Temporal Context Research Articles

Costume design in film: Telling the story and creating Malcolm X’s character in Spike Lee’s Malcolm X (1992)

Costume designers collaborate with film directors to bring the characters in the script to life. Film costumes are a visual tool of a narrative nature with which costume designers meet the diegetic needs of each story. Through clothing, they make internal aspects of the characters visible, such as their transformations, their nature and styles, their passions, aspirations and suffering, as well as aspects of the spatial, temporal and social context in which the stories take place. This study explores costume design by Ruth E. Carter as a dramatic tool in the biopic Malcolm X (1992), directed by Spike Lee. To that end, the function of film costumes is assessed both as a visual and narrative tool that exceeds the aesthetic dimension and is essential to give meaning to any film production.

2D/3D Deep Registration Along Trajectories With Spatiotemporal Context: Application to Prostate Biopsy Navigation.

The accuracy of biopsy targeting is a major issue for prostate cancer diagnosis and therapy. However, navigation to biopsy targets remains challenging due to the limitations of transrectal ultrasound (TRUS) guidance added to prostate motion issues. This article describes a rigid 2D/3D deep registration method, which provides a continuous tracking of the biopsy location w.r.t the prostate for enhanced navigation. A spatiotemporal registration network (SpT-Net) is proposed to localize the live 2D US image relatively to a previously aquired US reference volume. The temporal context relies on prior trajectory information based on previous registration results and probe tracking. Different forms of spatial context were compared through inputs (local, partial or global) or using an additional spatial penalty term. The proposed 3D CNN architecture with all combinations of spatial and temporal context was evaluated in an ablation study. For providing a realistic clinical validation, a cumulative error was computed through series of registrations along trajectories, simulating a complete clinical navigation procedure. We also proposed two dataset generation processes with increasing levels of registration complexity and clinical realism. The experiments show that a model using local spatial information combined with temporal information performs better than more complex spatiotemporal combination. The best proposed model demonstrates robust real-time 2D/3D US cumulated registration performance on trajectories. Those results respect clinical requirements, application feasibility, and they outperform similar state-of-the-art methods. Our approach seems promising for clinical prostate biopsy navigation assistance or other US image-guided procedure.

Local-Global Context Aware Transformer for Language-Guided Video Segmentation.

We explore the task of language-guided video segmentation (LVS). Previous algorithms mostly adopt 3D CNNs to learn video representation, struggling to capture long-term context and easily suffering from visual-linguistic misalignment. In light of this, we present Locater (local-global context aware Transformer), which augments the Transformer architecture with a finite memory so as to query the entire video with the language expression in an efficient manner. The memory is designed to involve two components - one for persistently preserving global video content, and one for dynamically gathering local temporal context and segmentation history. Based on the memorized local-global context and the particular content of each frame, Locater holistically and flexibly comprehends the expression as an adaptive query vector for each frame. The vector is used to query the corresponding frame for mask generation. The memory also allows Locater to process videos with linear time complexity and constant size memory, while Transformer-style self-attention computation scales quadratically with sequence length. To thoroughly examine the visual grounding capability of LVS models, we contribute a new LVS dataset, A2D-S +, which is built upon A2D-S dataset but poses increased challenges in disambiguating among similar objects. Experiments on three LVS datasets and our A2D-S + show that Locater outperforms previous state-of-the-arts. Further, we won the 1st place in the Referring Video Object Segmentation Track of the 3rd Large-scale Video Object Segmentation Challenge, where Locater served as the foundation for the winning solution.

A Bayesian efficient observer model to explain attractive and repulsive temporal context effects when perceiving multistable dot lattices

A Bayesian efficient observer model to explain attractive and repulsive temporal context effects when perceiving multistable dot lattices

In/equalities in digital education policy – sociotechnical imaginaries from three world regions

ABSTRACT The interplay of digital technologies and inequalities are increasingly discussed in contemporary research, mostly focusing on different forms of digital divides and often addressed as a ‘problem’ that societies should face. Hence, digital education and its governance becomes a major arena for addressing inequalities. In this paper, we offer a cross-country and multi-voiced perspective on how socio-digital inequalities are problematized in digital education policy in three world regions – Latin America, Africa and Europe – studying cases through policy documents in Argentina, Mexico, South Africa, Botswana, Germany and Sweden. Our analysis shows how differences and similarities between digital education policy are rooted in various sociotechnical imaginaries that go beyond the national as they are highly situated in spatial–temporal contexts and rooted in historical trajectories. Our contribution aims at a further exploration of the entanglements of educational technology and in/equalities through global conditions and local (hi)stories.

BANDT: A Border-Aware Network With Deformable Transformers for Visual Tracking

Siamese trackers that predict a tracking box over a regular grid of feature maps based on the sliding-window paradigm have recently drawn widespread attention in the tracking community. However, the sliding-window paradigm lacks the exploration to characterize the explicit border features of the tracking object for accurate box prediction. Furthermore, Siamese trackers do not use an online learning process to improve the model’s discriminative power and a deformable transformer to explore the rich temporal context from the successive frames. To overcome these issues, we propose a border-aware network with deformable transformers (BANDT), which contains classification and regression branches for tracking. The proposed BANDT tracker introduces a border-alignment operation to capture the “border features" from the extreme points of the object’s border to improve the point features of the sliding-window paradigm. The BANDT tracker implements a deformable transformer consisting of an encoder and a decoder to enhance the target representations within a discriminative online learning framework. Specifically, the introduced encoder of the deformable transformer enhances the target representations, while the decoder highlights the potential tracking location. The proposed tracker achieves state-of-the-art performance on seven public datasets. In particular, it achieves 69.6% overlap success and 90.0% precision scores on the UAV123 dataset.

Anti-occlusion tracker for infrared ground targets based on improved trajectory prediction network

Aiming at the problem of infrared ground target tracking drift or even failure caused by background occlusion, we propose an anti-occlusion tracker for infrared ground targets based on improved trajectory prediction network. First, the occlusion judgment criterion is proposed to accurately determine the occlusion of the infrared ground target. Then, based on the BiTraP trajectory prediction network, on the one hand, by introducing velocity information through the Siamese network structure and using one-way prediction, the SiamUniTraP trajectory prediction network is proposed, which improves the precision of trajectory prediction. On the other hand, by improving the training method and application method, it can predict the trajectory of ground target more accurately. For short-term occlusions, the SiamUniTraP network is employed to predict the bounding box for target occlusion based on temporal context information. For long-term occlusions, the search expansion strategy is proposed to handle the accumulation of prediction errors caused by the lack of real target information. Finally, the “second determination” criterion is proposed to achieve accurate recapture of the target and return to normal tracking. Infrared image sequence tests are conducted under occlusion conditions. Compared with the SuperDiMP tracker, the proposed tracker improves the success rate by 5.2% and the accuracy by 5.9% under the OPE evaluation index. This indicates that the proposed tracker has good robustness for infrared ground target tracking in occlusion situations, especially in full occlusion situations.

A Privacy-Preserving Time-Aware Method for Next POI Recommendation

Compared with traditional point-of-interest (POI) recommendation, next POI recommendation is more difficult and requires comprehensive consideration of users’ behavior patterns, spatial–temporal context, and other information. In addition, unreliable service providers may disclose the privacy of users when providing recommendation services. For next POI recommendation, a privacy-preserving time-aware recommendation method (PPTA-RM) is proposed in this paper. The PPTA-RM method is based on centralized differential privacy and combines coarse-grained recommendation with fine-grained recommendation. At the coarse-grained level, the users’ POI category preference is modeled by improved matrix factorization and predicted by singular spectrum analysis (SSA), and gradient perturbation is carried out during the matrix factorization process to protect the POI category preference of users. At the fine-grained level, the users’ POI preference is modeled and predicted by an improved hyperlink-induced topic search (HITS) algorithm, which considers the weighted combination of users’ social attributes and POI geographic distance attributes, and a privacy budget allocation strategy considering the visit count of POIs is designed to add Laplace noise to the check-in data of users. The experimental analysis on two real datasets shows that the proposed method improves F1-Score@10 by 0.4–21.8% under different privacy budgets, which validates that the proposed method holds the next POI recommendation accuracy better while preserving the user’s privacy.

Unobserved heterogeneity and temporal instability in an analysis of household water consumption under block rate pricing

Abstract There is a lack of studies investigating household water consumption while considering the possible heterogeneity in the observed data and its temporal instability, often resulting in inconsistent and biased parameter estimations and, as a result, inaccurate forecasting of household water consumption. To address these constraints, the current study investigates temporal shifts in the household water consumption pattern and the effects of different socioeconomic factors on forecasting household water consumption. Using the results of a household survey performed seasonally in three major cities in Northern Jordan over a 4-year period, separate seasonal models of water consumption are estimated using three alternate modeling approaches to account for possible unobserved heterogeneity. Likelihood ratio tests were performed to investigate the temporal stability of the models' estimations over different seasons across the 4-year period. The findings of these tests indicated that the data are temporally stable over two datasets (the summer and winter seasons). Also, the findings revealed that household water consumption is influenced by a variety of factors, with the impact of many of these factors varying across observations. Finally, the findings highlight the need for additional research into how unobserved heterogeneity can be best modeled in temporal contexts for accurate water consumption forecasting.

Islamic Articulation of the Carpe Diem Motif in Herrick's "To Daffodils": A Post-Structuralist and Intertextual Inquiry

While Herrick is known for his religious poetry, the intersection of Islam and his work has not been explored in existing literature. The article examines the potential for Islamic meanings within Robert Herrick's poem "To Daffodils" through post-structuralist and intertextual lenses of literary analysis. The study employs the tenets of post-structuralism to explore the poem's thematic significance in relation to Islam. The analysis takes into account the temporal context of Herrick's 17th century era and the emergence of secularism, as well as the notion of the universality of Islam. The study concludes that the poem serves as a powerful reminder of the transient nature of human life, which is also a central theme in Islamic ethos. Herrick's work can be seen as an exemplar of Islamic knowledge, which imparts messages to humans about the temporality of life and its purposes and its eventual end. This article highlights the importance of Islamic reading of Herrick’s literature conveying important messages about the human condition and the significance of contemplating the ephemeral nature of life.

Exploring the Factors Influencing the Impact of the COVID-19 Pandemic on Global Shipping: A Case Study of the Baltic Dry Index

The outbreak of COVID-19 in 2020 resulted in notable disruptions to global shipping and the global economy. As a key indicator influenced by supply and demand conditions in the shipping industry, the Baltic Dry Index (BDI) serves as an early economic indicator for global economic production. Contrary to expectations of decline, the BDI has exhibited a substantial increase. This research paper aims to investigate the impact of the COVID-19 pandemic on global shipping through a comprehensive analysis of the BDI. The study incorporates data spanning from 2019 to 2021, encompassing the pre- and post-pandemic periods. It examines 13 independent variables, including raw material prices (such as iron ore prices), international scrap steel prices, energy prices, stock market indexes, international commodity price volatility (as represented by the Commodity Research Bureau Index), global port calls, and confirmed COVID-19 cases. The primary objective is to explore the factors influencing the BDI and how they were affected by the pandemic. The study employs stepwise regression to select variables and build models before and after the pandemic. The findings of this study elucidate the prominent factors that influence the BDI in different temporal contexts. Before the outbreak, the BDI was notably impacted by variables, including the US Dollar Index (positive relationship), Brent, Port Calls, and CRB Index. However, a discernible shift in the relative significance of these factors has been observed in the post-pandemic period. Specifically, the US Dollar Index now exhibits a negative relationship with the BDI, whereas variables such as Port Calls, Iron Price, Steel Scrap Price, and confirmed COVID-19 cases had attained heightened prominence in shaping the dynamics of the freight index. These findings underscored the dynamic nature of the factors influencing the BDI, particularly in light of the unique circumstances brought about by the COVID-19 pandemic.

Using a Smartwatch App to Understand Young Adult Substance Use: Mixed Methods Feasibility Study.

Young adults in the United States exhibit some of the highest rates of substance use compared to other age groups. Heavy and frequent substance use can be associated with a host of acute and chronic health and mental health concerns. Recent advances in ubiquitous technologies have prompted interest and innovation in using technology-based data collection instruments to understand substance use and associated harms. Existing methods for collecting granular, real-world data primarily rely on the use of smartphones to study and understand substance use in young adults. Wearable devices, such as smartwatches, show significant potential as platforms for data collection in this domain but remain underused. This study aims to describe the design and user evaluation of a smartwatch-based data collection app, which uses ecological momentary assessments to examine young adult substance use in daily life. This study used a 2-phase iterative design and acceptability evaluation process with young adults (aged 18-25 y) reporting recent alcohol or cannabis use. In phase 1, participants (8/15, 53%) used the data collection app for 14 days on their Apple Watches to report their substance use patterns, social contexts of substance use, and psychosocial risk factors (eg, affect). After this 14-day deployment, the participants completed a user experience survey and a semistructured interview to record their perspectives and experiences of using the app. Formative feedback from this phase informed feature modification and refinement of the app. In phase 2, an additional cohort (7/15, 47%) used the modified app for 14 days and provided feedback through surveys and interviews conducted after the app use period. Analyses of overall app use patterns indicated high, consistent use of the app, with participants using the app for an average of 11.73 (SD 2.60) days out of 14 days of data collection. Participants reported 67 instances of substance use throughout the study, and our analysis indicates that participants were able to respond to ecological momentary assessment prompts in diverse temporal and situational contexts. Our findings from the user experience survey indicate that participants found the app usable and functional. Comparisons of app use metrics and user evaluation scores indicate that the iterative app design had a measurable and positive impact on users' experience. Qualitative data from the participant interviews highlighted the value of recording substance use patterns, low disruption to daily life, minimal overall burden, preference of platforms (smartphones vs smartwatches), and perspectives relating to privacy and app use in social contexts. This study demonstrated the acceptability of using a smartwatch-based app to collect intensive, longitudinal substance use data among young adults. The findings document the utility of smartwatches as a novel platform to understand sensitive and often-stigmatized behaviors such as substance use with minimal burden.

Re-expression of CA1 and entorhinal activity patterns preserves temporal context memory at long timescales

Converging, cross-species evidence indicates that memory for time is supported by hippocampal area CA1 and entorhinal cortex. However, limited evidence characterizes how these regions preserve temporal memories over long timescales (e.g., months). At long timescales, memoranda may be encountered in multiple temporal contexts, potentially creating interference. Here, using 7T fMRI, we measured CA1 and entorhinal activity patterns as human participants viewed thousands of natural scene images distributed, and repeated, across many months. We show that memory for an image’s original temporal context was predicted by the degree to which CA1/entorhinal activity patterns from the first encounter with an image were re-expressed during re-encounters occurring minutes to months later. Critically, temporal memory signals were dissociable from predictors of recognition confidence, which were carried by distinct medial temporal lobe expressions. These findings suggest that CA1 and entorhinal cortex preserve temporal memories across long timescales by coding for and reinstating temporal context information.

Neural substrates of top-down processing during perceptual duration-based timing and beat-based timing.

Temporal context is a crucial factor in timing. Previous studies have revealed that the timing of regular stimuli, such as isochronous beats or rhythmic sequences (termed beat-based timing), activated the basal ganglia, whereas the timing of single intervals or irregular stimuli (termed duration-based timing) activated the cerebellum. We conducted a functional magnetic resonance imaging (fMRI) experiment to determine whether top-down processing of perceptual duration-based and beat-based timings affected brain activation patterns. Our participants listened to auditory sequences containing both single intervals and isochronous beats and judged either the duration of the intervals or the tempo of the beats. Whole-brain analysis revealed that both duration judgments and tempo judgments activated similar areas, including the basal ganglia and cerebellum, with no significant difference in the activated regions between the two conditions. In addition, an analysis of the regions of interest revealed no significant differences between the activation levels measured for the two tasks in the basal ganglia as well as the cerebellum. These results suggested that a set of common brain areas were involved in top-down processing of both duration judgments and tempo judgments. Our findings indicate that perceptual duration-based timing and beat-based timing are driven by stimulus regularity irrespective of top-down processing.

A Novel Paddy Leaf Disease Detection Framework using Optimal Leaf Disease Features in Adaptive Deep Temporal Context Network

Since paddy has become the staple food for all human beings, crop productivity is highly demanded. Nowadays, the agriculture industry faces the leaf disease issue as the insect or pests affects the plant leaves to hinder further growth. Owing to this, the productivity gets affected that makes the farmers have economic loss. In earlier time, several methods have been explored to detect the disease significantly. However, such methods become more time consuming, structure complexity and other issues. To alleviate such complex, a new paddy leaf disease detection model is proposed using adaptive methodology. Initially, images related with paddy leaf are gathered from standard resources and offered as the input to segmentation region. Here, segmentation is performed by Fuzzy C-Means (FCM) to get the abnormal regions. Then, the segmented images are fed to ensemble feature extraction region to attain different features like deep, textural, morphological, and color features. Further, the acquired ensemble features are provided to concatenation phase to obtain the concatenate features and the optimal features are selected by the Fire Hawk Optimizer (FHO). Finally, the optimal features are subjected to paddy leaf detection phase, where leaf disease will be detected by Adaptive Deep Temporal Context Network (ADTCN), where the parameters are tuned by the FHO. Hence, the developed model secures efficient leaf disease detection rate than the classical techniques in the experiential analysis.

Incorporating multimodal context information into traffic speed forecasting through graph deep learning

Accurate traffic speed forecasting is a prerequisite for anticipating future traffic status and increasing the resilience of intelligent transportation systems. However, most studies ignore the involvement of context information ubiquitously distributed over the urban environment to boost speed prediction. The diversity and complexity of context information also hinder incorporating it into traffic forecasting. Therefore, this study proposes a multimodal context-based graph convolutional neural network (MCGCN) model to fuse context data into traffic speed prediction, including spatial and temporal contexts. The proposed model comprises three modules, ie (a) hierarchical spatial embedding to learn spatial representations by organizing spatial contexts from different dimensions, (b) multivariate temporal modeling to learn temporal representations by capturing dependencies of multivariate temporal contexts and (c) attention-based multimodal fusion to integrate traffic speed with the spatial and temporal context representations for multi-step speed prediction. We conduct extensive experiments in Singapore. Compared to the baseline model (spatial-temporal graph convolutional network, STGCN), our results demonstrate the importance of multimodal contexts with the mean-absolute-error improvement of 0.29 km/h, 0.45 km/h and 0.89 km/h in 30-min, 60-min and 120-min speed prediction, respectively. We also explore how different contexts affect traffic speed forecasting, providing references for stakeholders to understand the relationship between context information and transportation systems.

Riding a bicycle while building its wheels: the process of machine learning-based capability development and IT-business alignment practices

PurposeRecent advancements in Artificial Intelligence (AI) and, at its core, Machine Learning (ML) offer opportunities for organizations to develop new or enhance existing capabilities. Despite the endless possibilities, organizations face operational challenges in harvesting the value of ML-based capabilities (MLbC), and current research has yet to explicate these challenges and theorize their remedies. To bridge the gap, this study explored the current practices to propose a systematic way of orchestrating MLbC development, which is an extension of ongoing digitalization of organizations.Design/methodology/approachData were collected from Finland's Artificial Intelligence Accelerator (FAIA) and complemented by follow-up interviews with experts outside FAIA in Europe, China and the United States over four years. Data were analyzed through open coding, thematic analysis and cross-comparison to develop a comprehensive understanding of the MLbC development process.FindingsThe analysis identified the main components of MLbC development, its three phases (development, release and operation) and two major MLbC development challenges: Temporal Complexity and Context Sensitivity. The study then introduced Fostering Temporal Congruence and Cultivating Organizational Meta-learning as strategic practices addressing these challenges.Originality/valueThis study offers a better theoretical explanation for the MLbC development process beyond MLOps (Machine Learning Operations) and its hindrances. It also proposes a practical way to align ML-based applications with business needs while accounting for their structural limitations. Beyond the MLbC context, this study offers a strategic framework that can be adapted for different cases of digital transformation that include automation and augmentation of work.

Electrophysiological signatures of temporal context in the bisection task.

Despite having relatively accurate timing, subjective time can be influenced by various contexts, such as stimulus spacing and sample frequency. Several electroencephalographic (EEG) components have been associated with timing, including the contingent negative variation (CNV), offset P2, and late positive component of timing (LPCt). However, the specific role of these components in the contextual modulation of perceived time remains unclear. In this study, we conducted two temporal bisection experiments to investigate this issue. Participants had to judge whether a test duration was close to a short or long standard. Unbeknownst to them, we manipulated the stimulus spacing (Experiment 1) and sample frequency (Experiment 2) to create short and long contexts while maintaining consistent test ranges and standards across different sessions. The results revealed that the bisection threshold shifted towards the ensemble mean, and both CNV and LPCt were sensitive to context modulation. In the short context, the CNV exhibited an increased climbing rate compared to the long context, whereas the LPCt displayed reduced amplitude and latency. These findings suggest that the CNV represents an expectancy wave preceding a temporal decision process, while the LPCt reflects the decision-making process itself, with both components influenced by the temporal context.

A point‐image fusion network for event‐based frame interpolation

AbstractTemporal information in event streams plays a critical role in event‐based video frame interpolation as it provides temporal context cues complementary to images. Most previous event‐based methods first transform the unstructured event data to structured data formats through voxelisation, and then employ advanced CNNs to extract temporal information. However, voxelisation inevitably leads to information loss, and processing the sparse voxels introduces severe computation redundancy. To address these limitations, this study proposes a point‐image fusion network (PIFNet). In our PIFNet, rich temporal information from the events can be directly extracted at the point level. Then, a fusion module is designed to fuse complementary cues from both points and images for frame interpolation. Extensive experiments on both synthetic and real datasets demonstrate that our PIFNet achieves state‐of‐the‐art performance with high efficiency.

The Impact of Construction Systems Technology in Contemporary Architectural Product

This research examines the impact of construction technology systems in contemporary architectural production through the study of the evolution in it systems, construction materials and methods of construction in addition to the digital revolution which provided possibilities of structural and architectural design in creating a distinct architectural product, as considered construction systems technology is the source of creativity in the architectural product, the research is assumed that the construction systems technology have achieved a structural innovation in production through the materials and methods of construction and digital design.For Long time technology was connected to the global trend, but the contemporary trends of technology pointed out the possibility of achieving the character of place and confirm locality through construction systems technology, And it became this research to clarify the concept of construction systems technology through the definition of the concepts of the system in general and structural system in particular to identify aspects that supports the technological development of construction systems Which are summarized first, then analyze the relationship between construction systems technology and architectural product. The research reached to build a theoretical framework for the main and secondary vocabularies of construction systems technology and their possible formulations and their applications in a number of architectural projects that have defined by the literatures as excellence in construction technology systems . The research pointed out the role of technology and its progress and development in all fields, especially in the use and development of construction materials and methods of construction as well as advances in the computer applications in creating distinctive architecture within its spatial - temporal context.