Event Recognition Research Articles

Proposal Semantic Relationship Graph Network for Temporal Action Detection

Temporal action detection, a critical task in video activity understanding, is typically divided into two stages: proposal generation and classification. However, most existing methods overlook the importance of information transfer among proposals during classification, often treating each proposal in isolation, which hampers accurate label prediction. In this paper, we propose a novel method for inferring semantic relationships both within and between action proposals, guiding the fusion of action proposal features accordingly. Building on this approach, we introduce the Proposal Semantic Relationship Graph Network (PSRGN), an end-to-end model that leverages intra-proposal semantic relationship graphs to extract cross-scale temporal context and an inter-proposal semantic relationship graph to incorporate complementary neighboring information, significantly improving proposal feature quality and overall detection performance. This is the first method to apply graph structure learning in temporal action detection, adaptively constructing the inter-proposal semantic graph. Extensive experiments on two datasets demonstrate the effectiveness of our approach, achieving state-of-the-art results. Code and results are available at http://github.com/Riiick2011/PSRGN .

DSTANet: learning a dual-stream model for anomaly driving action detection using spatio-temporal and appearance features

DSTANet: learning a dual-stream model for anomaly driving action detection using spatio-temporal and appearance features

A Review on Robust Credit Card Fraud Detection System Leveraging Big Data and Machine Learning

This review offers a detailed strategy to address the growing threat of credit card fraud in today's digital landscape. By utilizing Big Data analytics alongside machine learning methods, the system aims to transform fraud detection processes. It tackles the challenges arising from the increasing volume and complexity of credit card transactions, enabling the real-time detection and prevention of fraudulent actions. The system employs sophisticated machine learning algorithms to identify patterns and anomalies linked to fraudulent activities, allowing for proactive responses to emerging fraud tactics. Additionally, the system is optimized to handle and analyze large datasets efficiently, ensuring timely and precise detection of fraud. It also incorporates strong security protocols to protect sensitive customer data while adhering to privacy regulations. This review ultimately seeks to enhance the safety and reliability of electronic payments, protecting financial institutions and consumers from the harmful effects of credit card fraud.

Efficient Credit Card Fraud Detection System Using Big Data and Machine Learning

This review offers a detailed strategy to address the growing threat of credit card fraud in today's digital landscape. By utilizing Big Data analytics alongside machine learning methods, the system aims to transform fraud detection processes. It tackles the challenges arising from the increasing volume and complexity of credit card transactions, enabling the real-time detection and prevention of fraudulent actions. The system employs sophisticated machine learning algorithms to identify patterns and anomalies linked to fraudulent activities, allowing for proactive responses to emerging fraud tactics. Additionally, the system is optimized to handle and analyze large datasets efficiently, ensuring timely and precise detection of fraud. It also incorporates strong security protocols to protect sensitive customer data while adhering to privacy regulations. This review ultimately seeks to enhance the safety and reliability of electronic payments, protecting financial institutions and consumers from the harmful effects of credit card fraud.

Multisource Threatening Event Recognition Scheme Targeting Drone Intrusion in the Fiber Optic DAS System

Multisource Threatening Event Recognition Scheme Targeting Drone Intrusion in the Fiber Optic DAS System

Research on fiber OTDR signal recognition and classification based on the ViT model

In the field of event recognition for phase-sensitive optical time-domain reflectometry (-OTDR), convolutional neural networks (CNNs) have been the mainstream tool. However, Transformer models, with their self-attention mechanism, have provided a new perspective for image recognition tasks. This paper proposes a -OTDR event recognition method based on the Transformer model and experimentally demonstrates its significant advantages over CNNs. The method utilizes an attention-based feature extraction approach to recognize distributed fiber optic sensing signals in a phase-sensitive optical time-domain reflectometer (-OTDR). In perimeter defense applications, various interferences and noise severely affect the recognition of -OTDR sensing signals, leading to false alarms, making accurate signal recognition both challenging and necessary. Extracting signal features and using machine learning classification models to recognize signals has been a research hotspot in recent years. The effectiveness of feature extraction is crucial to classification performance. This project introduces a temporal-spatial dual attention mechanism into the feature extraction of fiber optic sensing signals to improve the accuracy and robustness of signal recognition.

Tsg101 UEV Interaction with Nedd4 HECT Relieves E3 Ligase Auto-Inhibition, Promoting HIV-1 Assembly and CA-SP1 Maturation Cleavage

Tsg101, a component of the endosomal sorting complex required for transport (ESCRT), is responsible for recognition of events requiring the machinery, as signaled by cargo tagging with ubiquitin (Ub), and for recruitment of downstream acting subunits to the site. Although much is known about the latter function, little is known about its role in the earlier event. The N-terminal domain of Tsg101 is a structural homologue of Ub conjugases (E2 enzymes) and the protein associates with Ub ligases (E3 enzymes) that regulate several cellular processes including virus budding. A pocket in the domain recognizes a motif, PT/SAP, that permits its recruitment. PT/SAP disruption makes budding dependent on Nedd4L E3 ligases. Using HIV-1 encoding a PT/SAP mutation that makes budding Nedd4L-dependent, we identified as critical for rescue the residues in the catalytic (HECT) domain of the E3 enzyme that lie in proximity to sites in Tsg101 that bind Ub non-covalently. Mutation of these residues impaired rescue by Nedd4L but the same mutations had no apparent effect in the context of a Nedd4 isomer, Nedd4-2s, whose N-terminal (C2) domain is naturally truncated, precluding C2-HECT auto-inhibition. Surprisingly, like small molecules that disrupt Tsg101 Ub-binding, small molecules that interfered with Nedd4 substrate recognition arrested budding at an early stage, supporting the conclusion that Tsg101–Ub–Nedd4 interaction promotes enzyme activation and regulates Nedd4 signaling for viral egress. Tsg101 regulation of E3 ligases may underlie its broad ability to function as an effector in various cellular activities, including viral particle assembly and budding.

STMixer: A One-Stage Sparse Action Detector.

Traditional video action detectors typically adopt the two-stage pipeline, where a person detector is first employed to generate actor boxes and then 3D RoIAlign is used to extract actor-specific features for action recognition. This detection paradigm requires multi-stage training and inference, and the feature sampling is only constrained inside the box, failing to effectively leverage richer context information outside. Recently, several query-based action detectors have been proposed to predict action instances in an end-to-end manner. However, they still lack adaptability in feature sampling and decoding, thus suffering from the issues of inferior performance or slower convergence. In this paper, we propose two core designs for a more flexible one-stage sparse action detector. First, we present a query-based adaptive feature sampling module, which endows the detector with the flexibility of mining a group of discriminative features from the entire spatio-temporal domain. Second, we devise a decoupled feature mixing module, which dynamically attends to and mixes video features along the spatial and temporal dimensions respectively for better feature decoding. Based on these designs, we instantiate two detection pipelines, that is, STMixer-K for keyframe action detection and STMixer-T for action tubelet detection. Without bells and whistles, our STMixer detectors obtain the state-of-the-art results on five challenging spatio-temporal action detection benchmarks for keyframe action detection or action tube detection.

Pharmacovigilance: An Ethical Issue for Clinical Psychology, Psychiatry, and Pharmacy?

Pharmacovigilance helps determine when a treatment might cause novel or unintended effects. Patients, clinicians, regulators, and pharmaceutical companies have a stake in determining how the causality of treatment-induced effects should be established and when effects should be noted in settings from the academic literature to a medicine’s label. There have been different approaches to this task in different jurisdictions, with reporting to companies more common in the United States and reporting to regulators more common in Europe. Over time, pharmacovigilance has switched from being primarily a clinical enterprise to being a regulatory one, which has led to the elimination of the names of those suffering from an adverse event and the outsourcing of the job of recording the details of events to private companies, which appears likely to reduce the recognition of adverse events. This article calls for a restoration of clinical input on adverse events aimed at increasing reporting and recognition rates for important behavioral events.

Improved RNN Model for Real-Time Human Activity Recognition

This study focuses on the automatic detection of human actions in video streams. The requirement to detect what human activities happen in videos is recognition of human action due to significant differences in people's visual and motion appearance and actions, camera perspective shifts, moving background, occlusions, noise, and a massive amount of video data. The human activity recognition challenge involves identifying physical activities carried out by individuals or groups based on traces of movements, including gestures, actions, interactions, and group activities. The detection of concepts usually requires additional annotations for the training dataset. In this paper, useful methods for categorizing human action recognition are discussed. The current models are an accurate deep learning method that is based on models that have been changed to be more useful. The large disparities that result from the backdrop and the size of the objects have prevented the identification of activities in videos from being fully and effectively addressed. The main objective is to achieve better accuracy for the Long Short-Term Memory (LSTM) method, which was used to improve the Recurrent Neural Networks (RNN) model. In this paper, LSTM is used to come up with models for different action recognition tasks. The model was made better by making the LSTM have four layers and putting 128 units, 64 units, 32 units, and 16 units in each layer, respectively. In addition, the performance evaluation of deep learning-based approaches has been compared to other related works. Therefore, an improved approach to RNN is proposed to recognize human actions. To classify the videos, a multilayer RNN with a specific type of LSTM is used to extract features from video sequences. The UCF-101 and UCF Sports human action recognition datasets are utilized in this study for both training and assessment. Test findings demonstrate that the suggested strategy achieved increased accuracy. Finally, the enhanced RNN model's total model accuracy in the UCF-101 dataset is 93.78% and 95.70% for the UCF Sport dataset.

A benchmark dataset and semantics-guided detection network for spatial–temporal human actions in urban driving scenes

In real urban driving scenes, human actions are very complex and have the characteristic of multiple concurrent actions. It has a great significance to detect human actions in urban traffic scenes for auxiliary or autonomous driving systems. In this view, we introduce the TITAN-Human Action dataset for the task of multi-person spatial–temporal action detection in urban driving scenes. TITAN-Human Action provides the fine-grained action labels and location coordinates for 17,574 persons in the processed frames from the TITAN dataset. Furthermore, we propose a semantics-guided detection network (SGDNet) based on a semantic inference module (SIM) for spatial–temporal human action detection in urban driving scenes. SIM encodes the category labels into sentence vectors at the semantic level with prompting and embedding, utilizes graphs to represent the directed co-occurrence relations between categories, and adopts the graph convolutional network for semantic inference. SGDNet exploits the inference results of SIM to guide the visual branch in better performing human action detection, thereby achieving the integration of visual and linguistic information. We conducted experiments to evaluate SGDNet and several baseline methods on the TITAN-Human Action dataset, and reveal the generalizability of SIM in spatial–temporal human action detection. The source code and annotation files will be available at https://github.com/yyhbswyn/SGDNet.

Annealing Temporal–Spatial Contrastive Learning for multi-view Online Action Detection

In open-world scenarios, the analysis of action events from multiple viewpoints is crucial for achieving a holistic understanding, a concept that resonates with human perception. However, achieving a synthesis of information from multiple viewpoints presents a challenge, as the data can induce inter-view regularization, complicating the learning process. This paper is the first to delve into Online Action Detection (OAD) through a multi-view lens, underscoring the value of cross-observation in enriching view-level information. By harnessing the spatiotemporal dynamics inherent in multi-view video sequences, an Annealing Temporal–Spatial Contrastive Learning (ATSCL) consisting of Annealing Temporal Contrastive Learning (ATCL) and Spatial Contrastive Learning (SCL) is proposed, optimized for compatibility with RNN-based models. ATCL employs an annealing temporal loss to uncover the intrinsic video structures via a temporal annealing sampling mechanism. Concurrently, SCL utilizes a spatial loss to draw representations from various viewpoints closer together, mitigating the regularization effects. The ATSCL liberates training multi-view OAD from the stringent requirements of synchronized training videos, enabling the execution of OAD tasks asynchronously. Experiments demonstrate that the RNN-based models realize an average improvement of 5.92% on the DAHLIA dataset, 3.36% on the IKEA ASM dataset, 2.92% on the BREAKFAST dataset and 0.6% (mAP) on the THUMOS’14 dataset following the integration of the ATSCL framework, underscoring the ATSCL’s efficacy across different RNN structures.

Effective zero-shot learning method for event classification in Φ-OTDR sensing systems

Despite various Φ-OTDR intrusion event recognition methods having achieved high average accuracy rates (over 90%), these methods usually rely on a large amount of training sample data (80% of the data). When faced with certain intrusion events that are difficult to simulate or have few samples available, the model tends to overfit common types of intrusion events. To address this issue, this paper proposes a zero-sample learning one-dimensional residual model based on attribute point loss (APL-ZSL-1DResNet) to recognize one-dimensional intrusion event signals when training samples are insufficient. The proposed method is validated on two datasets, including a self-made dataset and an open dataset. In the experiments, each category of samples was set as zero-sample intrusion events, achieving an average recall rate of 75% and 66% respectively for zero-sample events, and an average recall rate of 94.6% and 83.5% respectively for common intrusion events.

A time patch dynamic attention transformer for enhanced well production forecasting in complex oilfield operations

In the field of oil production, accurately predicting well production is of great significance for optimizing production processes and enhancing economic benefits. However, oil production data generally exhibit characteristics such as high noise, complex distribution, and severe temporal fluctuations, which pose significant challenges to traditional prediction models, thereby limiting their accuracy. To address this issue, this study proposes an innovative Time Patch Dynamic Attention Transformer (TPDAT) model. This model segments the time series data into multiple time patches, extracts local features, and integrates a dynamically fused causal temporal attention mechanism to enhance the recognition of transient events and short-term fluctuations. The TPDAT model comprises the Temporal Patch Feature Extraction (TPF) module and the Dynamic Fusion Causal Temporal Attention (DFCTA) mechanism, effectively capturing multi-scale temporal features and enhancing the modeling of causal relationships during oilfield production. Experiments on the North Sea Volve oilfield dataset show that the TPDAT model significantly outperforms traditional deep learning models in well production prediction, achieves the best performance in model evaluation metrics, and demonstrates strong adaptability to complex data. The results confirm that the TPDAT model improves the accuracy and stability of well production prediction in complex oilfield environments, providing reliable support for oilfield production optimization.

FRC‐SGAN based anomaly event recognition for computer night vision in edge and cloud environment

FRC‐SGAN based anomaly event recognition for computer night vision in edge and cloud environment

IMAGE CAPTION GENERATOR USING CNN AND LSTM

Machine learning is now all the rage in the AI world. We have recently used AI to construct very clever devices with exceptional performance. Deep learning is a subset of machine learning that produces very accurate findings, which in turn indicates very good performance. Apps for picture description make use of deep learning in our study. Providing a description of a picture's content is what image description is all about. Object and action detection in the input picture is the foundation of the notion. When describing images, there are primarily two methods: bottom-up and top-down. Bottom-up methods create captions by combining the information of an input picture. Using different architectures, such as recurrent neural networks, top-down methods provide a semantic representation of an input picture, which is then translated into a caption. One potential advantage of picture description is that it might aid those with visual impairments in comprehending what is shown in online images. What follows is an explanation of the specifics. Looking at the image below, what can you make out?

A Process-Based Standardization of an Intraoperative Escalation Protocol in Anesthesiology.

Prompt recognition and management of critical events is pivotal for the provision of safe anesthetic care. This requires a well-functioning team that focuses on effective communication, timely decision-making, and escalation of potential complications. We believe that variation in bedside care leads to "near-misses," adverse outcomes, and serious safety events (SSEs). The principles of an escalation culture have been used successfully in other highly reliable industries such as aviation, military, and manufacturing. We discuss here the introduction of a unique and compelling thought-process for developing an intraoperative escalation protocol that is specifically tailored for our institution. Inspired by a critical intraoperative event, this departmental protocol was developed based on an analysis of multispecialty literature and expert opinion to decrease the incidence of SSEs. It includes a stepwise approach and incorporates patient-specific information to guide team members who encounter dynamic clinical situations. The implementation of the protocol has facilitated continuous quality improvement through iterative education, improving communication, and enhancing decision-making. Concurrently, we have plans to incorporate technology and electronic decision support tools to enhance real-time communication, monitor performance, and foster a culture of safety.

Receptive-field nonlinearities in primary auditory cortex: a comparative perspective.

Cortical processing of auditory information can be affected by interspecies differences as well as brain states. Here we compare multifeature spectro-temporal receptive fields (STRFs) and associated input/output functions or nonlinearities (NLs) of neurons in primary auditory cortex (AC) of four mammalian species. Single-unit recordings were performed in awake animals (female squirrel monkeys, female, and male mice) and anesthetized animals (female squirrel monkeys, rats, and cats). Neuronal responses were modeled as consisting of two STRFs and their associated NLs. The NLs for the STRF with the highest information content show a broad distribution between linear and quadratic forms. In awake animals, we find a higher percentage of quadratic-like NLs as opposed to more linear NLs in anesthetized animals. Moderate sex differences of the shape of NLs were observed between male and female unanesthetized mice. This indicates that the core AC possesses a rich variety of potential computations, particularly in awake animals, suggesting that multiple computational algorithms are at play to enable the auditory system's robust recognition of auditory events.

Distributed acoustic sensing signal event recognition and localization based on improved YOLOv7

Abstract The distributed acoustic sensing (DAS) system based on phase-sensitive optical time domain reflection ( Φ-OTDR) technology is widely used in pipeline safety monitoring, perimeter security, structure monitoring, etc. Accurate localization and recognition of multi-scene events over long distances has always been a challenge. This paper proposes an improved YOLOv7 algorithm for multi-event real-time detection of DAS system. The algorithm employs space-to-depth Conv(SPD-Conv) to replace the strided convolutions and pooling operations in YOLOv7, reducing fine-grained information loss and learning of inefficient feature representations. In addition, the Convolutional Block Attention Module (CBAM) is introduced in YOLOv7 to improve the model performance. We collected spatial–temporal signal data for six types of pipeline safety events, and passed them into the improved YOLOv7 algorithm in the form of data matrixes for training and evaluation. Experiments have shown that the proposed method achieves an mAP@.5 (mean Average Precision) of 99.7% for the identification of six pipeline safety event types. Positioning loss reduced to 0.2%, and detection speed can reach 70 frames per second(FPS). Our scheme achieves significant improvements in localization and classification accuracy compared to Faster R-CNN, etc. The event recognition localization method proposed in this paper has the advantage of fast speed and high accuracy.

Vamos: Middleware for best-effort third-party monitoring

As the complexity and criticality of software increase every year, so does the importance of runtime monitoring. Third-party and best-effort monitoring are especially valuable, yet under-explored areas of runtime monitoring. In this context, third-party monitoring means monitoring with a limited knowledge of the monitored software (as it has been developed by a third party). Best-effort monitoring keeps pace with the monitored software at the cost of possibly imprecise verdicts when keeping up with the monitored software would not be feasible. Most existing monitoring frameworks do not support the combination of third-party and best-effort monitoring because they either require the full access to the monitored code or the ability to process all observable events, or both.We present a middleware framework, Vamos, for the runtime monitoring of software. Vamos is explicitly designed to support third-party and best-effort scenarios. The design goals of Vamos are (i) efficiency (tracing events with low overhead), (ii) flexibility (the ability to monitor a variety of different event channels, and to connect to a wide range of monitors), and (iii) ease-of-use. To achieve its goals, Vamos combines aspects of event broker and event recognition systems with aspects of stream processing systems.We implemented a prototype toolchain for Vamos and conducted a set of experiments demonstrating the usability of the scheme. The results indicate that Vamos enables writing useful yet efficient monitors, and simplifies key aspects of setting up a monitoring system from scratch.