Learning Module Research Articles

Multi-scale multi-instance contrastive learning for whole slide image classification

Multi-instance learning (MIL) has become the mainstream solution for processing super-high resolution whole slide images (WSIs) with the pyramidal structure in digital pathology. Current MIL-based methods usually learn features from WSI at a specific magnification, ignoring the multi-scale information contained in the WSI and the comparative learning of global features. In addition, the lack of instance labeling can lead to weak model supervision, which may compromise the model’s ability to discriminate fine-grained features, ultimately affecting bag-level feature learning. Therefore, we propose a novel multi-scale multi-instance contrastive learning framework to learn more discriminative feature representation across scales for pathological WSI classification. The proposed method begins with a two-stream feature aggregator module, which extracts both bag embeddings and selects the representative instances simultaneously. Following the bag embedding branch, a multi-scale contrastive learning module is designed to learn the global feature comparisons of WSIs across multiple scales by leveraging its inherent pyramid structure. Additionally, based on the instances selection branch, a patch-level classifier is combined with the bag-level classifier to jointly optimize the model training process, enhancing the supervision of the model. The proposed framework is evaluated on three publicly available WSI datasets, achieving an area under the curve of 95.8%, 95.5%, and 88.2%, respectively, consistently outperforming all the compared methods including single- and multi-scale ones.

Multi-view attributed graph clustering based on graph diffusion convolution with adaptive fusion

Graph clustering is one of the popular techniques in data mining, which is widely used in social network analysis, recommendation system and anomaly detection. The existing methods based on multi-view attributed graph ignore the difference of different views and the consistency between views. To this end, this paper proposes a novel method for multi-view attributed graph clustering based on graph diffusion convolution with adaptive fusion. Specifically, a graph diffusion convolution is firstly employed to propagate features of the adjacency and attribute matrices on each view. A linear encoder–decoder is then used to learn the graph embedding representation of each view. Meanwhile, the consistency learning module is applied to capture the geometric relationship consistency of different views for finding a consistent embedding space during the embedding representation learning. To measure the importance of different views, the attention mechanism is subsequently utilized to adaptively learn the weights of different views to fuse multiple views of data for the final clustering. Finally, the graph representation learning and clustering tasks are jointly optimized to obtain a clustering friendly graph representation. Experiments conducted on two public datasets and three real futures datasets from the Zhengzhou Commodity Exchange demonstrate the effectiveness of the proposed method in the task of graph clustering.

Development of Research-Based Science Literacy Learning at State Madrasah Aliyah in Banda Aceh City

The development of research-based learning modules is crucial for enhancing students' scientific literacy, particularly in the context of Islamic educational institutions. This study addresses the need for a validated and practical science literacy module for Physics instruction at State Madrasah Aliyah (Islamic high schools) in Banda Aceh City. This research employed a development research approach using the ADDIE model (Analysis, Design, Development, Implementation, and Evaluation) to design and validate the learning module. The module underwent a three-stage validation process, including the initial module validity test, a second validation focusing on the content material, and a third test assessing the module’s practicality in classroom use. The findings indicate that the module passed through all three stages of testing with positive results. The module validity, content validity, and practicality were all rated as highly valid by respective validators, including module development experts, content specialists, and practicality assessors. The results suggest that the research-based science literacy module is not only valid in terms of content and structure but also practical for use in Physics instruction. The feedback from validators demonstrates that the module is effective and suitable for teaching purposes. The developed module is highly valid and practical for Physics instruction at State Madrasah Aliyah in Banda Aceh. It is feasible for implementation by Physics teachers to enhance students' scientific literacy in line with the research objectives.

Engaging Interprofessional Health Students in a Prescription Produce Plan.

Nursing students participated in an interprofessional student-led prescription produce program (PPP) serving low-income older adults attending a community-based wellness and care coordination program. Students engaged in an online training module covering nutrition education and health promotion, integral components of a PPP. Ninety-five percent of students self-rated themselves as somewhat confident/very confident to participate in the PPP after completing an online learning module. Further investigation is needed on integrating students from diverse health professions to address the multifaceted factors related to nutrition and other social determinants of health affecting the management of chronic diseases.

G[formula omitted]BFNN: Generalized geodesic basis function neural network

Real-world data is typically distributed on low-dimensional manifolds embedded in high-dimensional Euclidean spaces. Accurately extracting spatial distribution features on general manifolds that reflect the intrinsic characteristics of data is crucial for effective feature representation. Therefore, we propose a generalized geodesic basis function neural network (G2BFNN) architecture. The generalized geodesic basis functions (G2BF) are defined based on generalized geodesic distances. The generalized geodesic distance metric (G2DM) is obtained by learning the manifold structure. To implement this architecture, a specific G2BFNN, named discriminative local preserving projection-based G2BFNN (DLPP-G2BFNN) is proposed. DLPP-G2BFNN mainly contains two modules, namely the manifold structure learning module (MSLM) and the network mapping module (NMM). In the MSLM module, a supervised adjacency graph matrix is constructed to constrain the learning of the manifold structure. This enables the learned features in the embedding subspace to maintain the manifold structure while enhancing the discriminability. The features and G2DM learned in the MSLM are fed into the NMM. Through the G2BF in the NMM, the spatial distribution features on manifold are obtained. Finally, the output of the network is obtained through the fully connected layer. Compared with the local response neural network based on Euclidean distance, the proposed network can reveal more essential spatial structure characteristics of the data. Meanwhile, the proposed G2BFNN is a generalized network architecture that can be combined with any manifold learning method, showcasing high scalability. The experimental results demonstrate that the proposed DLPP-G2BFNN outperforms existing methods by utilizing fewer kernels while achieving higher recognition performance.

The use of an online learning module to improve knowledge for prevention of back pain and injury in industrial workers.

Back pain is a significant public health problem that accounts for a high percentage of morbidity and disability worldwide. Low back pain is a frequent cause of missed workdays and job-specific disability and is associated with poor outcomes for employees and employers. An online learning module that focused on normal anatomy of the spine, common pathophysiologic diagnosis or findings that may contribute to back pain, and techniques for back pain reduction was created for employees at risk due to the nature of their labor-intensive jobs. This module also contained case studies and graphics that demonstrated ways to reduce risks or hazards by incorporating job-specific changes in the work environment. A mixed method statistical analysis of knowledge change was completed after participation in the online module. This demonstrated that participants had a marked increase in knowledge in all areas examined. In addition, participants perceived the module as beneficial for grasping anatomical concepts, understanding injury prevention and management strategies, valuing the shared information, leveraging visual aids, and applying practical examples per qualitative questions answered. Participants gained knowledge that can be used on the job to decrease risk of sustaining back pain or injury. The intervention approach enhances the understanding of back pain among industrial workers and holds profound implications for public health on a broader scale. Monitoring population health and preventing back pain and injury while at work is essential for safety and is also a core competency in public health.

AFSC: A self-supervised augmentation-free spatial clustering method based on contrastive learning for identifying spatial domains

Recent research in spatial transcriptomics allows researchers to analyze gene expression without losing spatial information. Spatial information can assist in cell communication, identification of new cell subtypes, which provides important research methods for multiple fields such as microenvironment interactions and pathological processes of diseases. Identifying spatial domains is an important step in spatial transcriptomics analysis, and improving spatial clustering methods can benefit for identifying spatial domains. In addition to eliminating noise in original gene expression, how to use spatial information to assist clustering has also become a new problem. A variety of calculating methods have been applied to spatial clustering, including contrastive learning methods. However, existing spatial clustering methods based on contrastive learning use data augmentation to generate positive and negative pairs, which will inevitably destroy the biological meaning of the data. We propose a new self-supervised spatial clustering method based on contrastive learning, Augmentation-Free Spatial Clustering (AFSC), which integrates spatial information and gene expression to learn latent representations. We construct a contrastive learning module without negative pairs or data augmentation by designing Teacher and Student Encoder. We also design an unsupervised clustering module to make clustering and contrastive learning be trained together. Experiments on multiple spatial transcriptomics datasets at different resolutions demonstrate that our method performs well in self-supervised spatial clustering tasks. Furthermore, the learned representations can be used for various downstream tasks including visualization and trajectory inference.

Bidirectional consistency with temporal-aware for semi-supervised time series classification

Semi-supervised learning (SSL) has achieved significant success due to its capacity to alleviate annotation dependencies. Most existing SSL methods utilize pseudo-labeling to propagate useful supervised information for training unlabeled data. However, these methods ignore learning temporal representations, making it challenging to obtain a well-separable feature space for modeling explicit class boundaries. In this work, we propose a semi-supervised Time Series classification framework via Bidirectional Consistency with Temporal-aware (TS-BCT), which regularizes the feature space distribution by learning temporal representations through pseudo-label-guided contrastive learning. Specifically, TS-BCT utilizes time-specific augmentation to transform the entire raw time series into two distinct views, avoiding sampling bias. The pseudo-labels for each view, generated through confidence estimation in the feature space, are then employed to propagate class-related information into unlabeled samples. Subsequently, we introduce a temporal-aware contrastive learning module that learns discriminative temporal-invariant representations. Finally, we design a bidirectional consistency strategy by incorporating pseudo-labels from two distinct views into temporal-aware contrastive learning to construct a class-related contrastive pattern. This strategy enables the model to learn well-separated feature spaces, making class boundaries more discriminative. Extensive experimental results on real-world datasets demonstrate the effectiveness of TS-BCT compared to baselines.

PKM PUSKESMAS CURUGBITUNG: PENINGKATAN KUALITAS TUMBUH KEMBANG ANAK USIA DINI BERBASIS WEBSITE UNTUK MENDUKUNG PENCAPAIAN SDGS POIN 4

Lebak Regency has the second-highest prevalence of stunted toddlers in Banten, at 27.3%. The causes are not only malnutrition among pregnant women and toddlers but also a lack of maternal understanding of parenting practices that support the development of early childhood (0-6 years). Child development encompasses physical, cognitive, social, and emotional changes from birth to adulthood. At the Curugbitung Public Health Center (Puskesmas), midwives have not been equipped with comprehensive knowledge about child development, such as the Stimulation, Detection, and Early Intervention of Child Development (SDIDTK) program from the Indonesian Ministry of Health. The focus of midwives has remained limited to the 'Growth' aspect, such as height and weight, without considering the 'Development' aspect, which includes cognitive, social, emotional, and language development. Additionally, midwives are unable to provide age-appropriate developmental stimulation due to limited knowledge, time, and facilities. The solution offered by the Community Service team (PKM) from the International Relations Study Program of Universitas Budi Luhur is training to improve the quality of early childhood development based on a website to support the achievement of SDGs goal 4. This training aims to enhance midwives' knowledge and skills in early childhood care and development, with a holistic and integrative website-based learning module. This module facilitates midwives in providing counseling to parents, thereby improving the quality of early childhood education. The outcome of this activity is an increase in knowledge, skills, and the quality of health services, as well as the transfer of knowledge and technology to the community of Curugbitung, Lebak, Banten.

Multi-timescale attention residual shrinkage network with adaptive global-local denoising for rolling-bearing fault diagnosis

In actual engineering scenarios, bearing fault signals are inevitably overwhelmed by strong background noise from various sources. However, most deep-learning-based diagnostic models tend to broaden the feature extraction scale to extract rich fault features for bearing-fault identification under noise interference, with little attention paid to multi-timescale discriminative feature mining with adaptive noise rejection, which affects the diagnostic performance. Thus, a multi-timescale attention residual shrinkage network with adaptive global-local denoising (AMARSN) was proposed for rolling-bearing fault diagnosis by learning discriminative multi-timescale fault features from signals and fully eliminating noise components in the multi-timescale fault features. First, a multi-timescale attention learning module (MALMod) was developed to capture multi-timescale fault features and enhance their discriminability under noise interference. Subsequently, an adaptive global-local denoising module (AGDMod) was constructed to fully eliminate noise in multiscale fault features by constructing specific global-local denoising thresholds and designing an adaptive smooth soft thresholding function. Finally, end-to-end bearing fault diagnosis tasks were realized using a softmax classifier located at the end of the AMARSN. The AMARSN was validated using two bearing datasets. The extensive results demonstrated that the AMARSN can mine more effective fault features from signals and achieve average diagnostic accuracies of 85.24% and 80.09% under different noise with different levels.

Monoaminergic Modulation of Learning and Cognitive Function in the Prefrontal Cortex.

Extensive research has shed light on the cellular and functional underpinnings of higher cognition as influenced by the prefrontal cortex. Neurotransmitters act as key regulatory molecules within the PFC to assist with synchronizing cognitive state and arousal levels. The monoamine family of neurotransmitters, including dopamine, serotonin, and norepinephrine, play multifaceted roles in the cognitive processes behind learning and memory. The present review explores the organization and signaling patterns of monoamines within the PFC, as well as elucidates the numerous roles played by monoamines in learning and higher cognitive function.

Using in situ research-based design to explore learning module effectiveness and usability in a virtual reality system for workforce training

This study examines the implementation and effectiveness of Virtual Reality (VR) into employee communication training for Texas Department of Transportation employees. The study also explores the impact of iterative, in situ research-based design on VR system usability, and potential relationships between the usability and ergonomics of VR devices, and user receptiveness to VR content. For this work we adapt the definition of in situ to mean a learning activity that takes place in the location or environment where the participants will actually be trained. Following the pandemic, many office-based workers adopted hybrid-remote work formats (Yang, Kim, & Hong, 2023), necessitating updated approaches to employee training and instruction which VR may provide. Further, VR may offer opportunities for private role-play for employee communication practice, as well as an overall more high-fidelity learning opportunity. Findings indicate that VR is an effective and engaging solution for workforce and management communication training, and that hardware configurations influence overall employee enthusiasm for VR-based training.

Contextual visual and motion salient fusion framework for action recognition in dark environments

Infrared (IR) human action recognition (AR) exhibits resilience against shifting illumination conditions, changes in appearance, and shadows. It has valuable applications in numerous areas of future sustainable and smart cities including robotics, intelligent systems, security, and transportation. However, current IR-based recognition approaches predominantly concentrate on spatial or local temporal information and often overlook the potential value of global temporal patterns. This oversight can lead to incomplete representations of body part movements and prevent accurate optimization of a network. Therefore, a contextual-motion coalescence network (CMCNet) is proposed that operates in a streamlined and end-to-end manner for robust action representation in darkness in a near-infrared (NIR) setting. Initially, data are preprocessed to separate foreground, normalized, and resized. The framework employs two parallel modules: the contextual visual features learning module (CVFLM) for local feature extraction, and the temporal optical flow learning module (TOFLM) for acquiring motion dynamics. These modules focus on action-relevant regions used shift window-based operations to ensure accurate interpretation of motion information. The coalescence block harmoniously integrates the contextual and motion features within a unified framework. Finally, the temporal decoder module discriminatively identifies the boundaries of the action sequence. This sequence of steps ensures the synergistic optimization of both CVFLM and TOFLM and thorough competent feature extraction for precise AR. Evaluations of CMCNet are carried out on publicly available datasets, InfAR and NTURGB-D, where superior performance is achieved. Our model yields the highest average precision of 89% and 85% on these datasets, respectively, representing an improvement of 2.25% (on InfAR) compared to conventional methods operating at spatial and optical flow levels which underscores its efficacy.

A nonlinear structural pulse-like seismic response prediction method based on pulse-like identification and decomposition learning

Abstract Accurate prediction of structural responses under seismic action is important for the performance evaluation of structures. However, depending on the differences in the characteristics of ground motions, particularly whether they contain impulses, the seismic-response characteristics of structures may differ significantly. Hence, a new method, i.e., WD–AttDL, is proposed in this study to predict structural response under pulse-like ground motions. This method innovatively combines a wavelet decomposition-based velocity pulse-identification method with decomposition learning, where decomposed pulses and high-frequency features are used as inputs to the neural-network model, thus simplifying the identification of pulse features for the model. The decomposition learning module integrates different types of submodules, such as CNN feature-extraction, LSTM temporal-learning, and self-attention mechanism submodules. To reduce the nonlinear time-range analysis calculations required to generate training data, a screening method for impulsive ground motions based on time-series feature clustering is proposed. The accuracy and applicability of the proposed method are verified by numerically simulating three different cycles of reinforced-concrete frame structures and a three-dimensional masonry structure. Compared with existing structural seismic-response models, WD–AttDL synergistically integrates different modules and thus offers a higher prediction accuracy. In particular, it reduces the peak error of the predicted response, which is important for the evaluation of structural performance. Additionally, based on the response predicted by WD–AttDL, a vulnerability analysis of the structure under pulse-like seismic effects can be performed rapidly and accurately.

Radiogenomics based survival prediction of small-sample glioblastoma patients by multi-task DFFSP model.

In this paper, the multi-task dense-feature-fusion survival prediction (DFFSP) model is proposed to predict the three-year survival for glioblastoma (GBM) patients based on radiogenomics data. The contrast-enhanced T1-weighted (T1w) image, T2-weighted (T2w) image and copy number variation (CNV) is used as the input of the three branches of the DFFSP model. This model uses two image extraction modules consisting of residual blocks and one dense feature fusion module to make multi-scale fusion of T1w and T2w image features as backbone. Also, a gene feature extraction module is used to adaptively weight CNV fragments. Besides, a transfer learning module is introduced to solve the small sample problem and an image reconstruction module is adopted to make the model anatomy-aware under a multi-task framework. 256 sample pairs (T1w and corresponding T2w MRI slices) and 187 CNVs of 74 patients were used. The experimental results show that the proposed model can predict the three-year survival of GBM patients with the accuracy of 89.1 %, which is improved by 3.2 and 4.7 % compared with the model without genes and the model using last fusion strategy, respectively. This model could also classify the patients into high-risk and low-risk groups, which will effectively assist doctors in diagnosing GBM patients.

Noise-imitation learning: unpaired speckle noise reduction for optical coherence tomography

Objective.Optical coherence tomography (OCT) is widely used in clinical practice for its non-invasive, high-resolution imaging capabilities. However, speckle noise inherent to its low coherence principle can degrade image quality and compromise diagnostic accuracy. While deep learning methods have shown promise in reducing speckle noise, obtaining well-registered image pairs remains challenging, leading to the development of unpaired methods. Despite their potential, existing unpaired methods suffer from redundancy in network structures or interaction mechanisms. Therefore, a more streamlined method for unpaired OCT denoising is essential.Approach.In this work, we propose a novel unpaired method for OCT image denoising, referred to as noise-imitation learning (NIL). NIL comprises three primary modules: the noise extraction module, which extracts noise features by denoising noisy images; the noise imitation module, which synthesizes noisy images and generates fake clean images; and the adversarial learning module, which differentiates between real and fake clean images through adversarial training. The complexity of NIL is significantly lower than that of previous unpaired methods, utilizing only one generator and one discriminator for training.Main results.By efficiently fusing unpaired images and employing adversarial training, NIL can extract more speckle noise information to enhance denoising performance. Building on NIL, we propose an OCT image denoising pipeline, NIL-NAFNet. This pipeline achieved PSNR, SSIM, and RMSE values of 31.27 dB, 0.865, and 7.00, respectively, on the PKU37 dataset. Extensive experiments suggest that our method outperforms state-of-the-art unpaired methods both qualitatively and quantitatively.Significance.These findings indicate that the proposed NIL is a simple yet effective method for unpaired OCT speckle noise reduction. The OCT denoising pipeline based on NIL demonstrates exceptional performance and efficiency. By addressing speckle noise without requiring well-registered image pairs, this method can enhance image quality and diagnostic accuracy in clinical practice.

SleepGCN: A transition rule learning model based on Graph Convolutional Network for sleep staging

Background and Objective:Automatic sleep staging is essential for assessing and diagnosing sleep disorders, serving millions of people who suffer from them. Numerous sleep staging models have been proposed recently, but most of them have not fully explored the sleep transition rules that are essential for sleep experts to identify sleep stages. Therefore, one objective of this paper is to develop an automatic sleep staging model to capture the transition rules between sleep stages. Methods:In this paper, we propose a novel sleep staging model named SleepGCN. It utilizes the deep features of electroencephalogram (EEG) and electrooculogram (EOG) signals extracted by the sleep representation learning (SRL) module, in conjunction with the transition rules learned by the sleep transition rule learning (STRL) module to identify sleep stages. Specifically, the SRL module utilizes the residual network (ResNet) and Long Short Term Memory (LSTM) structure to capture the deep time-invariant features and temporal information of each sleep stage from the two-channel EEG-EOG, and then applies a feature enhancement block to obtain the refined features. The STRL module employs a Graph Convolutional Network (GCN) and a transition rule matrix to capture transition rules between sleep stages based on the sequence labels of the input signals. Results:We evaluate SleepGCN on five public datasets: SleepEDF-20, SleepEDF-78, SHHS, DOD-H and DOD-O. Overall, SleepGCN achieves an accuracy of 89.70%, 87.70%, 86.16%, 82.07%, and 81.20%, alongside a macro-average F1-score of 85.20%, 82.70%, 77.69%, 72.44%, and 72.93% across these datasets, respectively. Conclusions:The results achieved by our proposed model are much better than those of all other compared models. The ablation study validates the contributions of the SRL and STRL modules proposed in SleepGCN to the sleep staging tasks. Additionally, it shows that the sleep staging model using two-channel EEG-EOG outperforms the model using single-channel EEG or EOG. Overall, SleepGCN is an effective solution for sleep staging using two-channel EEG-EOG.

Meningkatkan kemampuan pemecahan masalah matematis siswa: Pengembangan modul pembelajaran berbasis studi etnomatematika pada budidaya tanaman hidroponik

This study aims to develop an ethnomathematical study-based learning module on hydroponic plant cultivation to improve the mathematical problem-solving ability of class VII junior high school students on social arithmetic material that meets the criteria of validity and effectiveness. This research method is research and development with the ADDIE model (analysis, design, development, implementation, evaluation). Data collection instruments include interviews, validation sheets, questionnaires, and pre-test and post-test questions. The data were analyzed using qualitative and quantitative data analysis techniques. The results showed that ethnomathematics research-based learning modules were considered effective and feasible, with a percentage of 90% results verified by material and ethnomathematics experts, 96% by media experts, 90% teacher assessments, and a pass rate of group examination assessments of 87.3%, and a pass rate of on-site examination evaluations of 88.61%. The modules developed are also claimed to be effective in improving students' mathematical solving skills, with the experimental class having an average N-gain score of 0.78 in the "very high" category, better than the control class with an average N-gain score of 0.32 in the "medium" category. Both data were tested using a two-sample t-test and obtained 0.00 results less than 0.05 then H0 was rejected and H1 was accepted.

Maximum Local Density-Driven Non-overlapping Radial Basis Function Support Kernel Neural Network

The learning and optimization of kernels in the radial basis function neural network (RBFNN) are crucial. However, in existing methods, there are issues of overfitting when learning kernel parameters. The learned kernels are also sensitive to outliers. This paper proposes a general kernel learning strategy for RBFNN called non-overlapping maximum local density support kernel learning (MLD-SKL), which contains two modules, the non-overlapping maximum local density (MLD) kernel learning module and support kernel learning (SKL) module. In the MLD kernel learning stage, the candidate set of kernels is incrementally determined based on the local density of samples. Meanwhile, it is required that the coverage ranges of kernels from different classes do not overlap with each other. This module is effective in reducing the impact of outliers. In the SKL stage, kernel importance indicator is defined to measure the importance of kernels. The learned support kernels are utilized to construct a maximum local density-driven non-overlapping radial basis function support kernel neural network (MLD-RBFSKNN). The RBFNN constructed through MLD-SKL exhibits a more compact structure. The experiments demonstrate that the proposed MLD-RBFSKNN improves accuracy in recognition task. Furthermore, while achieving superior recognition performance, the final constructed network also has the minimum number of kernels.

MLP-AIR: An effective MLP-based module for actor interaction relation learning in group activity recognition

Modeling actor interaction relations is crucial for group activity recognition. Previous approaches often adopt a fixed paradigm that involves calculating an affinity matrix to model these interaction relations, yielding significant performance. On the one hand, the affinity matrix introduces an inductive bias that actor interaction relations should be dynamically computed based on the input actor features. On the other hand, MLPs with static parameterization, in which parameters are fixed after training, can represent arbitrary functions. Therefore, it is an open question whether inductive bias is necessary for modeling actor interaction relations. To explore the impact of this inductive bias, we propose an affinity matrix-free paradigm that directly uses the MLP with static parameterization to model actor interaction relations. We term this approach MLP-AIR. This paradigm overcomes the limitations of the inductive bias and enhances the capture of implicit actor interaction relations. Specifically, MLP-AIR consists of two sub-modules: the MLP-based Interaction relation modeling module (MLP-I) and the MLP-based Relation refining module (MLP-R). MLP-I is used to model the spatial–temporal interaction relations by emphasizing cross-actor and cross-frame feature learning. Meanwhile, MLP-R is used to refine the relation between different channels of each relation feature, thereby enhancing the expression ability of the features. MLP-AIR is a plug-and-play module. To evaluate our module, we applied MLP-AIR to replicate three representative methods. We conducted extensive experiments on two widely used benchmarks—the Volleyball and Collective Activity datasets. The experiments demonstrate that MLP-AIR achieves favorable results. The code is available at https://github.com/Xuguoliang12/MLP-AIR.