paper proposes an innovative modal fusion approach, aiming to precisely locate the most prominent pedestrian information in images by combining visual features extracted by the ResNet-50 model with text representations generated by a text encoder. This method leverages the cross-attention mechanism of the Transformer Decoder to enable text features to dynamically guide visual features, enhancing the ability to identify and locate the target pedestrian. Experiments conducted on four public datasets, namely MSMT17, Market1501, DukeMTMC, and Occluded-Duke, demonstrate that our method outperforms the baseline network by 5.4%, 2.7%, 2.6%, and 9.2% in mAP, and by 4.3%, 1.7%, 2.7%, and 11.8% in Rank-1, respectively. This method exhibits excellent performance and provides new research insights for the task of person re-identification.

For fault diagnosis, it is important to effectively leverage the inherent characteristics of small datasets, but it is rarely considered in many the existing deep learning approaches. To this end, a dual-path network model based on multiple attention mechanisms is proposed in this work. The proposed model enriches the features of small sample by combining one-dimensional (1-D) frequency signals with two-dimensional (2-D) time-frequency images. A 1-D attention mechanism is applied in the 1-D frequency extraction path to focus classification on sensitive frequency information, while an improved global attention mechanism is added to the 2-D feature extraction path, which refines the key features and reduces interference resulting from noise in the image data. Moreover, the stability of the learning process is enhanced through the application of a combinatorial loss function composed of label smoothing regularization and gradient harmonizing mechanism loss functions. Finally, the diagnostic performance of the proposed method is validated using two different public fault diagnosis datasets in comparison with the state-of-the-art methods.

In this paper, an image measurement method using a high-speed imaging system is proposed for the evolution of crystal population sizes during cooling crystallization processes. Firstly, to resist the negative effect from solution stirring and particle motion during crystallization, a U-net network-based image processing method is established to efficiently detect sufficiently clear crystals from the online captured microscopic images. Accordingly, the crystal size distribution model is analyzed in terms of the counted probability densities of these crystal images. Subsequently, a measurement method of size growth rate based on crystal population distribution is proposed to estimate the growth condition. An experimental case on a crystallization process of β-form LGA is used to show the effectiveness of the proposed strategy.

To facilitate measuring crystal sizes during batch crystallization at high-solid concentrations by using an invasive imaging system, an in situ imaging measurement strategy based on edge detection and superpixel is proposed for the ambiguous boundary problem of large amounts of crystals. Firstly, an image filtering is employed to cope with image degradation caused by noise disturbance and suspension turbulence in the crystallizer. Subsequently, an image segmentation method is developed by utilizing improved edge detection and superpixel, which can be easily performed for crystal extraction. Accordingly, crystal size measurement can be developed for evaluation of the crystal size distribution. The experiment results on α-form L-glutamic acid present the effectiveness of the proposed method.