Explore the vast range of titles available.

The fields of human activity analysis have recently begun to diversify. Many researchers have taken much interest in developing action recognition or action prediction methods. The research on human action evaluation differs by aiming to design computation models and evaluation approaches for automatically assessing the quality of human actions. This line of study has become popular because of its explosively emerging real-world applications, such as physical rehabilitation, assistive living for elderly people, skill training on self-learning platforms, and sports activity scoring. This paper presents a comprehensive survey of approaches and techniques in action evaluation research, including motion detection and preprocessing using skeleton data, handcrafted feature representation methods, and deep learning-based feature representation methods. The benchmark datasets from this research field and some evaluation criteria employed to validate the algorithms’ performance are introduced. Finally, the authors present several promising future directions for further studies.

The task of the 2017 Soccer Prediction Challenge was to use machine learning to predict the outcome of future soccer matches based on a data set describing the match outcomes of 216,743 past soccer matches. One of the goals of the Challenge was to gauge where the limits of predictability lie with this type of commonly available data. Another goal was to pose a real-world machine learning challenge with a fixed time line, involving the prediction of real future events. Here, we present two novel ideas for integrating soccer domain knowledge into the modeling process. Based on these ideas, we developed two new feature engineering methods for match outcome prediction, which we denote as recency feature extraction and rating feature learning. Using these methods, we constructed two learning sets from the Challenge data. The top-ranking model of the 2017 Soccer Prediction Challenge was our k-nearest neighbor model trained on the rating feature learning set. In further experiments, we could slightly improve on this performance with an ensemble of extreme gradient boosted trees (XGBoost). Our study suggests that a key factor in soccer match outcome prediction lies in the successful incorporation of domain knowledge into the machine learning modeling process.

Noisy inputs pose significant challenges for reinforcement learning (RL) agents navigating real-world environments. While animals demonstrate robust spatial learning under dynamic conditions, the mechanisms underlying this resilience remain understudied in RL frameworks. This paper introduces a novel comparative analysis of predecessor feature (PF) and successor feature (SF) algorithms under controlled noise conditions, revealing several insights. Our key innovation lies in demonstrating that SF algorithms achieve superior noise resilience compared to traditional approaches, with cumulative rewards of 2216.88±3.83 (mean ± SEM), even under high noise conditions (σ=0.5) in one-dimensional environments, while Q learning achieves only 19.22±0.57. In two-dimensional environments, we discover an unprecedented nonlinear relationship between noise level and algorithm performance, with SF showing optimal performance at moderate noise levels (σ=0.25), achieving cumulative rewards of 2886.03±1.63 compared to 2798.16±3.54 for Q learning. The λ parameter in PF learning is a significant factor, with λ=0.7 consistently achieving higher λ values under most noise conditions. These findings bridge computational neuroscience and RL, offering practical insights for developing noise-resistant learning systems. Our results have direct applications in robotics, autonomous navigation, and sensor-based AI systems, particularly in environments with inherent observational uncertainty.

In this study, we present the Ensemble Convolutional Neural Network (ECNN), an elaborate CNN frame formulated based on ensembling state-of-the-art CNN models, to identify village buildings from open high-resolution remote sensing (HRRS) images. First, to optimize and mine the capability of CNN for village mapping and to ensure compatibility with our classification targets, a few state-of-the-art models were carefully optimized and enhanced based on a series of rigorous analyses and evaluations. Second, rather than directly implementing building identification by using these models, we exploited most of their advantages by ensembling their feature extractor parts into a stronger model called ECNN based on the multiscale feature learning method. Finally, the generated ECNN was applied to a pixel-level classification frame to implement object identification. The proposed method can serve as a viable tool for village building identification with high accuracy and efficiency. The experimental results obtained from the test area in Savannakhet province, Laos, prove that the proposed ECNN model significantly outperforms existing methods, improving overall accuracy from 96.64% to 99.26%, and kappa from 0.57 to 0.86.

Video-based pedestrian re-identification (ReID) is able to match the same pedestrian from various cameras in a complex real-world scene. The extracted representations can’t contain all the useful information about the persons, due to the occlusion and misalignment of human areas between video sequences, and thus lack integrity and discrimination. To resolve this issue, we propose a new Spatial-Temporal Aware Network, which can mine and complement person features with feature relationships and intra-frame cues. According to the high correlation of the feature nodes of the same person between different video sequences, we employ the learned pedestrian feature nodes to construct the temporal relationship graph. In detail, the Temporal Interaction Module is designed to locate relevant pedestrian regions by modeling the correlation of feature nodes with reference nodes; and the Temporal Attention Module that we have designed is used to select more specific reference nodes. Then, we apply the designed Spatial Reference Module to adaptively mine each frame for fine-grained cues, making the spatial-temporal characteristics of persons more discriminative. We have implemented numerous experiments to demonstrate the excellent performance of STAN, such as achieving 88.0 % mAP and 89.5 % Rank-1 accuracy on the MARS dataset.

This paper aims to construct a resource base for adult online education using a multimodal fusion basis. The fusion processing methods of knowledge resources incorporate temporal and non-temporal feature learning. This paper proposes a process for constructing a multimodal subject knowledge space that can aid educators in organizing and presenting multimodal teaching content effectively. Also, the operation process of each major functional module of the adult online education resource library, including the online teaching process, online learning process and online resource production process, is studied in detail. Finally, the performance test of optimizing small file storage, the performance test of de-duplication of redundant data of learning resources and the stress test were conducted on the constructed resource library. The study concluded that the resource memory occupancy of the computer class was reduced by 0.35 after the de-duplication process, and in the stress test, the login response time was less than 8 seconds, and the average CPU utilization of the database server was <50%.

With the rapid development of aeronautic and deep space exploration technologies, a large number of high-resolution asteroid spectral data have been gathered, which can provide diagnostic information for identifying different categories of asteroids as well as their surface composition and mineralogical properties. However, owing to the noise of observation systems and the ever-changing external observation environments, the observed asteroid spectral data always contain noise and outliers exhibiting indivisible pattern characteristics, which will bring great challenges to the precise classification of asteroids. In order to alleviate the problem and to improve the separability and classification accuracy for different kinds of asteroids, this paper presents a novel Neighboring Discriminant Component Analysis (NDCA) model for asteroid spectrum feature learning. The key motivation is to transform the asteroid spectral data from the observation space into a feature subspace wherein the negative effects of outliers and noise will be minimized while the key category-related valuable knowledge in asteroid spectral data can be well explored. The effectiveness of the proposed NDCA model is verified on real-world asteroid reflectance spectra measured over the wavelength range from 0.45 to 2.45 μm, and promising classification performance has been achieved by the NDCA model in combination with different classifier models, such as the nearest neighbor (NN), support vector machine (SVM) and extreme learning machine (ELM).

Visible-infrared person re-identification (VI-ReID) is an important but very challenging task in the automated video surveillance and forensics. Although existing VI-ReID methods have achieved very encouraging results, how to make full use of the useful information contained in cross-modality visible and infrared images has not been well studied. In this paper, we propose an Information Disentanglement based Cross-modal Representation Learning (IDCRL) approach for VI-ReID. Specifically, IDCRL first extracts the shared and specific features from data of each modality by using the shared feature learning module and the specific feature learning module, respectively. To ensure that the shared and specific information can be well disentangled, we impose an orthogonality constraint on the shared and specific features of each modality. To make the shared features extracted from the visible and infrared images of the same person own high similarity, IDCRL designs a shared feature consistency constraint. Furthermore, IDCRL uses a modality-aware loss to ensure that the useful modality-specific features can be extracted from each modality effectively. Then, the obtained shared and specific features are concatenated as the representation of each image. Finally, identity loss function and cross-modal discriminant loss function are employed to enhance the discriminability of the obtained image representation. We conducted comprehensive experiments on the benchmark visible-infrared pedestrian datasets (SYSU-MM01 and RegDB) to evaluate the efficacy of our IDCRL approach. Experimental results demonstrate that IDCRL outperforms the compared state-of-the-art methods. On the SYSU-MM01 dataset, the rank-1 matching rate of our approach reaches 62.35% and 71.64% in the all-search and in-door modes, respectively. On the RegDB dataset, the rank-1 result of our approach reaches 76.32% and 75.49% in the visible to thermal and thermal to visible modes, respectively.

In real‐world applications, large amounts of data from multiple sources come in the form of streams. This makes multi‐view feature learning cost much time when new instances rise incrementally. Dealing with these growing multi‐view data becomes a challenging problem. Some single‐view methods focus on processing the data dynamically, but they are not suitable for multi‐view data. Some online multi‐view methods are proposed to tackle it, but they ignore the influence of uncorrelated items in each view. Therefore, in this study, the authors propose a new algorithm, called Incremental Multi‐view Correlated Feature Learning (IMCFL) based on non‐negative matrix factorisation, to learn the common feature across views. By separating uncorrelated items of new instances and constructing incremental joint learning of correlated and uncorrelated features, the proposed IMCFL can eliminate the influence of uncorrelated information in the individual view and improve the effectiveness of incremental multi‐view common feature learning. Extensive experiments on real‐world datasets confirm its superiority by comparing it with other state‐of‐the‐art incremental and non‐incremental methods.

Recently, deep learning has been reported to be an effective method for improving hyperspectral image classification and convolutional neural networks (CNNs) are, in particular, gaining more and more attention in this field. CNNs provide automatic approaches that can learn more abstract features of hyperspectral images from spectral, spatial, or spectral-spatial domains. However, CNN applications are focused on learning features directly from image data—while the intrinsic relations between original features, which may provide more information for classification, are not fully considered. In order to make full use of the relations between hyperspectral features and to explore more objective features for improving classification accuracy, we proposed feature relations map learning (FRML) in this paper. FRML can automatically enhance the separability of different objects in an image, using a segmented feature relations map (SFRM) that reflects the relations between spectral features through a normalized difference index (NDI), and it can then learn new features from SFRM using a CNN-based feature extractor. Finally, based on these features, a classifier was designed for the classification. With FRML, our experimental results from four popular hyperspectral datasets indicate that the proposed method can achieve more representative and objective features to improve classification accuracy, outperforming classifications using the comparative methods.