More Like this

1. Sniffer Faster R-CNN ++: An Efficient Camera-LiDAR Object Detector with Proposal Refinement on Fused Candidates

   https://doi.org/10.1145/3631138  

   Dhakal, Sudip; Carrillo, Dominic; Qu, Deyuan; Yang, Qing; Fu, Song (April 2024, ACM Journal on Autonomous Transportation Systems)

   In this paper we present Sniffer Faster R-CNN++, an efficient Camera-LiDAR late fusion network for low complexity and accurate object detection in autonomous driving scenarios. The proposed detection network architecture operates on output candidates of any 3D detector and proposals from regional proposal network of any 2D detector to generate final prediction results. In comparison to the single modality object detection approaches, fusion based methods in many instances suffer from dissimilar data integration difficulties. On one hand, fusion based network models are complicated in nature and on the other hand they require large computational overhead and resources, processing pipelines for training and inference specially, the early fusion and deep fusion approaches. As such, we devise a late fusion network that in-cooperates pre-trained, single-modality detectors without change, performing association only at the detection level. In addition to this, lidar based method fail to detect distant object due to its sparse nature so we devise proposal refinement algorithm to jointly optimize detection candidates and assist detection for distant objects. Extensive experiments on both the 3D and 2D detection benchmark of challenging KITTI dataset illustrate that our proposed network architecture significantly improves the detection accuracy, accelerating the detection speed. 

   more » « less
2. A Family of Novel Switch Capacitor Based Integrated Matrix Autotransformer LLC Converter for Data Center Application

   https://doi.org/10.1109/GreenTech56823.2023.10173801  

   Qiu, Maohang; Wei, Mengxuan; Liu, Xiaoyan; Meng, Haoran; Cao, Dong (April 2023, IEEE)

   Switched Tank Converter(STC) is one kind of Resonant Switch Capacitor(ReSC) that can be considered as a good candidate for data center application with high power efficiency and high power density. On the other hand, LLC converter can also realize very good performance for low voltage application. Although STC can realize relatively higher efficiency than LLC converter in the light load since the core loss is saved, LLC can keep relatively higher efficiency in the heavy load than STC does since the conduction loss of LLC is smaller. The main reason is because transformer’s winding resistance is smaller than semiconductor devices’ resistance, and this is very important for high current application.In order to utilize the benefits of the STC and the LLC converter together, this paper proposes a family of the novel Switch Capacitor based Integrated Matrix Autotransformer LLC Converters (SCIMAC). The proposed converters share the same high voltage side circuit of the STC with low voltage stress devices. Different from the traditional LLC converter with an isolated transformer, the proposed SCIMAC utilizes one autotransformer with only the secondary side windings similar to LLC's secondary side. There are several advantages that can be realized of the SCIMAC: 1). Low figure of merit (FOM) devices can be adopted to realize higher efficiency due to the low voltage stress of the SCIMAC. 2). Higher power efficiency can be realized when compared with STC converter in heavy load because the resistance of the autotransformer’s windings is lower than semiconductor devices’ resistance. 3). The primary side winding loss of the transformer is saved to further increase the efficiency. 4) ZVS turning on can be realized by the magnetizing current of the core. 

   more » « less
3. Unsupervised Attributed Network Embedding via Cross Fusion

   https://doi.org/10.1145/3437963.3441763  

   Pan, Guosheng; Yao, Yuan; Tong, Hanghang; Xu, Feng; Lu, Jian (March 2021, WSDM)

   null (Ed.)

   Attributed network embedding aims to learn low dimensional node representations by combining both the network's topological structure and node attributes. Most of the existing methods either propagate the attributes over the network structure or learn the node representations by an encoder-decoder framework. However, propagation based methods tend to prefer network structure to node attributes, whereas encoder-decoder methods tend to ignore the longer connections beyond the immediate neighbors. In order to address these limitations while enjoying the best of the two worlds, we design cross fusion layers for unsupervised attributed network embedding. Specifically, we first construct two separate views to handle network structure and node attributes, and then design cross fusion layers to allow flexible information exchange and integration between the two views. The key design goals of the cross fusion layers are three-fold: 1) allowing critical information to be propagated along the network structure, 2) encoding the heterogeneity in the local neighborhood of each node during propagation, and 3) incorporating an additional node attribute channel so that the attribute information will not be overshadowed by the structure view. Extensive experiments on three datasets and three downstream tasks demonstrate the effectiveness of the proposed method. 

   more » « less
4. Spatiotemporal Modeling of Mitochondrial Network Architecture

   https://doi.org/10.1103/PRXLife.2.043002  

   Holt, Keaton B; Winter, Julius; Manley, Suliana; Koslover, Elena F (October 2024, PRX Life)

   In many cell types, mitochondria undergo extensive fusion and fission to form dynamic, responsive network structures that contribute to a number of homeostatic, metabolic, and signaling functions. The relationship between the dynamic interactions of individual mitochondrial units and the cell-scale network architecture remains an open area of study. In this work, we use coarse-grained simulations and approximate analytic models to establish how the network morphology is governed by local mechanical and kinetic parameters. The transition between fragmented structures and extensive networks is controlled by local fusion-to-fission ratios, network density, and geometric constraints. Similar fusion rate constants are found to account for the very different structures formed by mammalian networks (poised at the percolation transition) and well-connected budding yeast networks. Over a broad parameter range, the simulated network structures can be described by effective mean-field association constants that exhibit a nonlinear dependence on the microscopic nonequilibrium fusion, fission, and transport rates. Intermediate fusion rate constants are shown to result in the highest rates of network remodeling, with mammalian mitochondrial networks situated in a regime of high turnover. This spatially resolved modeling and simulation framework helps elucidate the emergence of cellular scale network structures, and allows for the quantitative extraction of microscopic kinetic parameters from past and future experimental data. Published by the American Physical Society2024 

   more » « less
5. An Enhanced Deep Convolutional Model for Spatiotemporal Image Fusion

   https://doi.org/10.3390/rs11242898  

   Tan, Zhenyu; Di, Liping; Zhang, Mingda; Guo, Liying; Gao, Meiling (December 2019, Remote Sensing)

   Earth observation data with high spatiotemporal resolution are critical for dynamic monitoring and prediction in geoscience applications, however, due to some technique and budget limitations, it is not easy to acquire satellite images with both high spatial and high temporal resolutions. Spatiotemporal image fusion techniques provide a feasible and economical solution for generating dense-time data with high spatial resolution, pushing the limits of current satellite observation systems. Among existing various fusion algorithms, deeplearningbased models reveal a promising prospect with higher accuracy and robustness. This paper refined and improved the existing deep convolutional spatiotemporal fusion network (DCSTFN) to further boost model prediction accuracy and enhance image quality. The contributions of this paper are twofold. First, the fusion result is improved considerably with brand-new network architecture and a novel compound loss function. Experiments conducted in two different areas demonstrate these improvements by comparing them with existing algorithms. The enhanced DCSTFN model shows superior performance with higher accuracy, vision quality, and robustness. Second, the advantages and disadvantages of existing deeplearningbased spatiotemporal fusion models are comparatively discussed and a network design guide for spatiotemporal fusion is provided as a reference for future research. Those comparisons and guidelines are summarized based on numbers of actual experiments and have promising potentials to be applied for other image sources with customized spatiotemporal fusion networks. 

   more » « less