Recent advancements in computational techniques significantly impact bioengineering, particularly in drug safety assessments and neuroscience trials using primate models. Macaques are extensively used due to their genetic and physiological similarities to humans. However, there is a scarcity of macaque action recognition datasets and challenges in accurately identifying their actions. To address these limitations, we construct the Macaque-Motion-Monitor (M3) dataset, containing 47,236 action labels across 12 categories, and propose a Motion-Aware Recognition Network (MARN), a novel network specifically designed to handle occlusions and rapid movements. Our method achieves state-of-the-art performance, demonstrating a 5.1% increase in mean Average Precision (mAP) over current high-performing methods when evaluated on the M3, Animal Kingdom and PNPB datasets, establishing a new benchmark for future research. Our data and code will be released in the future.

The development of Neural Architecture Search (NAS) is hindered by high costs associated with evaluating network architectures. Recently, several zero-cost proxies have been proposed as a promising method to reduce the evaluation cost of network architectures in NAS. They can quickly estimate the final performance of the network in a few seconds during the initial phase. However, existing zero-cost proxies either ignore the network structure's impact on performance or are limited to specific tasks. To address these issues, we propose a novel zero-cost proxy called Skeleton Path Kernel Trace (SPKT) that leverages the whole network architecture's skeleton path structure information. We then integrate it into an effective Bayesian optimization for NAS framework called PATNAS, and demonstrate its efficacy on different datasets. The results show that our proposed SPKT zero-cost proxy can achieve a high correlation with the final performance of the network across multiple tasks. Furthermore, it can significantly accelerate the search process for finding the best-performing network architectures.

In the existing spectral GNNs, polynomial-based methods occupy the mainstream in designing a filter through the Laplacian matrix. However, polynomial combinations factored by the Laplacian matrix naturally have limitations in message passing (e.g., over-smoothing). Furthermore, most existing spectral GNNs are based on polynomial bases, which struggle to capture the high-frequency parts of the graph spectral signal. Additionally, we also find that even increasing the polynomial order does not change this situation, which means polynomial-based models have a natural deficiency when facing high-frequency signals. To tackle these problems, we propose WaveNet, which aims to effectively capture the high-frequency part of the graph spectral signal from the perspective of wavelet bases through reconstructing the message propagation matrix. We utilize Multi-Resolution Analysis (MRA) to model this question, and our proposed method can reconstruct arbitrary filters theoretically. We also conduct node classification experiments on real-world graph benchmarks and achieve superior performance on most datasets. Our code is available at https://github.com/Bufordyang/WaveNet

Continuous blood pressure (BP) monitoring holds potential in preventing and detecting cardiovascular disease (CVD). Photoplethysmography (PPG)-based BP measuring systems with noninvasive and continuous properties are of enormous research value in biomedical science. However, mainstream technologies such as Transformer are not viable for implementation in compact devices due to their significant processing complexity. Additionally, the unique individual variability of biosignals limits the generalization performance of the model. In this work, we propose a personalized modeling approach employing a lightweight convolutional neural network(CNN) that streamlines the structure while preserving the model’s ability for long-term predictions. We leverage continuous records from 413 and 30 subjects extracted from MIMIC-III for model pretraining and personalization. The final results demonstrate that, calibrated with only 30 labeled windows for the target subject, the personalized model achieves an estimation error of -0.218±7.657 mmHg for systolic BP (SBP) and -0.261±4.898 mmHg for diastolic BP (DBP). This performance meets the standard requirements of the Association for the Advancement of Medical Instrumentation (AAMI). The lightweight structure and personalized modeling approach improve the accuracy of BP estimation while reducing the difficulty of deployment.

Facial age estimation has attracted considerable attention owing to its great potential in applications. However, it still falls short of reliable age estimation due to the lack of sufficient training data with accurate age labels. Using conventional semi-supervised methods to exploit unlabeled data appears to be a good solution, but it does not yield sufficient performance gains while significantly increasing training time. Therefore, to tackle these problems, we present a Divergence-driven Consistency Training (DCT) method for enhancing both efficiency and performance in this paper. Following the idea of pseudo-labeling and consistency regularization, we assign pseudo labels predicted by the teacher model to unlabeled samples and then train the student model on labeled and unlabeled samples based on consistency regularization. Based on this, we propose two main promotions. The first is the Efficient Sample Selection (ESS) strategy, which is based on the Divergence Score to select effective samples from massive unlabeled images to reduce the training time and improve efficiency. The second is Identity Consistency (IC) regularization as the additional loss function, which introduces a high dependency of aging traits on a person. Moreover, we propose Local Prediction (LP), which is a plug-and-play component, to capture local semantics. Extensive experiments on multiple age benchmark datasets, including CACD, Morph II, MIVIA, and Chalearn LAP 2015, indicate DCT outperforms the state-of-the-art approaches significantly.

Facial age estimation has received a lot of attention for its diverse application scenarios. Most existing studies treat each sample equally and aim to reduce the average estimation error for the entire dataset, which can be summarized as General Age Estimation. However, due to the long-tailed distribution prevalent in the dataset, treating all samples equally will inevitably bias the model toward the head classes (usually the adult with a majority of samples). Driven by this, some works suggest that each class should be treated equally to improve performance in tail classes (with a minority of samples), which can be summarized as Long-tailed Age Estimation. However, Long-tailed Age Estimation usually faces a performance trade-off, i.e., achieving improvement in tail classes by sacrificing the head classes. In this paper, our goal is to design a unified framework to perform well on both tasks, killing two birds with one stone. To this end, we propose a simple, effective, and flexible training paradigm named GLAE, which is two-fold. First, we propose Feature Rearrangement (FR) and Pixel-level Auxiliary learning (PA) for better feature utilization to improve the overall age estimation performance. Second, we propose Adaptive Routing (AR) for selecting the appropriate classifier to improve performance in the tail classes while maintaining the head classes. Moreover, we introduce a new metric, named Class-wise Mean Absolute Error (CMAE), to equally evaluate the performance of all classes. Our GLAE provides a surprising improvement on Morph II, reaching the lowest MAE and CMAE of 1.14 and 1.27 years, respectively. Compared to the previous best method, MAE dropped by up to 34%, which is an unprecedented improvement, and for the first time, MAE is close to 1 year old. Extensive experiments on other age benchmark datasets, including CACD, MIVIA, and Chalearn LAP 2015, also indicate that GLAE outperforms the state-of-the-art approaches significantly.

Sequential recommendation is intended to model the dynamic behavior regularity through users' behavior sequences. Recently, various deep learning techniques are applied to model the relation of items in the sequences. Despite their effectiveness, we argue that the aforementioned methods only consider the macro-structure of the behavior sequence, but neglect the micro-structure in the sequence which is important to sequential recommendation. To address the above limitation, we propose a novel model called Motif-aware Sequential Recommendation (MoSeR), which captures the motifs hidden in behavior sequences to model the micro-structure features. MoSeR extracts the motifs that contain both the last behavior and the target item. These motifs reflect the topological relations among local items in the form of directed graphs. Thus our method can make a more accurate prediction with the awareness of the inherent patterns between local items. Extensive experiments on three benchmark datasets demonstrate that our model outperforms the state-of-the-art sequential recommendation models.

Fluorescence molecular tomography (FMT), as a powerful imaging technique in preclinical research, can offer the three-dimensional distribution of biomarkers by detecting the fluorescently labelled probe noninvasively. However, because of the light scattering effect and the ill-pose of inverse problem, it is challenging to develop an efficient reconstruction method, which can provide accurate location and morphology of the fluorescence distribution. In this research, we proposed a novel adaptive Gaussian weighted Laplace prior (AGWLP) regularization method, which assumed the variance of fluorescence intensity between any two voxels had a non-linear correlation with their Gaussian distance. It utilized an adaptive Gaussian kernel parameter strategy to achieve accurate morphological reconstructions in FMT. To evaluate the performance of the AGWLP method, we conducted numerical simulation and in vivo experiments. The results were compared with fast iterative shrinkage (FIS) thresholding method, split Bregman-resolved TV (SBRTV) regularization method, and Gaussian weighted Laplace prior (GWLP) regularization method. We validated in vivo imaging results against planar fluorescence images of frozen sections. The results demonstrated that the AGWLP method achieved superior performance in both location and shape recovery of fluorescence distribution. This enabled FMT more suitable and practical for in vivo visualization of biomarkers.

Fluorescence molecular tomography (FMT), as a promising imaging modality in preclinical research, can obtain the three-dimensional (3-D) position information of the stem cell in mice. However, because of the ill-posed nature and sensitivity to noise of the inverse problem, it is a challenge to develop a robust reconstruction method, which can accurately locate the stem cells and define the distribution. In this paper, we proposed a sparsity adaptive correntropy matching pursuit (SACMP) method. SACMP method is independent on the noise distribution of measurements and it assigns small weights on severely corrupted entries of data and large weights on clean ones adaptively. These properties make it more suitable for in vivo experiment. To analyze the performance in terms of robustness and practicability of SACMP, we conducted numerical simulation and in vivo mice experiments. The results demonstrated that the SACMP method obtained the highest robustness and accuracy in locating stem cells and depicting stem cell distribution compared with stagewise orthogonal matching pursuit and sparsity adaptive subspace pursuit reconstruction methods. To the best of our knowledge, this is the first study that acquired such accurate and robust FMT distribution reconstruction for stem cell tracking in mice brain. This promotes the application of FMT in locating stem cell and distribution reconstruction in practical mice brain injury models.