Action Classification Research Articles

Does Phage Therapy Need a Pan-Phage?

The emergence of multidrug-resistant bacteria is undoubtedly one of the most serious global health threats. One response to this threat that has been gaining momentum over the past decade is 'phage therapy'. According to this, lytic bacteriophages are used for the treatment of bacterial infections, either alone or in combination with antimicrobial agents. However, to ensure the efficacy and broad applicability of phage therapy, several challenges must be overcome. These challenges encompass the development of methods and strategies for the host range manipulation and bypass of the resistance mechanisms developed by pathogenic bacteria, as has been the case since the advent of antibiotics. As our knowledge and understanding of the interactions between phages and their hosts evolves, the key issue is to define the host range for each application. In this article, we discuss the factors that affect host range and how this determines the classification of phages into different categories of action. For each host range group, recent representative examples are provided, together with suggestions on how the different groups can be used to combat certain types of bacterial infections. The available methodologies for host range expansion, either through sequential adaptation to a new pathogen or through genetic engineering techniques, are also reviewed.

Simulation of artificial intelligence robots in dance action recognition and interaction process based on machine vision

Artificial intelligence robots based on machine vision have shown great potential in dance action recognition and interaction. In order to perform action recognition, a large amount of dance action video data was collected as the basis for training and testing the model. In motion recognition, various computer vision techniques are used to extract motion features from images or videos to capture key information of dance movements. Machine learning technology was adopted to construct an action classification model. By using the data collected in the early stage and the extracted features, an efficient and accurate classifier has been studied and trained. It can classify the input dance actions into different categories, segment continuous video frames into different action segments, and ensure accurate differentiation of different dance actions during the recognition process, avoiding misjudgment or confusion. By accurately capturing and analyzing the posture information of the human body, we can better understand and simulate dance movements, and enhance the performance and realism of artificial intelligence robots in dance interactions. The experimental results show that the system can accurately recognize various dance movements and achieve good interaction with users.

Beyond target chemicals: updating the NORMAN prioritisation scheme to support the EU chemicals strategy with semi-quantitative suspect/non-target screening data

BackgroundPrioritisation of chemical pollutants is a major challenge for environmental managers and decision-makers alike, which is essential to help focus the limited resources available for monitoring and mitigation actions on the most relevant chemicals. This study extends the original NORMAN prioritisation scheme beyond target chemicals, presenting the integration of semi-quantitative data from retrospective suspect screening and expansion of existing exposure and risk indicators. The scheme utilises data retrieved automatically from the NORMAN Database System (NDS), including candidate substances for prioritisation, target and suspect screening data, ecotoxicological effect data, physico-chemical data and other properties. Two complementary workflows using target and suspect screening monitoring data are applied to first group the substances into six action categories and then rank the substances using exposure, hazard and risk indicators. The results from the ‘target’ and ‘suspect screening’ workflows can then be combined as multiple lines of evidence to support decision-making on regulatory and research actions.ResultsAs a proof-of-concept, the new scheme was applied to a combined dataset of target and suspect screening data. To this end, > 65,000 substances on the NDS, of which 2579 substances supported by target wastewater monitoring data, were retrospectively screened in 84 effluent wastewater samples, totalling > 11 million data points. The final prioritisation results identified 677 substances as high priority for further actions, 7455 as medium priority and 326 with potentially lower priority for actions. Among the remaining substances, ca. 37,000 substances should be considered of medium priority with uncertainty, while it was not possible to conclude for 19,000 substances due to insufficient information from target monitoring and uncertainty in the identification from suspect screening. A high degree of agreement was observed between the categories assigned via target analysis and suspect screening-based prioritisation. Suspect screening was a valuable complementary approach to target analysis, helping to prioritise thousands of substances that are insufficiently investigated in current monitoring programmes.ConclusionsThis updated prioritisation workflow responds to the increasing use of suspect screening techniques. It can be adapted to different environmental compartments and can support regulatory obligations, including the identification of specific pollutants in river basins and the marine environments, as well as the confirmation of environmental occurrence levels predicted by modelling tools.Graphical

Cell Painting unravels insecticidal modes of action on Spodoptera frugiperda insect cells

The “Cell Painting” technology utilizes multiplexed fluorescent staining of various cell organelles, to produce high-content microscopy images of cells for multidimensional phenotype assessment. The phenotypic profiles extracted from those images can be analyzed upon perturbations with biologically active molecules to annotate the mode of action or biological activity by comparison with reference profiles of already known mechanisms of action, ultimately enabling the determination of on-target and off-target effects. This approach is already described in various human cell cultures, the most commonly used being the U2OS cell line, yet allows broad applications in additional areas of chemical-biological research. Here we describe for the first time the application and adaptation of Cell Painting to an insect cell line, the Sf9 cells from Spodoptera frugiperda. By adjusting image acquisition and analysis models, specific phenotypic profiles were obtained in a dose-dependent manner for 20 reference compounds, including representatives for the most relevant insecticidal modes of action categories (nerve & muscle, respiration and growth & development). Through a dimensionality-reduction method, both calculations of phenotypic half maximal inhibition concentration (IC50) values as well as similarity analysis of the obtained profiles by hierarchical clustering were performed. By Cell Painting effects on the phenotype could be obtained at higher sensitivity than in other assay formats, such as cytotoxicity assessments. More importantly, these analyses provide insight into mechanistic determinants of biological activity. Compounds with similar modes of action showed a high degree of proximity in a hierarchical clustering analysis while being distinct from actives with an unrelated mode of action. In essence, we provide strong evidence on the impact of Cell Painting mechanistic understanding of insecticides with regards to determinants of efficacy and safety utilizing an insect cell model system.

Anomaly detection for high-content image-based phenotypic cell profiling.

High-content image-based phenotypic profiling combines automated microscopy and analysis to identify phenotypic alterations in cell morphology and provide insight into the cell's physiological state. Classical representations of the phenotypic profile can not capture the full underlying complexity in cell organization, while recent weakly machine-learning based representation-learning methods are hard to biologically interpret. We used the abundance of control wells to learn the in-distribution of control experiments and use it to formulate a self-supervised reconstruction anomaly-based representation that encodes the intricate morphological inter-feature dependencies while preserving the representation interpretability. The performance of our anomaly-based representations was evaluated for downstream tasks with respect to two classical representations across four public Cell Painting datasets. Anomaly-based representations improved reproducibility, Mechanism of Action classification, and complemented classical representations. Unsupervised explainability of autoencoder-based anomalies identified specific inter-feature dependencies causing anomalies. The general concept of anomaly-based representations can be adapted to other applications in cell biology.

Enhancing Single-Frame Supervision for Better Temporal Action Localization.

Temporal action localization aims to identify the boundaries and categories of actions in videos, such as scoring a goal in a football match. Single-frame supervision has emerged as a labor-efficient way to train action localizers as it requires only one annotated frame per action. However, it often suffers from poor performance due to the lack of precise boundary annotations. To address this issue, we propose a visual analysis method that aligns similar actions and then propagates a few user-provided annotations (e.g., boundaries, category labels) to similar actions via the generated alignments. Our method models the alignment between actions as a heaviest path problem and the annotation propagation as a quadratic optimization problem. As the automatically generated alignments may not accurately match the associated actions and could produce inaccurate localization results, we develop a storyline visualization to explain the localization results of actions and their alignments. This visualization facilitates users in correcting wrong localization results and misalignments. The corrections are then used to improve the localization results of other actions. The effectiveness of our method in improving localization performance is demonstrated through quantitative evaluation and a case study.

Non-Hausdorff germinal groupoids for actions of countable groups

We study conditions under which the germinal groupoid associated to a minimal equicontinuous action of a countable group on a Cantor set has non-Hausdorff topology. We develop a new criterion, which serves as an obstruction for the étale topology on the groupoid to be non-Hausdorff. We use this and other criteria to study the topology of germinal groupoids for a few classes of actions. In particular, we give examples of families of contracting and non-contracting self-similar groups, which are amenable and whose actions have associated germinal groupoids with non-Hausdorff topology.

A Video Action Recognition Method via Dual-Stream Feature Fusion Neural Network with Attention

Video action recognition is a technique for automatically determining the category of a video action. It is necessary to design an efficient video action recognition algorithm to predict video labels. This work proposes a video action recognition model based on dual-stream information fusion with attention mechanisms (DSIFAM), which consists of three different sub-modules. First, this proposes an improved keyframe extraction method (IKFE). Based on K-means clustering, this uses convolutional features to calculate the similarity between video frames instead of pixel points. After obtaining preliminary clustering results, the method performs secondary optimization to obtain more representative keyframes. Second, this proposes a video action recognition model based on dual-stream information fusion (DSIF). The method introduces ConvLSTM in the spatial stream and uses P3D instead of the original convolutional network in the temporal stream, which can better extract spatial-temporal information and improve the classification performance. Third, this designs a multi-scale attention mechanism (MSAM) to enhance the feature extraction stage and obtain higher quality classification features. The resulting features are more prominent and have stronger representation capabilities. Finally, this work conducts systematic experiments on different datasets, the results verify the superiority of DSIFAM for video action recognition.

Subject review: Human activity recognition based on depth images

Human activity recognition (HAR) has becomes a well-known area of study for researchers due to its multiple possible applications. HAR systems are applied in many areas including supervisory nursing care, medical supervision, surveillance, human- machine interaction, gaming and entertainment, etc. However, developing a robust HAR system that incorporates a comprehensive and scalable set of feature spaces is a challenging task. Much research has been done in this area to develop efficient HAR systems. In this article, a review of the developments in Human Activity Recognition (HAR) will be presented. Human activity recognition works on two basic principles; feature extraction from sensor data and classification of features into action classes. The review presented in this article is hence divided into two parts. The first part deals with feature representation in HAR systems such as Space-time Features, Frequency Features, Local Descriptors, Optical Flow Based, and Skeleton Joints. The second part deals with the classification approaches used in the literature such as Bayesian, and HMM.

The Body as Medium - Embodied Communication and Body Issues in Cloud Fitness

The "body turn" of "cloud fitness" has brought a new theoretical logic to communication. In this paper, we make a preliminary attempt at embodied communication in the context of the new Crown pneumonia epidemic, exploring the issues of body movement and moving bodies on "Shake" and "b-station". Here, the author argues that understanding embodied communication is inseparable from reflecting on technology, and that it is a form of communication in which people, media and technology interact. The article explores the changes of the philosophical category of bodily action in the virtual space of the Internet by tracing the origins of embodied communication; then understands the communication of the body as a medium through the "cloud space" and "cloud body"; and in the whole process of communication, the physical attributes of the body give the online and offline behaviors of the body a new meaning and a new meaning and a new meaning. In the whole process of communication, the physical attributes of the body bring tension to the online and offline actors; in the future, with the advent of the scene-oriented era, the body will have multiple symbolic attributes.

Evolving malware detection through instant dynamic graph inverse reinforcement learning

The rapid development and increasing evolution of malware necessitate novel defensive techniques with high accuracy and minimal false positives to safeguard information systems against potential threats. Unfortunately, current malware detection methods, primarily relying on deep learning to identify malicious fingerprints from extensive training sets, prove ineffective against few-shot and evolving malware variants. To address these challenges, this paper introduces MalIRL, which designs a model-free inverse reinforcement learning (IRL) mechanism to automatically capture the evolving attack intent of malware. Specifically, MalIRL explores six representative categories of malware actions and employs sliding windows to organically divide the massive malware execution event stream into multiple attack stages, achieving a reduced action space and state space. To model dynamic malicious environments, MalIRL proposes an instant dynamic heterogeneous graph representation learning technique. This technique learns state representations of different malware attack stages, enhancing detection accuracy and efficiency by incrementally capturing the newly added contextual semantics of diverse malware entities and relations. In experiments with three real-world malware datasets, MalIRL surpasses existing state-of-the-art methods, particularly in few-shot malware detection scenarios, MalIRL exhibits performance benefits of up to 18.9%.

Implementation of a health information technology safety classification system in the Veterans Health Administration's Informatics Patient Safety Office.

Implement the 5-type health information technology (HIT) patient safety concern classification system for HIT patient safety issues reported to the Veterans Health Administration's Informatics Patient Safety Office. A team of informatics safety analysts retrospectively classified 1year of HIT patient safety issues by type of HIT patient safety concern using consensus discussions. The processes established during retrospective classification were then applied to incoming HIT safety issues moving forward. Of 140 issues retrospectively reviewed, 124 met the classification criteria. The majority were HIT failures (eg, software defects) (33.1%) or configuration and implementation problems (29.8%). Unmet user needs and external system interactions accounted for 20.2% and 10.5%, respectively. Absence of HIT safety features accounted for 2.4% of issues, and 4% did not have enough information to classify. The 5-type HIT safety concern classification framework generated actionable categories helping organizations effectively respond to HIT patient safety risks.

Perceiving Actions via Temporal Video Frame Pairs

Video action recognition aims at classifying the action category in given videos. In general, semantic-relevant video frame pairs reflect significant action patterns such as object appearance variation and abstract temporal concepts like speed, rhythm, and so on. However, existing action recognition approaches tend to holistically extract spatiotemporal features. Though effective, there is still a risk of neglecting the crucial action features occurring across frames with a long-term temporal span. Motivated by this, in this article, we propose to perceive actions via frame pairs directly and devise a novel Nest Structure with frame pairs as basic units. Specifically, we decompose a video sequence into all possible frame pairs and hierarchically organize them according to temporal frequency and order, thus transforming the original video sequence into a Nest Structure. Through naturally decomposing actions, the proposed structure can flexibly adapt to diverse action variations such as speed or rhythm changes. Next, we devise a Temporal Pair Analysis module (TPA) to extract discriminative action patterns based on the proposed Nest Structure. The designed TPA module consists of a pair calculation part to calculate the pair features and a pair fusion part to hierarchically fuse the pair features for recognizing actions. The proposed TPA can be flexibly integrated into existing backbones, serving as a side branch to capture various action patterns from multi-level features. Extensive experiments show that the proposed TPA module can achieve consistent improvements over several typical backbones, reaching or updating CNN-based SOTA results on several challenging action recognition benchmarks.

Temporal cues enhanced multimodal learning for action recognition in RGB-D videos

Action recognition is an important and active research direction in computer vision, where temporal modeling is critical for action representation. Generally, unimodal methods that use only RGB or skeleton modality for human action recognition have their limitations, e.g., information redundancy/environment noise of RGB video modality, and spatial interaction deficiency of skeleton modality. In this paper, we present a novel multimodal learning approach based on RGB and skeleton modalities for action recognition in RGB-D videos. Specifically, we (1) transfer skeleton knowledge to RGB video for effective video compression, which produces the informative action image from raw RGB video, (2) introduce the temporal cues enhancement module to adequately learn the spatiotemporal representation for action classification, and (3) propose a multi-level multimodal co-learning framework for human action recognition in RGB-D videos. Experimental results on NTU RGB+D, PKU-MMD, and N-UCLA datasets demonstrate the effectiveness of the proposed multimodal learning method.

Discriminative Segment Focus Network for Fine-grained Video Action Recognition

Fine-grained video action recognition aims at identifying minor and discriminative variations among fine categories of actions. While many recent action recognition methods have been proposed to better model spatio-temporal representations, how to model the interactions among discriminative atomic actions to effectively characterize inter-class and intra-class variations has been neglected, which is vital for understanding fine-grained actions. In this work, we devise a Discriminative Segment Focus Network (DSFNet) to mine the discriminability of segment correlations and localize discriminative action-relevant segments for fine-grained video action recognition. Firstly, we propose a hierarchic correlation reasoning (HCR) module which explicitly establishes correlations between different segments at multiple temporal scales and enhances each segment by exploiting the correlations with other segments. Secondly, a discriminative segment focus (DSF) module is devised to localize the most action-relevant segments from the enhanced representations of HCR by enforcing the consistency between the discriminability and the classification confidence of a given segment with a consistency constraint. Finally, these localized segment representations are combined with the global action representation of the whole video for boosting final recognition. Extensive experimental results on two fine-grained action recognition datasets, i.e., FineGym and Diving48, and two action recognition datasets, i.e., Kinetics400 and Something-Something, demonstrate the effectiveness of our approach compared with the state-of-the-art methods.

TODO-Net: Temporally Observed Domain Contrastive Network for 3-D Early Action Prediction.

Early action prediction aiming to recognize which classes the actions belong to before they are fully conveyed is a very challenging task, owing to the insufficient discrimination information caused by the domain gaps among different temporally observed domains. Most of the existing approaches focus on using fully observed temporal domains to "guide" the partially observed domains while ignoring the discrepancies between the harder low-observed temporal domains and the easier highly observed temporal domains. The recognition models tend to learn the easier samples from the highly observed temporal domains and may lead to significant performance drops on low-observed temporal domains. Therefore, in this article, we propose a novel temporally observed domain contrastive network, namely, TODO-Net, to explicitly mine the discrimination information from the hard actions samples from the low-observed temporal domains by mitigating the domain gaps among various temporally observed domains for 3-D early action prediction. More specifically, the proposed TODO-Net is able to mine the relationship between the low-observed sequences and all the highly observed sequences belonging to the same action category to boost the recognition performance of the hard samples with fewer observed frames. We also introduce a temporal domain conditioned supervised contrastive (TD-conditioned SupCon) learning scheme to empower our TODO-Net with the ability to minimize the gaps between the temporal domains within the same action categories, meanwhile pushing apart the temporal domains belonging to different action classes. We conduct extensive experiments on two public 3-D skeleton-based activity datasets, and the results show the efficacy of the proposed TODO-Net.

A dual-prototype network combining query-specific and class-specific attentive learning for few-shot action recognition

Few-Shot Action Recognition (FSAR) aims at recognizing novel action classes with only a few labelled samples. Due to its simplicity and effectiveness, the prototypical network has attracted increasing interest in the field of FSAR. It is key to learn representative prototypes from a few labelled videos with various action lengths and speeds. To address this issue, this paper presents a dual-prototype network that combines class-specific and query-specific attentive learning for FSAR. First, we propose a class-specific attentive learning method that computes the within-class similarity for each class of the support sample. This method not only increases the representativeness of prototypes but also mitigates the impact of noises and outlying samples. Second, the class-specific attention is combined with query-specific attention to establish two parallel sets of prototypes for FSAR. The incorporation of query-specific attention further increases the discrimination among prototypes for different query samples. Furthermore, we propose a temporal-relation model to express the temporal dependency of action videos with different lengths and speeds. The proposed method is validated on four benchmark datasets. Extensive experimental results demonstrate the superiority of our method to the other 11 state-of-the-art FSAR methods.

Pesticide Mode of Action Classification: Understanding Resistance Action Committees (RACs)

This publication defines the concept of a pesticide mode of action and provides several examples. It emphasizes the importance of identifying and differentiating modes of action for pesticide resistance management. To this end, it defines the development and goals of the three Resistance Action Committees for insecticides (IRAC), herbicides (HRAC), and fungicides (FRAC) and describes each group’s pesticide mode of action classification scheme. Finally, it provides an example of a pesticide label and instructs applicators on how to rotate pesticides to manage resistance. This publication presents the subject matter in a concise manner and directs pesticide applicators to the very useful RAC Mode of Action group numbers for rotation purposes.

Aligning Correlation Information for Domain Adaptation in Action Recognition.

Domain adaptation (DA) approaches address domain shift and enable networks to be applied to different scenarios. Although various image DA approaches have been proposed in recent years, there is limited research toward video DA. This is partly due to the complexity in adapting the different modalities of features in videos, which includes the correlation features extracted as long-range dependencies of pixels across spatiotemporal dimensions. The correlation features are highly associated with action classes and proven their effectiveness in accurate video feature extraction through the supervised action recognition task. Yet correlation features of the same action would differ across domains due to domain shift. Therefore, we propose a novel adversarial correlation adaptation network (ACAN) to align action videos by aligning pixel correlations. ACAN aims to minimize the distribution of correlation information, termed as pixel correlation discrepancy (PCD). Additionally, video DA research is also limited by the lack of cross-domain video datasets with larger domain shifts. We, therefore, introduce a novel HMDB-ARID dataset with a larger domain shift caused by a larger statistical difference between domains. This dataset is built in an effort to leverage current datasets for dark video classification. Empirical results demonstrate the state-of-the-art performance of our proposed ACAN for both existing and the new video DA datasets.

Reckoning climate apartheid

This paper provides a critical, interdisciplinary analysis of the current global landscape of climate action and response with the aim of determining its overall trajectory toward either justice and equity on the one hand, or exploitation and segregation on the other. It finds that tendencies toward the latter are far more pronounced. This paper summarizes those findings and presents arguments for three categories of climate action that are producing and/or exacerbating inequity, injustice, and segregation. They are: securitization (of resources, infrastructure, borders, and land), financialization (of exploitative mitigation and adaptation measures), and (im)mobilization (of migrants and the climate-vulnerable alongside the increased mobility of elite populations). An examination of the political rhetoric and public discourse associated with these trends follows, revealing widespread dehumanization and ‘othering’ used to condone a system that justifies protection for some populations and the expendability of others. Together, this analysis provides a framework for exposing and critiquing our current trajectory toward an outcome that is best described as climate apartheid.