Ensuring product quality and integrity is paramount in the rapidly evolving landscape of industrial manufacturing. Although effective to a certain degree, traditional quality control methods often fail to meet the demands for efficiency, accuracy, and adaptability in today’s fast-paced production environments. The advent of Deep Learning (DL) and Computer Vision (CV) technologies has opened new vistas for automated defect detection, promising to revolutionize the way industries approach quality control and inspection. This systematic review focuses on recent advancements in DL and CV applications for automated defect detection in manufacturing processes. It provides a comprehensive overview of state-of-the-art techniques for detecting, classifying, and predicting defects, highlighting the significant strides made in addressing challenges such as varying lighting conditions, complex defect patterns, and the seamless integration of these technologies into existing manufacturing workflows. Through a critical analysis of current methodologies, this study identifies key areas of opportunity, outlines the challenges that persist and suggests directions for future research. This review synthesizes findings from a broad spectrum of industrial applications, offering insights into the potential of DL and CV to enhance quality control mechanisms. By charting the progress and pinpointing the gaps in current practices, this paper aims to serve as a valuable resource for researchers, practitioners, and policymakers seeking to leverage the benefits of DL and CV for improved product management and manufacturing excellence.

Sign Language Recognition (SLR) represents a revolutionary technology aiming to establish communication between deaf and non-deaf communities, surpassing traditional interpreter-based approaches. Existing efforts in automatic sign recognition predominantly rely on hand skeleton joint information, steering clear of image pixels to address challenges like partial occlusion and redundant backgrounds. Many researchers have been working to develop automatic sign recognition using hand skeleton joint information instead of image pixels to overcome partial occlusion and redundant background problems. However, body motion and facial expression play an essential role in increasing the inner gesture variance in expressing sign language emotion besides hand information for large-scale sign word datasets. Recently, some researchers have been working to develop muti-gesture-based SLR recognition systems, but their performance accuracy and efficiency are unsatisfactory for real-time deployment. Addressing these limitations, we propose a novel approach – a two-stream multistage graph convolution with attention and residual connection (GCAR) – designed to extract spatial-temporal contextual information. The multistage GCAR system, incorporating a channel attention module, dynamically enhances attention levels, particularly for non-connected skeleton points during specific events within spatial-temporal features. The methodology involves capturing joint skeleton points and motion, offering a comprehensive understanding of a person’s entire body movement during sign language gestures and feeding this information into two streams. In the first stream, joint key features undergo processing through sep-TCN, graph convolution, deep learning layer, and a channel attention module across multiple stages, generating intricate spatial-temporal features in sign language gestures. Simultaneously, the joint motion is processed in the second stream, mirroring the steps of the first branch. The fusion of these two features yields the final feature vector, which is then fed into the classification module. The model excels in capturing discriminative structural displacements and short-range dependencies by leveraging unified joint features projected onto a high-dimensional space. Owing to the effectiveness of these features, the proposed method achieved significant accuracies: 90.31%, 94.10%, 99.75%, and 34.41%, for the WLASL, PSL, MSL, and ASLLVD large-scale datasets, respectively, with 0.69 million parameters. The high-performance accuracy, coupled with stable computational complexity, demonstrates the superiority of the proposed model. This innovative approach is anticipated to redefine the landscape of sign language recognition, setting a new standard in the field.

Human Activity Recognition (HAR) systems aim to understand human behavior and assign a label to each action, attracting significant attention in computer vision due to their wide range of applications. HAR can leverage various data modalities, such as RGB images and video, skeleton, depth, infrared, point cloud, event stream, audio, acceleration, and radar signals. Each modality provides unique and complementary information suited to different application scenarios. Consequently, numerous studies have investigated diverse approaches for HAR using these modalities. This survey includes only peer-reviewed research papers published in English to ensure linguistic consistency and academic integrity. This paper presents a comprehensive survey of the latest advancements in HAR from 2014 to 2025, focusing on Machine Learning (ML) and Deep Learning (DL) approaches categorized by input data modalities. We review both single-modality and multi-modality techniques, highlighting fusion-based and co-learning frameworks. Additionally, we cover advancements in hand-crafted action features, methods for recognizing human–object interactions, and activity detection. Our survey includes a detailed dataset description for each modality, as well as a summary of the latest HAR systems, accompanied by a mathematical derivation for evaluating the deep learning model for each modality, and it also provides comparative results on benchmark datasets. Finally, we provide insightful observations and propose effective future research directions in HAR.

Weakly supervised video anomaly detection (WS-VAD) is a crucial research domain in computer vision for the implementation of intelligent surveillance systems. Many researchers have been working to develop WS-VAD systems using various technologies by assessing anomaly scores. However, they are still facing challenges because of lacking effective feature extraction. To mitigate this limitation, we propose a multi-stage deep-learning model for separating abnormal events from normality to extract the hierarchical effective features. In the first stage, we extract two stream features using pre-trained techniques: the first stream employs a ViT-based CLIP module to select top-k features, while the second stream utilizes a CNN-based I3D module integrated into the Temporal Contextual Aggregation (TCA) mechanism. These features are concatenated and fed into the second-stage module, where an Uncertainty-regulated Dual Memory Units (UR-DMU) model is employed to learn representations of regular and abnormal data simultaneously. The UR-DMU integrates global and local structures, leveraging Graph Convolutional Networks (GCN) and Global and Local Multi-Head Self Attention (GL-MHSA) modules to capture video associations. Subsequently, feature reduction is achieved using the multilayer-perceptron (MLP) integration with the Prompt-Enhanced Learning (PEL) module via the knowledge-based prompt. Finally, we employed a classifier module to predict the snippet-level anomaly scores. In the training phase, the based function transfers the snippet-level scores into bag-level predictions for learning high activation in anomalous cases. Our approach integrates these cutting-edge technologies and methodologies, offering a comprehensive solution to video-based anomaly detection. Extensive experiments on ShanghaiTech, XD-Violence, and UCF-Crime datasets validate the superiority of our method over state-of-the-art approaches by a substantial margin. We believe that our model holds significant promise for real-world applications, demonstrating superior performance and efficacy in anomaly detection tasks.

This paper proposes a novel method for accelerating ray tracing of animated scenes in which objects are moved, added, or deleted. The method uses two trees with different structures. The first tree is a hierarchical grid tree that is easily generatable from the primitive list and modifiable according to its change. The second tree is a bounding volume hierarchy (BVH) tree, constructed from the first tree with intra-node agglomerative clustering. When the scene is modified, the first tree is updated, and then, the second tree is partially rebuilt for accessed nodes in the first tree. The resulting BVH tree is deterioration-free; it always coincides with the tree generated by frame-wise rebuilding. For applications where a small portion of the scene is modified between frames, the tree formation cost of the proposed method is much lower than frame-wise rebuilding. Experiments showed that the quality of BVH trees generated by this method is comparable to those created by the binned surface area heuristic approach, and that the tree formation speed is faster not only for dynamic scenes but also for static scenes.