Panoptic segmentation, which needs to assign a category label to each pixel and segment each object instance simultaneously, is a challenging topic. Traditionally, the existing approaches utilize two independent models without sharing features, which makes the pipeline inefficient to implement. In addition, a heuristic method is usually employed to merge the results. However, the overlapping relationship between object instances is difficult to determine without sufficient context information during the merging process. To address the problems, we propose a novel end-to-end Occlusion Aware Network (OANet) for panoptic segmentation, which can efficiently and effectively predict both the instance and stuff segmentation in a single network. Moreover, we introduce a novel spatial ranking module to deal with the occlusion problem between the predicted instances. Extensive experiments have been done to validate the performance of our proposed method and promising results have been achieved on the COCO Panoptic benchmark.
Divalent europium 5d-4f transition has aroused great attention in many fields, in a way of doping Eu2+ ions into inorganic solids. However, molecular Eu2+ complexes with 5d-4f transition are thought to be too air-unstable to explore their applications. In this work, we synthesized four Eu2+-containing azacryptates EuX2-Nn (X = Br, I, n = 4, 8) and systematically studied the photophysical properties in crystalline samples and solutions. Intriguingly, the EuX2-N8 complexes exhibit near-unity photoluminescence quantum yield, good air-/thermal-stability and mechanochromic property (X = I). Furthermore, we proved the application of Eu2+ complexes in organic light-emitting diodes (OLEDs) with high efficiency and luminance. The optimized device employing EuI2-N8 as emitter has the best performance as the maximum luminance, current efficiency, and external quantum efficiency up to 25470 cd m−2, 62.4 cd A−1, and 17.7%, respectively. Our work deepens the understanding of structure-property relationship in molecular Eu2+ complexes and could inspire further research on application in OLEDs.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.