Semi-supervised Counting via Pixel-by-pixel Density Distribution Modelling.

This paper focuses on semi-supervised crowd counting, where only a small portion of the training data are labeled. We formulate the pixel-wise density value to regress as a probability distribution, instead of a single deterministic value. On this basis, we propose a semi-supervised crowd counting model.

Comparative effects of Health Qigong and closed motor exercise on the physical and mental health of female drug rehabilitation participants: a randomized controlled trial.

Background: Drug rehabilitation is a challenging process that impacts both the physical and mental health of individuals. Traditional martial arts, such as Health Qigong, and closed motor exercises, such as power cycling, have shown potential benefits in improving health outcomes. This study aims to compare the effects of Health Qigong, closed motor exercises, and their combination on the physical and mental health of female drug rehabilitation participants.

Knock-knee diagnosis in Chinese adolescents: Expert evaluation and defensive strategies in image analysis - A population study.

Background: Knock-knee, a prevalent postural deformity problem among adolescents, poses significant challenges to traditional diagnostic methods in terms of complexity, high cost, and radiation risk. Therefore, there is a demand for diagnostic techniques that are more accessible, safe, and non-invasive for knock-knee.

Methods: We collected 1519 clear whole-body images from 1689 Chinese adolescents aged 10-19 years as image data, and obtained expert annotations on the presence or absence of knock-knee from three orthopedic surgeons.

Impact of structured exercise interventions on health outcomes in drug rehabilitation patients: a comparative study of open and closed exercises.

Background: This study investigates the effects of open and closed exercise interventions on the physical and mental health of individuals undergoing substance use disorder (SUD). We examined changes in tendency of recurrence of use, vital capacity (VC), resting heart rate (RHR), sleep quality, and choice reaction time.

Methods: Conducted over six months at the drug rehabilitation center, 95 participants were randomly assigned to closed exercise, open exercise, or control group.

Investigating the efficacy of AI-enhanced telerehabilitation in sarcopenic older individuals.

Objective: This study explores the effectiveness of 3D pose estimation technology in Yi Jin Jing (a traditional Chinese exercise) interventions for sarcopenic older individuals.

Design: A randomized controlled trial involving 93 participants (mean age: 71.64 ± 7.

Adversarially trained RTMpose: A high-performance, non-contact method for detecting Genu valgum in adolescents.

Genu valgum (GV), a prevalent postural deformity in adolescents, is traditionally diagnosed using methods that are complex, costly, and accompanied by radiation risks. To address these challenges, we evaluated 1519 Chinese adolescents, collecting GV annotations from three medical professionals to establish a robust dataset. Leveraging these annotations, we developed an end-to-end GV prediction model using RTMpose for body landmark extraction from images.

Improve Noise Tolerance of Robust Loss via Noise-Awareness.

Robust loss minimization is an important strategy for handling robust learning issue on noisy labels. Current approaches for designing robust losses involve the introduction of noise-robust factors, i.e.

Revisiting Nonlocal Self-Similarity from Continuous Representation.

Nonlocal self-similarity (NSS) is an important prior that has been successfully applied in multi-dimensional data processing tasks, e.g., image and video recovery.

Multidimensional Measure Matching for Crowd Counting.

This article addresses the challenge of scale variations in crowd-counting problems from a multidimensional measure-theoretic perspective. We start by formulating crowd counting as a measure-matching problem, based on the assumption that discrete measures can express the scattered ground truth and the predicted density map. In this context, we introduce the Sinkhorn counting loss and extend it to the semi-balanced form, which alleviates the problems including entropic bias, distance destruction, and amount constraints.

Quantum-inspired analysis of neural network vulnerabilities: the role of conjugate variables in system attacks.

Neural networks demonstrate vulnerability to small, non-random perturbations, emerging as adversarial attacks. Such attacks, born from the gradient of the loss function relative to the input, are discerned as input conjugates, revealing a systemic fragility within the network structure. Intriguingly, a mathematical congruence manifests between this mechanism and the quantum physics' uncertainty principle, casting light on a hitherto unanticipated interdisciplinarity.

Proposal and validation of a new approach in tele-rehabilitation with 3D human posture estimation: a randomized controlled trial in older individuals with sarcopenia.

Objective: Through a randomized controlled trial on older adults with sarcopenia, this study compared the training effects of an AI-based remote training group using deep learning-based 3D human pose estimation technology with those of a face-to-face traditional training group and a general remote training group.

Methods: Seventy five older adults with sarcopenia aged 60-75 from community organizations in Changchun city were randomly divided into a face-to-face traditional training group (TRHG), a general remote training group (GTHG), and an AI-based remote training group (AITHG). All groups underwent a 3-month program consisting of 24-form Taichi exercises, with a frequency of 3 sessions per week and each session lasting 40 min.

Causal effect of physical activity and sedentary behavior on the risk of alcohol dependence: A bidirectional two-sample Mendelian randomization study.

Background: Alcohol dependence, influenced by physical activity (PA) and sedentary behavior, lacks clear causal clarity. This study aims to clarify causal relationships by estimating these effects using bidirectional two-sample Mendelian randomization (MR).

Methods: A bidirectional multivariable two-sample MR framework was employed to assess the causal effects of PA and sedentary behavior on alcohol dependence.

Spatial Prior-Guided Bi-Directional Cross-Attention Transformers for Tooth Instance Segmentation.

Tooth instance segmentation of dental panoramic X-ray images is of significant clinical importance. Teeth exhibit symmetry within the upper and lower jawbones and are arranged in a specific order. However, previous studies frequently overlook this crucial spatial prior information, resulting in the misidentifications of tooth categories, especially for adjacent or similarly shaped teeth.

Deep Diversity-Enhanced Feature Representation of Hyperspectral Images.

In this paper, we study the problem of efficiently and effectively embedding the high-dimensional spatio-spectral information of hyperspectral (HS) images, guided by feature diversity. Specifically, based on the theoretical formulation that feature diversity is correlated with the rank of the unfolded kernel matrix, we rectify 3D convolution by modifying its topology to enhance the rank upper-bound. This modification yields a rank-enhanced spatial-spectral symmetrical convolution set (ReS -ConvSet), which not only learns diverse and powerful feature representations but also saves network parameters.

Rotation Equivariant Proximal Operator for Deep Unfolding Methods in Image Restoration.

The deep unfolding approach has attracted significant attention in computer vision tasks, which well connects conventional image processing modeling manners with more recent deep learning techniques. Specifically, by establishing a direct correspondence between algorithm operators at each implementation step and network modules within each layer, one can rationally construct an almost "white box" network architecture with high interpretability. In this architecture, only the predefined component of the proximal operator, known as a proximal network, needs manual configuration, enabling the network to automatically extract intrinsic image priors in a data-driven manner.

De novo and somatic structural variant discovery with SVision-pro.

Long-read-based de novo and somatic structural variant (SV) discovery remains challenging, necessitating genomic comparison between samples. We developed SVision-pro, a neural-network-based instance segmentation framework that represents genome-to-genome-level sequencing differences visually and discovers SV comparatively between genomes without any prerequisite for inference models. SVision-pro outperforms state-of-the-art approaches, in particular, the resolving of complex SVs is improved, with low Mendelian error rates, high sensitivity of low-frequency SVs and reduced false-positive rates compared with SV merging approaches.

Semi-supervised iterative adaptive network for low-dose CT sinogram recovery.

Concern has been expressed regarding the risk of carcinogenesis from medical computed tomography (CT) radiation. Lowering radiation in CT without appropriate modifications often leads to severe noise-induced artifacts in the images. The utilization of deep learning (DL) techniques has achieved promising reconstruction performance in low-dose CT (LDCT) imaging.

Deep Variational Network Toward Blind Image Restoration.

Blind image restoration (IR) is a common yet challenging problem in computer vision. Classical model-based methods and recent deep learning (DL)-based methods represent two different methodologies for this problem, each with their own merits and drawbacks. In this paper, we propose a novel blind image restoration method, aiming to integrate both the advantages of them.

Self-determined sequence exercise program for elderly with sarcopenia: A Randomized controlled trial with clinical assistance from explainable artificial intelligence.

To improve and even reverse sarcopenia in elderly people, this study developed a self-determined sequence exercise program consisting of strength training exercise, Yijinjing exercise (a traditional Chinese exercise), and hybrid strength training with Yijinjing exercise. Ninety-four community-dwelling older adults screened for sarcopenia using the Asian Working Group for Sarcopenia criteria were randomly assigned to 24 weeks of a control group (CG, n = 30), self-determined sequence exercise program group (SDSG, n = 34) or strength training group (STG, n = 30). The study examined the effects of three interventions on participantsL3 skeletal muscle fat density, L3 skeletal muscle fat area, L3 skeletal muscle density, L3 skeletal muscle area, muscle fat infiltration, relative skeletal muscle mass index, and grip strength using a repeated-measures ANOVA to evaluate the experimental data.

Low-Rank Tensor Function Representation for Multi-Dimensional Data Recovery.

Since higher-order tensors are naturally suitable for representing multi-dimensional data in real-world, e.g., color images and videos, low-rank tensor representation has become one of the emerging areas in machine learning and computer vision.

MESPool: Molecular Edge Shrinkage Pooling for hierarchical molecular representation learning and property prediction.

Identifying task-relevant structures is important for molecular property prediction. In a graph neural network (GNN), graph pooling can group nodes and hierarchically represent the molecular graph. However, previous pooling methods either drop out node information or lose the connection of the original graph; therefore, it is difficult to identify continuous subtructures.

Infrared Small and Dim Target Detection With Transformer Under Complex Backgrounds.

The infrared small and dim (S&D) target detection is one of the key techniques in the infrared search and tracking system. Since the local regions similar to infrared S&D targets spread over the whole background, exploring the correlation amongst image features in large-range dependencies to mine the difference between the target and background is crucial for robust detection. However, existing deep learning-based methods are limited by the locality of convolutional neural networks, which impairs the ability to capture large-range dependencies.