Explore the vast range of titles available.

Session-based recommendation aims to predict the next item based on a user’s limited interactions within a short period. Existing approaches use mainly recurrent neural networks (RNNs) or graph neural networks (GNNs) to model the sequential patterns or the transition relationships between items. However, such models either ignore the over-smoothing issue of GNNs, or directly use cross-entropy loss with a softmax layer for model optimization, which easily results in the over-fitting problem. To tackle the above issues, we propose a self-supervised graph learning with target-adaptive masking (SGL-TM) method. Specifically, we first construct a global graph based on all involved sessions and subsequently capture the self-supervised signals from the global connections between items, which helps supervise the model in generating accurate representations of items in the ongoing session. After that, we calculate the main supervised loss by comparing the ground truth with the predicted scores of items adjusted by our designed target-adaptive masking module. Finally, we combine the main supervised component with the auxiliary self-supervision module to obtain the final loss for optimizing the model parameters. Extensive experimental results from two benchmark datasets, Gowalla and Diginetica, indicate that SGL-TM can outperform state-of-the-art baselines in terms of Recall@20 and MRR@20, especially in short sessions.

This study investigated whether symmetry perception is vulnerable to metacontrast masking and whether such masking selectively disrupts feedback-dependent visual processes. Across four experiments, we employed a metacontrast paradigm with briefly presented targets (20 ms) followed by masks at varying stimulus onset asynchronies (SOAs), manipulating both target–mask configuration and task demands. All experiments produced the classic U-shaped accuracy-by-SOA curve associated with Type B masking, where performance is lowest at intermediate SOAs. Critically, performance at 0 ms SOA varied depending on the perceptual compatibility of the stimuli. In Experiments 1 and 2, the target and mask were spatially complementary and could be perceptually grouped into a unified figure. Under these conditions, performance at 0 ms SOA exceeded the no-mask baseline, reflecting facilitation due to perceptual integration. In contrast, in Experiments 3 and 4—where the stimuli and mask had no complementary shape and could not be integrated into a coherent object—performance at 0 ms SOA was slightly suppressed, indicating that integration failed to occur. These findings suggest that facilitation at short SOAs depends on the rapid formation of a coherent perceptual object, whereas symmetry detection—requiring temporally extended, feedback-supported integration—is more susceptible to early interruption by masking. Together, these results support both dual-channel and recurrent models of visual masking. Type B suppression reflects interactions between fast feedforward and slower feedback signals, while the presence or absence of early facilitation serves as an index of perceptual organization. These findings underscore how stimulus structure and task context affect the temporal dynamics of shape perception.

Ground Penetrating Radar (GPR) is a non-destructive technique used for detecting subsurface structure and space. However, the interpretation of field GPR data is quite labour-intensive and time-consuming. This paper develops a deep learning-based approach for the detection and segmentation of subsurface targets based on GPR data. Since existing deep learning methods do not always accurately reflect the true quality of segmentation masks and exhibit locality when handling details in complex scenes, the proposed method employs the Mask Scoring R-CNN (MS R-CNN) framework as its primary framework and makes additional modifications to its backbone and neck architecture. Experimental results on GPR bridge dataset show notable improvements in loss metrics, segmentation accuracy, and bounding box precision. These enhancements have effectively reduced overall losses and enhanced the performance of Average Precision index of the enhanced MS R-CNN, demonstrating the effectiveness of our approach in the accurate identification of underground objects under complex environments.

Due to the limited number of SAR samples in the dataset, current networks for SAR automatic target recognition (SAR ATR) are prone to overfitting the environmental information, which diminishes their generalization ability under cross-background conditions. However, acquiring sufficient measured data to cover the entire environmental space remains a significant challenge. This paper proposes a novel feature disentanglement network, named FDSANet. The network is designed to decouple and distinguish the features of the target from the background before classification, thereby improving its adaptability to background changes. Specifically, the network consists of two sub-networks. The first is an autoencoder sub-network based on dual-mask-guided slot attention. This sub-network utilizes target mask to guide the encoder to distinguish between target and background features. It then outputs these features as independent representations, respectively, achieving feature disentanglement. The second is a classification sub-network. It includes an encoder and a classifier, which work together to perform the classification based on the extracted target features. This network enhances the causal relationship between the target and the classification result, while mitigating the background’s interference on the classification. Moreover, the network, trained under a fixed background, demonstrates strong adaptability when applied to a new background. Experiments conducted on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset, as well as the OpenSARShip dataset, demonstrate the superior performance of FDSANet.

Facial expression recognition (FER) is significantly influenced by the cultural background (CB) of observers and the masking conditions of the target face. This study aimed to clarify these factors’ impact on FER, particularly in machine-learning datasets, increasingly used in human-computer interaction and automated systems. We conducted an FER experiment with East Asian participants and compared the results with the FERPlus dataset, evaluated by Western raters. Our novel analysis approach focused on variability between images and participants within a \"majority\" category and the eye-opening rate of target faces, providing a deeper understanding of FER processes. Notable findings were differences in \"fear\" perception between East Asians and Westerners, with East Asians more likely to interpret \"fear\" as \"surprise.\" Masking conditions significantly affected emotion categorization, with \"fear\" perceived by East Asians for non-masked faces interpreted as \"surprise\" for masked faces. Then, the emotion labels were perceived as different emotions across categories in the masking condition, rather than simply lower recognition rates or confusion as in existing studies. Additionally, \"sadness\" perceived by Westerners was often interpreted as \"disgust\" by East Asians. These results suggest that one-to-one network learning models, commonly trained using majority labels, might overlook important minority response information, potentially leading to biases in automated FER systems. In conclusion, FER dataset characteristics differ depending on the target face’s masking condition and the diversity among evaluation groups. This study highlights the need to consider these factors in machine-learning-based FER that relies on human-judged labels, to contribute to the development of more nuanced and fair automated FER systems. Our findings emphasize the novelty of our approach compared to existing studies and the importance of incorporating a broader range of human variability in FER research, setting the stage for future evaluations of machine learning classifiers on similar data.

Small interfering RNAs (siRNAs) promote RNA degradation in a variety of processes and have important clinical applications. siRNAs direct cleavage of target RNAs by guiding Argonaute2 (AGO2) to its target site. Target site accessibility is critical for AGO2-target interactions, but how target site accessibility is controlled in vivo is poorly understood. Here, we use live-cell single-molecule imaging in human cells to determine rate constants of the AGO2 cleavage cycle in vivo. We find that the rate-limiting step in mRNA cleavage frequently involves unmasking of target sites by translating ribosomes. Target site masking is caused by heterogeneous intramolecular RNA-RNA interactions, which can conceal target sites for many minutes in the absence of translation. Our results uncover how dynamic changes in mRNA structure shape AGO2-target recognition, provide estimates of mRNA folding and unfolding rates in vivo, and provide experimental evidence for the role of mRNA structural dynamics in control of mRNA-protein interactions.Live-cell single-molecule imaging reveals that the rate-limiting step in AGO2-mediated mRNA cleavage frequently involves unmasking of target sites by translating ribosomes.

Multimodal medical images have been widely applied in various clinical diagnoses and treatments. Due to the practical restrictions, certain modalities may be hard to acquire, resulting in incomplete data. Existing methods attempt to generate the missing data with multiple available modalities. However, the modality differences in tissue contrast and lesion appearance become an obstacle to making a precise estimation. To address this issue, we propose an autoencoder-driven multimodal collaborative learning framework for medical image synthesis. The proposed approach takes an autoencoder to comprehensively supervise the synthesis network using the self-representation of target modality, which provides target-modality-specific prior to guide multimodal image fusion. Furthermore, we endow the autoencoder with adversarial learning capabilities by converting its encoder into a pixel-sensitive discriminator capable of both reconstruction and discrimination. To this end, the generative model is completely supervised by the autoencoder. Considering the efficiency of multimodal generation, we also introduce a modality mask vector as the target modality label to guide the synthesis direction, empowering our method to estimate any missing modality with a single model. Extensive experiments on multiple medical image datasets demonstrate the significant generalization capability as well as the superior synthetic quality of the proposed method, compared with other competing methods. The source code will be available: https://github.com/bcaosudo/AE-GAN.

Verifying the identity of an unfamiliar person is a difficult task, especially when targets wear masks that cover most of their faces. This presents a major challenge for law enforcement in border control, security, and criminal investigations. Therefore, we aim to explore ways to improve face-matching performance when a face is heavily masked. In two experiments, we investigated whether face-matching performance can benefit from the presentation of isolated facial features, namely the eyes (Experiment 1) and the mouth (Experiment 2), when a target face is masked. Participants viewed pairs of faces and determined whether they belonged to the same person or different people. In congruent pairs, participants matched a full-face image to another full-face image or a masked image to an isolated facial feature. In incongruent pairs, participants matched a full-face image to an image of the eyes or the mouth only or to a masked image. Matching accuracy was significantly better in congruent than incongruent pairs. Interestingly, the benefit of showing an isolated facial feature was even present when that single feature was the mouth. Overall, the findings showed that focusing on isolated facial features, such as the eyes or mouth, can be a valuable strategy for enhancing identity matching with masked perpetrators.

Visual masking can reveal the timescale of perception, but the underlying circuit mechanisms are not understood. Here we describe a backward masking task in mice and humans in which the location of a stimulus is potently masked. Humans report reduced subjective visibility that tracks behavioral deficits. In mice, both masking and optogenetic silencing of visual cortex (V1) reduce performance over a similar timecourse but have distinct effects on response rates and accuracy. Activity in V1 is consistent with masked behavior when quantified over long, but not short, time windows. A dual accumulator model recapitulates both mouse and human behavior. The model and subjects’ performance imply that the initial spikes in V1 can trigger a correct response, but subsequent V1 activity degrades performance. Supporting this hypothesis, optogenetically suppressing mask-evoked activity in V1 fully restores accurate behavior. Together, these results demonstrate that mice, like humans, are susceptible to masking and that target and mask information is first confounded downstream of V1. The authors introduce a novel visual masking task and use recordings and optogenetics to reveal the role of visual cortex.

YOLO, an important algorithm for target detection, is ineffective in detecting small dynamic targets. In this paper, we utilize background subtraction, which is highly sensitive to dynamic pixels, to provide YOLO with the location and features of small dynamic targets, thus reducing the missed detection rate of small targets. This method uses background subtraction and YOLO to obtain the mask and class of the target, respectively. If the target’s mask and class can be detected, the features of YOLO and Masks data module are constructed or updated using its characteristics and class. Conversely, if only the target mask is obtained, the target mask is introduced into the features of YOLO and Masks data module for similarity detection, so as to determine the target class. Finally, YOLO performs the forced detection of the target based on the coordinates of the mask with the determined class. Validated with the SBMnet dataset, the experimental results show that for dynamic targets with three different line-of-sight distances, the method proposed in this paper improves the precision by 2.3%, recall by 3.5%, and F1-score by 3.1%.