The core task of object detection is to extract features of various sizes by hierarchically stacking multi-scale feature maps. However, it is not easy to decide whether we should transmit semantic information to the low layers while reducing the loss of semantic information of the high-level features. In this paper, we present a novel method to reduce the loss of semantic information, and at the same time to improve the object detection performance by using the attention mechanism on the high-level layer of the feature pyramid network. The proposed method focuses on the sparse spatial information using deformable convolution v2 (DCNv2) on the lateral connection in the feature pyramid network. Specifically, the upsampling process is divided into two branches. The first one pays attention to the global context information of high-level features, and the other rescales the feature map by interpolation. Finally, by multiplying the results from the two branches, we can obtain upsampling result that pays attention to semantic information of the high-level layer. The proposed pyramid attention upsampling module has three contributions. First, It can be easily applied to any models using feature pyramid network. Second, it is possible to reduce losses in semantic information of the high-level feature map by performing context attention of the high-level layer. Third, it improves the detection performance by stacking layers up to the low layer. We used MS-COCO 2017 detection dataset to evaluate the performance of the proposed method. Experimental results show that the proposed method provided better detection performance comparing with existing feature pyramid network-base methods.
The incorporation of metal oxide nanoparticles (NPs) in fiber filters is an effective approach to enhance the specific surface area and surface roughness of the fiber, hence improving their efficiency for fine dust capture and other gas treatment or biological applications. Nevertheless, uneven distribution of NPs limits their practical applications. In this study, a commercial silane coupling agent (3-methacryloxypropyltrimethoxysilane) was used to improve the dispersion of zinc oxide (ZnO) NPs in thin polyacrylonitrile fibers. Scanning electron microscopy (SEM) revealed that the fibers incorporating the silane-modified NPs exhibited better distribution of NPs than those prepared with pristine ZnO NPs. The silane modification enhanced the specific surface area, surface roughness, and fiber porosity. In particular, the nanofiber filter incorporating 12 wt% ZnO NPs modified with 0.5 g silane per g of ZnO NPs maintained a filtration efficiency of 99.76% with a low pressure drop of 44 Pa, excellent antibacterial activity, and could decompose organic methylene blue dye with an efficiency of 85.11% under visible light.
Various action recognition approaches have recently been proposed with the aid of three-dimensional (3D) convolution and a multiple stream structure. However, existing methods are sensitive to background and optical flow noise, which prevents from learning the main object in a video frame. Furthermore, they cannot reflect the accuracy of each stream in the process of combining multiple streams. In this paper, we present a novel action recognition method that improves the existing method using optical flow and a multi-stream structure. The proposed method consists of two parts: (i) optical flow enhancement process using image segmentation and (ii) score fusion process by applying weighted sum of the accuracy. The enhancement process can help the network to efficiently analyze the flow information of the main object in the optical flow frame, thereby improving accuracy. A different accuracy of each stream can be reflected to the fused score while using the proposed score fusion method. We achieved an accuracy of 98.2% on UCF-101 and 82.4% on HMDB-51. The proposed method outperformed many state-of-the-art methods without changing the network structure and it is expected to be easily applied to other networks.
No abstract
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.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.