Search

Object detection is one of the most fundamental yet challenging research topics in the domain of computer vision. Recently, the study on this topic in aerial images has made tremendous progress. However, complex background and worse imaging quality are obvious problems in aerial object detection. Most state-of-the-art approaches tend to develop elaborate attention mechanisms for the space-time feature calibrations with arduous computational complexity, while surprisingly ignoring the importance of feature calibrations in channel-wise. In this work, we propose a simple yet effective calibrated-guidance (CG) scheme to enhance channel communications in a feature transformer fashion, which can adaptively determine the calibration weights for each channel based on the global feature affinity correlations. Specifically, for a given set of feature maps, CG first computes the feature similarity between each channel and the remaining channels as the intermediary calibration guidance. Then, rerepresenting each channel by aggregating all the channels weighted together via the guidance operation. Our CG is a general module that can be plugged into any deep neural networks, which is named as CG-Net. To demonstrate its effectiveness and efficiency, extensive experiments are carried out on both oriented object detection task and horizontal object detection task in aerial images. Experimental results on two challenging benchmarks (i.e., DOTA and HRSC2016) demonstrate that our CG-Net can achieve the new state-of-the-art performance in accuracy with a fair computational overhead. The source code has been open sourced at https://github.com/WeiZongqi/CG-Net.

It is essential to avoid opportunistic behaviors of food supply chain members to guarantee food safety and sustainable supply. This research adopted the perspective of supply chain membership governance to discuss the critical mechanisms of opportunistic behavior avoidance and performance improvement in the food supply chain. Two information-sharing mechanisms (information sharing with customers and information sharing with suppliers) were used as mediating variables to explore the mechanisms of how social control, information sharing, and opportunistic behavior worked on supply chain performance. Furthermore, an online questionnaire survey was conducted to collect 210 data samples from the food manufacturing industry in China, and the structural equation model method was applied to test the research hypotheses. According to the empirical research findings, social control can directly reduce opportunistic behaviors of supply chain members and reduce such behaviors indirectly via the mediating factor of information sharing; social control affects the supply chain performance via the mediating factors of information sharing and opportunistic behavior, instead of directly improving supply chain performance. Two information sharing mechanisms vary in their mechanism of influence. Information sharing with customers reduces opportunistic behaviors, but does not directly improve supply chain performance. Information sharing with suppliers enhances supply chain performance and reduces opportunistic behaviors. This research offers theoretical and practical suggestions for performance improvement and opportunistic behavior avoidance to promote food supply chain management.

Based on the enterprise knowledge-based view, this study follows the basic logic of “knowledge acquisition-knowledge transformation-knowledge creation” to explore the effects of cross-border search and knowledge co-creation on the service innovation performance of manufacturing enterprises. Furthermore, compositional capability is introduced to investigate the moderator in the connection of knowledge co-recreation and service innovation performance. We collected 378 samples from the organizations that are taking servicizing transformation in China’s manufacturing industry. Then we applied structural equation modeling (SEM) to test our research model. The results reveal that both cross-border technological knowledge search and cross-border market knowledge search can significantly improve embedded knowledge co-creation and alliance-based knowledge creation of manufacturing enterprises, and then, directly and indirectly, boost service innovation performance. Compositional capability positively moderates the relationship between embedded knowledge co-creation and service innovation performance. This study provides theoretical and practical guidance for knowledge-based service innovation in China’s manufacturing industry.

Based on the resource orchestration theory, this study built a research model to understand the effect of supply chain network insight and supply chain integration on enterprise performance. We also involved the contingency theory to investigate the moderating effect of environmental uncertainty on supply chain integration and enterprise performance. We collected the data samples from 405 enterprises and used the SEM approach to verify the model. Results demonstrated the direct path of network insight to promote enterprise performance, the indirect path of supply chain integration as a mediating factor, and the role of environmental uncertainty as a boundary condition for the relationship between supply chain integration and enterprise performance, thus making theoretical and practical contributions to the management of supply chain resources and relationships and the performance enhancement of manufacturing.