Search results

Based on the strong feature representation ability of the convolutional neural network (CNN), generous object detection methods in remote sensing (RS) have been proposed one after another. However, due to the large variation in scale and the omission of relevant relationships between objects, there are still great challenges for object detection in RS. Most object detection methods fail to take the difficulties of detecting small and medium-sized objects and global context into account. Moreover, inference time and lightness are also major pain points in the field of RS.

To alleviate the aforementioned problems, this study proposes a novel method for object detection in RS, which is called lightweight object detection with a multi-receptive field and long-range dependency in RS images (MFLD). The multi-receptive field extraction (MRFE) and long-range dependency information extraction (LDIE) modules are put forward.

To concentrate on the variability of objects in RS, MRFE effectively expands the receptive field by a combination of atrous separable convolutions with different dilated rates. Considering the shortcomings of CNN in extracting global information, LDIE is designed to capture the relationships between objects. Extensive experiments over public datasets in RS images demonstrate that our MFLD method surpasses the state-of-the-art methods. Most of all, on the NWPU VHR-10 dataset, our MFLD method achieves 94.6% mean average precision with 4.08 M model volume.

This paper proposed a method called lightweight object detection with multi-receptive field and long-range dependency in RS images.

Assembly action recognition plays an important role in assembly process monitoring and human-robot collaborative assembly. Previous works overlook the interaction relationship between hands and operated objects and lack the modeling of subtle hand motions, which leads to a decline in accuracy for fine-grained action recognition. This paper aims to model the hand-object interactions and hand movements to realize high-accuracy assembly action recognition.

In this paper, a novel multi-stream hand-object interaction network (MHOINet) is proposed for assembly action recognition. To learn the hand-object interaction relationship in assembly sequence, an interaction modeling network (IMN) comprising both geometric and visual modeling is exploited in the interaction stream. The former captures the spatial location relation of hand and interacted parts/tools according to their detected bounding boxes, and the latter focuses on mining the visual context of hand and object at pixel level through a position attention model. To model the hand movements, a temporal enhancement module (TEM) with multiple convolution kernels is developed in the hand stream, which captures the temporal dependences of hand sequences in short and long ranges. Finally, assembly action prediction is accomplished by merging the outputs of different streams through a weighted score-level fusion. A robotic arm component assembly dataset is created to evaluate the effectiveness of the proposed method.

The method can achieve the recognition accuracy of 97.31% and 95.32% for coarse and fine assembly actions, which outperforms other comparative methods. Experiments on human-robot collaboration prove that our method can be applied to industrial production.

The author proposes a novel framework for assembly action recognition, which simultaneously leverages the features of hands, objects and hand-object interactions. The TEM enhances the representation of dynamics of hands and facilitates the recognition of assembly actions with various time spans. The IMN learns the semantic information from hand-object interactions, which is significant for distinguishing fine assembly actions.

This study aims to explore how coworkers leverage epistemic objects and guanxi (a Chinese term defining relationships based on mutual dependence) network to promote knowledge integration of “who knows what” in the development of sustainable innovation.

This study used a mixed-methods research approach, including quantitative questionnaires, social network analyses and a qualitative ethnography, all of which were collected from a large enterprise in China.

Epistemic objects can promote knowledge integration of “who knows what” among coworkers during their innovation development process. In addition, structural holes in a coworker network will impede knowledge integration of “who knows what,” but guanxi can turn this impeding effect into a facilitating effect.

First, the focus on the role of epistemic objects in eliciting knowledge generates implications for creating employee identity and coordinating knowledge heterogeneity. Second, by demonstrating how epistemic objects trigger both affective and cognitive trust to promote knowledge integration of “who knows what,” the authors complement existing studies of knowledge management (KM). Third, by presenting how coworkers fill their structural holes in their collaborative innovation, the study reveals the nature of connecting the appropriate resources with the appropriate needs, which generates implications for social capital integration and innovation enhancement. Fourth, by showing how “structural hole controllers” become “structural hole fillers” under different conditions, the authors recognize the different ways in which brokers leverage their structural holes and highlight the unique role of Chinese guanxi culture in triggering a structural hole filling behavior, thereby contributing to the literature of structural hole theory and culture management. Fifth, by creating a full picture of how coworkers strategically leverage their knowledge of “who knows what” in the development of sustainable innovation, the authors identify the influential factor that stimulates innovation, adding to the literature on the interaction between KM and innovation. Sixth, the emphasis on the independent role of epistemic objects produces an implication for the interplay between object-control and human-control in innovation work.

This study supports organizational leaders to make optimal decisions in their innovation development process by suggesting them to invest in developing an integrated knowledge of “who knows what.” To achieve it, the authors suggest managers make good use of non-human artifacts to gain the identification with the knowledge of not only themselves but also the whole team, and award the “integrator” an honor for filling structural holes that may trigger the creation of more structural hole fillers. Furthermore, the focus on the independent role of epistemic objects as knowledge elicitors and trust triggers in innovation work generates another practical implication for managers to rethink the controlling role of objects and humans in the organization and modify their managerial practices accordingly.

By exploring how coworkers leverage epistemic objects and guanxi network to promote knowledge integration of “who knows what” in the development of sustainable innovation, this study reveals the role of object-control and human-control in facilitating knowledge practices for stimulating innovation, thereby contributing to the literature of KM and innovation.

This paper considers how knowledge has been organized about museum objects and belongings at the Museum of Anthropology, in what is now known as British Columbia, and proposes the concept of historical or provenance warrant to understand how cataloguing decisions were made and are limited by current museum systems.

Through interviews and archival research, we trace how cataloguing was done at the museum through time and some of the challenges imposed by historical documentation systems.

Reading from the first attempts at standardizing object nomenclatures in the journals of private collectors to the contemporary practices associated with object documentation in the digital age, we posit that historic or provenance warrant is crafted through donor attribution or association, object naming, the concept of geo-cultural location and the imposition of unique identifiers, numbers and direct labels that physically mark belongings.

The ultimate goal and contribution of this research is to understand and describe the systems that structure and organize knowledge, in an effort to repair the history and terminologies moving forward.

The involvement of clients in service encounters and service development has become a central principle for contemporary health and social care organizations. However, in day-to-day work settings, the shift toward client involvement is still in progress. We examined how health and social care professionals, together with clients and managers, co-develop their conceptions of client involvement and search for practical ways in which to implement these in organizational service processes.

The empirical case of this study was a developmental intervention, the client involvement workshop, conducted in a Finnish municipal social and welfare center. The cultural-historical activity theory (CHAT) framework was used to analyze the development of client involvement ideas and the modes of interaction during the intervention.

Analysis of the collective discussion revealed that the conceptions of client involvement developed through two interconnected object-orientations: Enabling client involvement in service encounters and promoting client involvement in the service system. The predominant mode of interaction in the collective discussion was that of “coordination.” The clients' perspective and contributions were central aspects in the turning points from coordination to cooperation; professionals crossed organizational boundaries, and together with clients, constructed a new client involvement-based object. This suggests that client participation plays an important role in the development of services.

The CHAT-based examination of the modes of interaction clarifies the potential of co-developing client-involvement-based services and highlights the importance of clients' participation in co-development.

The research focuses on determining the prospects for improving the practice of accounting, reflecting in International Financial Reporting Standards (IFRS), and managing intellectual property objects in Uzbekistan based on international experience. Using data from the World Bank's 2022 statistics and regression analysis, the authors model the impact of a set of managerial measures on the manifestations of creating and applying intellectual property objects. The authors conclude that nonfinancial measures are preferable, with human resource management (HRM) in research and development (R&D) being a prospective choice for managing the creation and application of intellectual property objects. The theoretical significance lies in justifying the need to reflect an expanded list of intellectual property objects in IFRS. The research also justifies the conditions for effective management of intellectual property objects, that are a rejection of financial measures and reliance on and active use of nonfinancial management measures. The managerial significance is reflected in the newly developed nonfinancial approach to accounting, reflecting in IFRS and managing intellectual property objects. This approach can enhance the efficiency of such management in knowledge-intensive and high-tech industries, unlocking the potential of IFRS to support the development of the knowledge economy. The practical significance lies in offering author recommendations for improving the practice of accounting, reflecting in IFRS, and managing intellectual property objects in Uzbekistan. Implementing these recommendations in the practice of IFRS and corporate accounting in Uzbekistan could propel the country toward a leading model in the knowledge economy and strengthen its position in global high-tech markets.

Advances in material agency driven by artificial intelligence (AI) have facilitated breakthroughs in material adaptivity enabling smart objects to autonomously provide individualized smart services, which makes smart objects act as social actors embedded in the real world. However, little is known about how material adaptivity fosters the infusion use of smart objects to maximize the value of smart services in customers' lives. This study examines the underlying mechanism of material adaptivity (task and social adaptivity) on AI infusion use, drawing on the theoretical lens of social embeddedness.

This study adopted partial least squares structural equation modeling (PLS-SEM), mediating tests, path comparison tests and polynomial modeling to analyze the proposed research model and hypotheses.

The results supported the proposed research model and hypotheses, except for the hypothesis of the comparative effects on infusion use. Besides, the results of mediating tests suggested the different roles of social embeddedness in the impacts of task and social adaptivity on infusion use. The post hoc analysis based on polynomial modeling provided a possible explanation for the unsupported hypothesis, suggesting the nonlinear differences in the underlying influencing mechanisms of instrumental and relational embeddedness on infusion use.

The formation mechanisms of AI infusion use based on material adaptivity and social embeddedness help to develop the business strategies that enable smart objects as social actors to exert a key role in users' daily lives, in turn realizing the social and economic value of AI.

This study advances the theoretical research on material adaptivity, updates the information system (IS) research on infusion use and identifies the bridging role of social embeddedness of smart objects as agentic social actors in the AI context.

This paper aims to provide an integrated BIM-based approach for quantity take-off for progress payments in the context of high-rise buildings in Vietnam. It tries to find answers for the following questions: (1) When to start the QTO processes to facilitate the contract progress payments? (2) What information is required to measure the quantity of works to estimate contract progress payment (3) What are the challenges to manage (i.e. create, store, update and exploit)? What are the required information for this BIM use? and (4) How to process the information to deliver BIM-based QTO to facilitate contract progress payment?

The paper applied a deductive approach and expert consensus through a Delphi procedure to adapt to current innovation around BIM-based QTO. Starting with a literature review, it then discusses current practices in BIM-based QTO in general and high-rise building projects in particular. Challenges were compiled from the previous studies for references for BIM-based QTO to facilitate contract progress payment for high-rise building projects in Vietnam. A framework was developed considering a standard information management process throughout the construction lifecycle, when the BIM use of this study is delivered. The framework was validated with Delphi technique.

Four major challenges for BIM-based QTO discovered: new types of information required for the BIM model, changes and updates as projects progress, low interoperability between BIM model and estimation software, potentiality of low productivity and accuracy in data entry. Required information for QTO to facilitate progress payments in high-rise building projects include Object Geometric/Appearance Information, Structural Components' Definition and Contextual Information. Trade-offs between “Speed – Level of Detail–Applicable Breadth” and “Quality – Productivity” are proposed to consider the information amount to input at a time when creating/updating BIM objects. Interoperability check needed for creating, authoring/updating processing the BIM model's objects.

This paper is not flawless. The first limitation lies in that the theoretical framework was established only based on desk research and small number of expert judgment. Further primary data collection would be needed to determine exactly how the framework underlies widespread practices. Secondly, this study only discussed the quantity take-off specifically for contract progress payment, but not for other purposes or broader BIM uses. Further research in this field would be of great help in developing a standard protocol for automatic quantity surveying system in Vietnam.

A new theoretical framework for BIM-based QTO validated with Delphi technique to facilitate progress payments for high-rise building projects, considering all information management stages and the phases of information development in the project lifecycle. The framework identified four types of information required for this QTO, detailed considerations for strategies (Library Objects Development, BIM Objects Information Declaration, BIM-based QTO) for better managing the information for this BIM use. Two trade-offs of “Speed – LOD–Applicable Breadth” and “Quality – Productivity” have been proposed for facilitating the strategies and also for enhancing the total efficiency and effectiveness of the QTO process.

The purpose of this paper is to address the challenging issue of developing a quantitative approach for the representation of cultural significance data in heritage information systems (HIS). The authors propose to provide experts in the field with a dedicated framework to structure and integrate targeted data about historical objects' significance in such environments.

This research seeks the identification of key indicators which allow to better inform decision-makers about cultural significance. Identified concepts are formalized in a data structure through conceptual data modeling, taking advantage on unified modeling language (HIS). The design science research (DSR) method is implemented to facilitate the development of the data model.

This paper proposes a practical solution for the formalization of data related to the significance of objects in HIS. The authors end up with a data model which enables multiple knowledge representations through data analysis and information retrieval.

The framework proposed in this article supports a more sustainable vision of heritage preservation as the framework enhances the involvement of all stakeholders in the conservation and management of historical sites. The data model supports explicit communications of the significance of historical objects and strengthens the synergy between the stakeholders involved in different phases of the conservation process.

The accuracy and reliability of upper limb motion assessment have received great attention in the field of rehabilitation. Grasping test is widely carried out for motion assessment, which requires patients to grasp objects and move them to target place. The traditional assessments test the upper limb motion ability by therapists, which mainly relies on experience and lacks quantitative indicators. This paper aims to propose a deep learning method based on the vision system of our upper limb rehabilitation robot to recognize the motion trajectory of rehabilitation target objects automatically and quantitatively assess the upper limb motion in the grasping test.

To begin with, an SRF network is designed to recognize rehabilitation target objects grasped in assessment tests. Moreover, the upper limb motion trajectory is calculated through the motion of objects’ central positions. After that, a GAE network is designed to analyze the motion trajectory which reflects the motion of upper limb. Finally, based on the upper limb rehabilitation exoskeleton platform, the upper limb motion assessment tests are carried out to show the accuracy of both object recognition of SRF network and motion assessment of GAE network. The results including object recognition, trajectory calculation and deviation assessment are given with details.

The performance of the proposed networks is validated by experiments that are developed on the upper limb rehabilitation robot. It is implemented by recognizing rehabilitation target objects, calculating the motion trajectory and grading the upper limb motion performance. It illustrates that the networks, including both object recognition and trajectory evaluation, can grade the upper limb motion functionn accurately, where the accuracy is above 95.0% in different grasping tests.

A novel assessment method of upper limb motion is proposed and verified. According to the experimental results, the accuracy can be remarkably enhanced, and the stability of the results can be improved, which provide more quantitative indicators for further application of upper limb motion assessment.