检索结果-内蒙古大学图书馆

Spatiotemporal Action Detection Based on Fine-Grained

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Cheng, Yan Mike, Jack Fang, Chengxing Huang, Jiawen Wen, Yu School of Software Jiangxi Normal University Nanchang330022 China School of Computer Information Engineering Jiangxi Normal University Nanchang330022 China Business College of Jiangxi Normal University Nanchang330022 China Key Laboratory of Intelligent Information Processing and Emotional Computing in Jiangxi Province Nanchang330022 China Shanxi Datong University China

In the field of computer vision, spatiotemporal action detection is a challenging task. Traditional methods such as YOWO have achieved certain results in real-time and accuracy, but still have shortcomings in dealing with missing detail information, capturing long-distance dependencies, and target overlap problems. In response to these issues, this article proposes a spatiotemporal action detection method based on fine-grained enhancement. Firstly, a dual path fine-grained enhancement module is designed to enhance the ability to extract fine-grained features;Secondly, the self-attention&convolution module was introduced, which can better capture long-distance dependencies and cross level feature relationships;Finally, in order to address the issue of target overlap, the SIoU loss function is introduced to more comprehensively evaluate the similarity between predicted boxes and real boxes. The experimental results show that the proposed method achieves 86.4% F-mAP and 52.6% V-mAP on the UCF101-24 dataset, 20.5% F-mAP on the AVA dataset, and only 44.0 GFlops with an FPS of 34, ensuring the real-time performance of the proposed method with higher accuracy than SOTA model. In addition, the ablation experiment further demonstrated the effectiveness of each module in this paper. Overall, this method significantly improves the accuracy of spatiotemporal action detection while maintaining high efficiency, providing an effective solution for real-time action detection. © 2024, The Authors. All rights reserved.

关键词： Feature extraction

PRISTA-Net: Deep Iterative Shrinkage Thresholding Network for Coded Diffraction Patterns Phase Retrieval

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liu, Aoxu Fan, Xiaohong Yang, Yin Zhang, Jianping The School of Mathematics and Computational Science Xiangtan University Hunan Key Laboratory for Computation and Simulation in Science and Engineering Xiangtan411105 China The School of Mathematics and Computational Science Xiangtan University the Key Laboratory of Intelligent Computing & Information Processing the Ministry of Education Xiangtan411105 China The School of Mathematics and Computational Science Xiangtan University the National Center for Applied Mathematics in Hunan Xiangtan411105 China

The problem of phase retrieval (PR) involves recovering an unknown image from limited amplitude measurement data and is a challenge nonlinear inverse problem in computational imaging and image processing. However, many of the PR methods are based on black-box network models that lack interpretability and plug-and-play (PnP) frameworks that are computationally complex and require careful parameter tuning. To address this, we have developed PRISTA-Net, a deep unfolding network (DUN) based on the first-order iterative shrinkage thresholding algorithm (ISTA). This network utilizes a learnable nonlinear transformation to address the proximal-point mapping sub-problem associated with the sparse priors, and an attention mechanism to focus on phase information containing image edges, textures, and structures. Additionally, the fast Fourier transform (FFT) is used to learn global features to enhance local information, and the designed logarithmic-based loss function leads to significant improvements when the noise level is low. All parameters in the proposed PRISTA-Net framework, including the nonlinear transformation, threshold parameters, and step size, are learned end-to-end instead of being manually set. This method combines the interpretability of traditional methods with the fast inference ability of deep learning and is able to handle noise at each iteration during the unfolding stage, thus improving recovery quality. Experiments on Coded Diffraction Patterns (CDPs) measurements demonstrate that our approach outperforms the existing state-of-the-art methods in terms of qualitative and quantitative evaluations. Our source codes are available at https://***/liuaxou/PRISTA-Net. Copyright © 2023, The Authors. All rights reserved.

关键词： Mapping

Attributed Multi-order Graph Convolutional Network for Heterogeneous Graphs

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Chen, Zhaoliang Wu, Zhihao Zhong, Luying Plant, Claudia Wang, Shiping Guo, Wenzhong College of Computer and Data Science Fuzhou University Fuzhou350116 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350116 China Faculty of Computer Science University of Vienna Vienna1090 Austria ds:UniVie Vienna1090 Austria

Heterogeneous graph neural networks aim to discover discriminative node embeddings and relations from multi-relational networks. One challenge of heterogeneous graph learning is the design of learnable meta-paths, which significantly influences the quality of learned embeddings. Thus, in this paper, we propose an Attributed Multi-Order Graph Convolutional Network (AMOGCN), which automatically studies meta-paths containing multi-hop neighbors from an adaptive aggregation of multi-order adjacency matrices. The proposed model first builds different orders of adjacency matrices from manually designed node connections. After that, an intact multi-order adjacency matrix is attached from the automatic fusion of various orders of adjacency matrices. This process is supervised by the node semantic information, which is extracted from the node homophily evaluated by attributes. Eventually, we utilize a one-layer simplifying graph convolutional network with the learned multi-order adjacency matrix, which is equivalent to the cross-hop node information propagation with multi-layer graph neural networks. Substantial experiments reveal that AMOGCN gains superior semi-supervised classification performance compared with state-of-the-art competitors. Copyright © 2023, The Authors. All rights reserved.

关键词： Graph neural networks

BGRA-Net: Boundary-Guided and Region-Aware Convolutional Neural Network for the Segmentation of Breast Ultrasound Images

学校读者我要写书评

暂无评论

BGRA-Net: Boundary-Guided and Region-Aware Convolutional Neu...

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Xiang Zhang Xuanya Li Kai Hu Xieping Gao Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University Xiangtan China Baidu Inc. Beijing China Key Laboratory of Medical Imaging and Artifical Intelligence of Hunan Province Xiangnan University Chenzhou China Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha China

ISBN: (纸本)9781665429825

In this paper, we propose a novel convolutional neural network based on boundary-guided and region-aware (BGRA-Net) for breast tumor segmentation in ultrasound images. In particular, in the encoding stage, we propose a boundary-guided module (BGM) to guide the learning of boundary features in the decoding stage by explicitly strengthening the extracted boundary information. Meanwhile, in the decoding stage, we propose a region-aware module (RAM) to integrate different levels of detailed and semantic features to improve the comprehensive representation of tumor regional features. Besides, a scale-adaptive module (SAM) is further proposed to capture the characteristics of tumors with different sizes between the encoding and decoding stages. To evaluate the effectiveness of our BGRA-Net, we conduct extensive experiments on the UDIAT dataset and compare it with eight state-of-the-art methods. The experimental results show that our BGRA-Net outperforms the state-of-the-art methods and can achieve accurate segmentation of breast tumors with ambiguous boundaries.

关键词： Deep learning Image segmentation Breast tumors Ultrasonic imaging Semantics Feature extraction Visual effects

Distributed Online Private Learning of Convex Nondecomposable Objectives

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Cheng, Huqiang Liao, Xiaofeng Li, Huaqing Key Laboratory of Dependable Services Computing in Cyber Physical Society-Ministry of Education College of Computer Science Chongqing University Chongqing400044 China Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information Engineering Southwest University Chongqing400715 China

In the machine learning domain, datasets share several new features, including distributed storage, high velocity, and privacy concerns, which naturally requires the development of distributed privacy-preserving algorithms. Moreover, nodes (e.g., learners, sensors, GPUs, mobiles, etc.) in the real networks usually process tasks in real time, which inevitably requires nodes to have online learning capabilities. Therefore, we deal with a general distributed constrained online learning problem with privacy over time-varying networks, where a class of nondecomposable objectives are considered. Under this setting, each node only controls a part of the global decision, and the goal of all nodes is to collaboratively minimize the global cost over a time horizon T while guarantees the security of the transmitted information. For such problems, we first design a novel generic algorithm framework, named as DPSDA, of differentially private distributed online learning using the Laplace mechanism and the stochastic variants of dual averaging method. Note that in the dual updates, all nodes of DPSDA employ the noise-corrupted gradients for more generality. Then, we propose two algorithms, named as DPSDA-C and DPSDA-PS, under this framework. In DPSDA-C, the nodes implement a circulation-based communication in the primal updates so as to alleviate the disagreements over time-varying undirected networks. In addition, for the extension to time-varying directed ones, the nodes implement the broadcast-based push-sum dynamics in DPSDA-PS, which can achieve average consensus over arbitrary directed networks. Theoretical results show that both algorithms attain an expected regret upper bound in O(√T) when the objective function is convex, which matches the best utility achievable by cutting-edge algorithms. Finally, numerous numerical experiments on both synthetic and real-world datasets verify the effectiveness of our algorithms. © 2022, CC BY.

关键词： Stochastic systems

Multi-user Dual-function Radar-communications System Based on Circulating Code Array

学校读者我要写书评

暂无评论

Multi-user Dual-function Radar-communications System Based o...

2021 CIE International Conference on Radar, Radar 2021

作者： Zhang, Qiuyue Feng, Cunqian Gu, Yabin Zhang, Linrang Zhou, Yu Chen, Zhanye Air and Missile Defense College Air Force Engineering University Xi'an China Shannxi Huanghe Group Company Ltd. Xi'an China Xidian University National Laboratory of Radar Signal Processing Xi'an China Chongqing University Chongqing Key Laboratory of Space Information Network and Intelligent Information Fusion Chongqing China

ISBN: (纸本)9781665498142

To ease the shortage of the spectrum resource, a dual-function radar-communications (DFRC) system based on circulating code array is proposed in this paper. The relationship between the spectrum of the synthesized signal and the spatial angle is firstly analyzed. By utilizing this relationship, different frequency bands can be allocated to multiple different communication users located in different spatial directions. Radar and communication receiving processing procedures are analyzed secondly. At the communication receiver, the relationship between the spectrum of the transmitted basic waveform and the spectrum of the synthesized waveform of circulating code array provides the possibility to demodulate the communication symbols from the received signal. The proposed DFRC system requires only one transmitted basic waveform to implement multi-user communication transmission and radar detection simultaneously. It is verified that the designed method can use different modulation schemes to simultaneously transmit information to multiple communication users located in different directions without sacrificing radar detection performance. Simulation results are presented to validate the performance of the designed DFRC system. © 2021 IEEE.

关键词： BER circulating code array DFRC radar detection

Computationally Expensive High-Dimensional Multiobjective Optimization via Surrogate-Assisted Reformulation and Decomposition

学校读者我要写书评

暂无评论

IEEE Transactions on Evolutionary Computation 2024年 1-1页

作者： Pan, Linqiang Lin, Jianqing Wang, Handing He, Cheng Tan, Kay Chen Jin, Yaochu School of Artificial Intelligence and Automation Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China Huazhong University of Science and Technology Wuhan China School of Artificial Intelligence Xidian University Xi’an China School of Electrical and Electronic Engineering Huazhong University of Science and Technology Wuhan China Department of Computing The Hong Kong Polytechnic University Hong Kong Hong Kong School of Engineering Trustworth and General Artificial Intelligence Laboratory Westlake University Hangzhou China

In recent decades, various surrogate-assisted evolutionary algorithms (SAEAs) have been proposed to solve computationally expensive multiobjective optimization problems (EMOPs). Nevertheless, designing an SAEA to handle high-dimensional EMOPs and balance convergence, diversity, and computational complexity remains challenging. Here, we propose a two-phase SAEA (TP-SAEA), which follows the idea of convergence first and diversity second, for solving high-dimensional EMOPs. In Phase I, a surrogate-assisted problem reformulation method is proposed to fast-track the Pareto optimal set in association with some reference solutions. Specifically, the high-dimensional EMOP is reformulated into an expensive single-objective one with low-dimensional decision space. Then, the surrogate-assisted optimization is utilized to obtain well-converged solutions. In Phase II, the high-dimensional EMOP is decomposed into two subproblems to explore subregions of the decision space that can effectively promote the diversity of the solutions. The two subproblems are optimized independently via surrogate-assisted optimization, aiming to push the population towards different regions of the Pareto optimal front. Experiments are conducted on EMOPs with 100 to 500 decision variables compared with four state-of-the-art SAEAs. The proposed TP-SAEA obtains well-converged and diverse solutions with only 509 real function evaluations. Moreover, its superiority is examined in six real-world instances with up to 12,000 decision variables. IEEE

关键词： Iron

Quasi-cyclic perfect codes in Doob graphs and special partitions of Galois rings

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Shi, Minjia Li, Xiaoxiao Krotov, Denis S. Özbudak, Ferruh Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education School of Mathematical Sciences Anhui University Hefei230601 China School of Mathematical Sciences Anhui University Hefei230601 China Sobolev Institute of Mathematics pr. Akademika Koptyuga 4 Novosibirsk630090 Russia Faculty of Engineering and Natural Sciences Sabancı University Middle East Technical University 34956 Istanbul Ankara06800 Turkey

The Galois ring GR(4∆) is the residue ring Z4[x]/(h(x)), where h(x) is a basic primitive polynomial of degree ∆ over Z4. For any odd ∆ larger than 1, we construct a partition of GR(4∆)\{0} into 6-subsets of type {a, b, −a−b, −a, −b, a+b} and 3-subsets of type {c, −c, 2c} such that the partition is invariant under the multiplication by a nonzero element of the Teichmuller set in GR(4∆) and, if ∆ is not a multiple of 3, under the action of the automorphism group of GR(4∆). As a corollary, this implies the existence of quasi-cyclic additive 1-perfect codes of index (2∆ − 1) in D((2∆ − 1)(2∆ − 2)/6, 2∆ − 1) where D(m, n) is the Doob metric scheme on Z2m+n .MSC Codes 94B99 Copyright © 2023, The Authors. All rights reserved.

关键词： Algebra

BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Yinhao Ge, Zheng Yu, Guanyi Yang, Jinrong Wang, Zengran Shi, Yukang Sun, Jianjian Li, Zeming Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS China University of Chinese Academy of Sciences China MEGVII Technology China Huazhong University of Science and Technology China Xi’an Jiaotong University China

In this research, we propose a new 3D object detector with a trustworthy depth estimation, dubbed BEVDepth, for camera-based Bird’s-Eye-View (BEV) 3D object detection. Our work is based on a key observation – depth estimation in recent approaches is surprisingly inadequate given the fact that depth is essential to camera 3D detection. Our BEVDepth resolves this by leveraging explicit depth supervision. A camera-awareness depth estimation module is also introduced to facilitate the depth predicting capability. Besides, we design a novel Depth Refinement Module to counter the side effects carried by imprecise feature unprojection. Aided by customized Efficient Voxel Pooling and multi-frame mechanism, BEVDepth achieves the new state-of-the-art 60.9% NDS on the challenging nuScenes test set while maintaining high efficiency. For the first time, the NDS score of a camera model reaches 60%. Code is released at https://***/Megvii-BaseDetection/BEVDepth. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection