检索结果-内蒙古大学图书馆

Transformer RGBT Tracking with Spatio-Temporal Multimodal Tokens

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Sun, Dengdi Pan, Yajie Lu, Andong Li, Chenglong Luo, Bin The Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education School of Artificial Intelligence Anhui University Hefei230601 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230026 China The Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China

Many RGBT tracking researches primarily focus on modal fusion design, while overlooking the effective handling of target appearance changes. While some approaches have introduced historical frames or fuse and replace initial templates to incorporate temporal information, they have the risk of disrupting the original target appearance and accumulating errors over time. To alleviate these limitations, we propose a novel Transformer RGBT tracking approach, which mixes spatio-temporal multimodal tokens from the static multimodal templates and multimodal search regions in Transformer to handle target appearance changes, for robust RGBT tracking. We introduce independent dynamic template tokens to interact with the search region, embedding temporal information to address appearance changes, while also retaining the involvement of the initial static template tokens in the joint feature extraction process to ensure the preservation of the original reliable target appearance information that prevent deviations from the target appearance caused by traditional temporal updates. We also use attention mechanisms to enhance the target features of multimodal template tokens by incorporating supplementary modal cues, and make the multimodal search region tokens interact with multimodal dynamic template tokens via attention mechanisms, which facilitates the conveyance of multimodal-enhanced target change information. Our module is inserted into the transformer backbone network and inherits joint feature extraction, search-template matching, and cross-modal interaction. Extensive experiments on three RGBT benchmark datasets show that the proposed approach maintains competitive performance compared to other state-of-the-art tracking algorithms while running at 39.1 FPS. Copyright © 2024, The Authors. All rights reserved.

关键词： Feature extraction

Stable Attribute Group Editing for Reliable Few-shot Image Generation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ding, Guanqi Han, Xinzhe Wang, Shuhui Wu, Shuzhe Jin, Xin Tu, Dandan Huang, Qingming The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Peng Cheng Laboratory Shenzhen518066 China Huawei Cloud EI Innovation Lab China

Few-shot image generation aims to generate data of an unseen category based on only a few samples. Apart from basic content generation, a bunch of downstream applications hopefully benefit from this task, such as low-data detection and few-shot classification. To achieve this goal, the generated images should guarantee category retention for classification beyond the visual quality and diversity. In our preliminary work, we present an "editing-based" framework Attribute Group Editing (AGE) for reliable few-shot image generation, which largely improves the performance compared with existing methods that require re-training a GAN with limited data. Nevertheless, AGE's performance on downstream classification is not as satisfactory as expected. This paper investigates the class inconsistency problem and proposes Stable Attribute Group Editing (SAGE) for more stable class-relevant image generation. Different from AGE which directly edits from a one-shot image, SAGE takes use of all given few-shot images and estimates a class center embedding based on the category-relevant attribute dictionary. Meanwhile, according to the projection weights on the category-relevant attribute dictionary, we can select category-irrelevant attributes from the similar seen categories. Consequently, SAGE injects the whole distribution of the novel class into StyleGAN's latent space, thus largely remains the category retention and stability of the generated images. Going one step further, we find that class inconsistency is a common problem in GAN-generated images for downstream classification. Even though the generated images look photo-realistic and requires no category-relevant editing, they are usually of limited help for downstream classification. We systematically discuss this issue from both the generative model and classification model perspectives, and propose to boost the downstream classification performance of SAGE by enhancing the pixel and frequency components. Extensive experime

关键词： Generative adversarial networks

FPGA demonstration for WLAN-OFDM baseband receiver

学校读者我要写书评

暂无评论

Journal of information Hiding and Multimedia Signal processing 2018年第5期9卷 1281-1292页

作者： Wu, Chih-Feng Shiue, Muh-Tian Sung, Tien-Wen Pan, Jeng-Shyang School of Information Science and Engineering Fujian University of Technology Fuzhou350118 China Department of Electrical Engineering National Central University Taoyuan32001 Taiwan College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian China Department of Information Management Chaoyang University of Technology Taichung41349 Taiwan

The FPGA demonstration for WLAN-OFDM baseband receiver is presented in this paper. In this OFDM baseband receiver, the CORDIC computing is employed to realize various arithmetics of baseband signal process and then to reduce the computational complexity of baseband receiver. For a large open office channel with 100 ns RMS delay spread, the measured EVMs of WLAN-OFDM baseband receiver are −13.3, −16.6, −25.4 and −31.0 dB for BPSK, QPSK, 16-QAM and 64-QAM, respectively. Finally, the physical design of WLAN-OFDM baseband receiver with 0.18 µm 1P6M CMOS technology indicates that the core area and power consumption are 1.2 mm2 (1094 µm × 1092 µm) and 33.2 mW, respectively, with supply voltage of 1.8 V and operating clock of 40 MHz. © 2018, Ubiquitous International. All rights reserved.

关键词： Signal to noise ratio

Discriminative feature combination selection for enhancing multiclass classification

学校读者我要写书评

暂无评论

Discriminative feature combination selection for enhancing m...

International Conference on Behavior, Economic and Social Computing (BESC)

作者： Aibo Song Wei Qian Zhiang Wu Jinghua Zhao School of Computer Science and Engineering Southeast University Nanjing China Jiangsu Provincial Key Laboratory of E-Business Nanjing University of Finance and Economics Nanjing China College of Information Science and Engineering Shandong University of Science and Technology Shandong China

Frequent pattern mining is commonly utilized to generate combined-feature candidates, yet many are non-discriminative and thus might be useless for predictive models. In this paper, we propose to use feature combinations derived from frequent patterns to obtain more accurate multiclass classification models. Specifically, we present a novel mathematics inference to show what are discriminative feature combinations. Hence, an efficient algorithm is proposed for mining and selecting discriminative patterns. Experimental results on twenty UCI datasets demonstrate that the proposed method can help to improve the classification performance remarkably, compared with other baseline methods. Moreover, an internal evaluation is employed to validate the strong discriminative power of our feature combinations.

关键词： Breast Diabetes Vehicles Classification algorithms Niobium Size measurement

Review and Prospect: NMR Spectroscopy Denoising & Reconstruction with Low Rank Hankel Matrices and Tensors

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Qiu, Tianyu Wang, Zi Liu, Huiting Guo, Di Qu, Xiaobo Department of Electronic Science Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance Xiamen University P.O.Box 979 Xiamen361005 China School of Computer and Information Engineering Xiamen University of Technology Xiamen361024 China

Nuclear Magnetic Resonance (NMR) spectroscopy is an important analytical tool in chemistry, biology, and life science, but it suffers from relatively low sensitivity and long acquisition time. Thus, improving the apparent signal-to-noise ratio and accelerating data acquisition become indispensable. In this review, we summarize the recent progress on low rank Hankel matrix and tensor methods, that exploit the exponential property of free induction decay signals, to enable effective denoising and spectra reconstruction. We also outline future developments that are likely to make NMR spectroscopy a far more powerful technique. Copyright © 2020, The Authors. All rights reserved.

关键词： Matrix algebra

Significance-aware Medication Recommendation with Medication Representation Learning

学校读者我要写书评

暂无评论

Significance-aware Medication Recommendation with Medication...

International Conference on computer Supported Cooperative Work in Design

作者： Yishuo Li Zhufeng Shao Weimin Chen Shoujin Wang Yuehan Du Wenpeng Lu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Mental Health Center Jinan China Data Science Institute University of Technology Sydney Sydney Australia Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

The goal of medication recommendation system is to recommend appropriate pharmaceutical interventions based on a patient’s diagnosis. Most of existing approaches often formulate these recommendations use data on diagnoses, procedures, and prescriptions accumulated in the electronic health records (EHR), and despite the great successes, they seem to have limitations on modelling the significance of medication to a patient’s current visit and mining fine-grained medication representation information. To address these issues, we propose a novel Significanceaware Medication Recommendation (SMRec) framework built on significance of medication to patients and fine-grained medication representation learning. Specifically, we first design a encoding mechanism to compute significance information of medications for each patient’s visit. Then, we utilize the set-level medication co-occurrence graph based on patients’ medical history which integrates temporal dependency to learn fine-grained medication representations. Experimental results on the publicly available MIMIC-III dataset demonstrate the superior effectiveness of our model compared to other approaches 1 .

关键词： Representation learning Drugs Federated learning Computational modeling MIMICs Encoding History

Robust image steganography against lossy JPEG compression based on embedding domain selection and adaptive error correction

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Duan, Xiaolong Li, Bin Yin, Zhaoxia Zhang, Xinpeng Luo, Bin Anhui Province Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security Shenzhen University Shenzhen518060 China School of Communication & Electronic Engineering East China Normal University Shanghai200241 China School of Computer Science Fudan University Shanghai200433 China

Transmitting images for communication on social networks has become routine, which is helpful for covert communication. The traditional steganography algorithm is unable to successfully convey secret information since the social network channel will perform lossy operations on images, such as JPEG compression. Previous studies tried to solve this problem by enhancing the robustness or making the cover adapt to the channel processing. In this study, we proposed a robust image steganography method against lossy JPEG compression based on embedding domain selection and adaptive error correction. To improve anti-steganalysis performance, the embedding domain is selected adaptively. To increase robustness and lessen the impact on anti-steganalysis performance, the error correction capacity of the error correction code is adaptively adjusted to eliminate redundancy. The experimental results show that the proposed method achieves better anti-steganalysis and robustness. Copyright © 2023, The Authors. All rights reserved.

关键词： Error correction

Usage: Uncertain Flow Graph and Spatio-Temporal Graph Network-Based Saturation Attack Detection Method

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Wang, Kaixi Cui, Yunhe Qian, Qing Chen, Yi Guo, Chun Shen, Guowei Engineering Research Center of Text Computing & Cognitive Intelligence Guizhou University China State Key Laboratory of Public Big Data Guizhou University China Guizhou Provincial Characteristic Key Laboratory of Software Engineering and Information Security Guizhou University China College of Computer Science and Technology Guizhou University China School of Information Guizhou University of Finance and Economics China

With the development of Software-Defined Networking (SDN), its security problems have become important research content. Among these security problems, saturation attack is one of the most destructive problems. Saturation attacks can destroy SDN networks. Currently, neural graph networks have already been used for detecting saturation attacks in SDN. When constructing the graph based on K-Nearest Neighbors (KNN) algorithm, the number of edges in the graph is fixed. That cannot reflect the different nodes’ relationship well. In addition, when using the Graph Convolutional Network (GCN) to detect saturation attack against SDN, only a partial graph structure and node features will be learned, causing the flow graph nodes information cannot be fully utilized. To overcome these issues, in this work, we propose USAGE, an uncertain flow graph and spatio-temporal graph network-based saturation attack detection method. More specifically, USAGE designs the CRAM algorithm and EGG model. The CRAM algorithm is designed to generate an uncertain flow graph for each traffic flow, which can represent the uncertain relationship among different nodes. EGG is a spatio-temporal graph convolutional network model, which is proposed to detect saturation attacks towards SDN switches. The evaluation results demonstrate that USAGE can generate a better graph than KNN and achieve high detection performance. Meanwhile, USAGE outperforms other methods in terms of TPR, TNR, accuracy, precision, recall, F-score, confusion matrix, ROC curves, and PR curves. © 2023, The Authors. All rights reserved.

关键词： Flow graphs

Radar HRRP Open Set Recognition Using Hierarchical Prototype Learning

学校读者我要写书评

暂无评论

Radar HRRP Open Set Recognition Using Hierarchical Prototype...

IEEE International Conference on Radar

作者： Yichen Liu Yanhua Wang Liang Zhang Binhua Yu Xiaojing Yang Yu-ang Zhang Le Zheng Difan Zou School of Information and Electronics Beijing Institute of Technology Beijing China Beijing Key Laboratory of Embedded Real-Time Information Processing Technology Beijing China Department of Computer Science University of Hong Kong Hongkong China HKU Musketeers Foundation Institute of Data Science University of Hong Kong Hongkong China

ISBN: (数字)9798350362381

ISBN: (纸本)9798350362398

High-resolution range profiles (HRRP) are increasingly employed in radar automatic target recognition (RATR). In practical applications of RATR, the environment is open and dynamic, and the recognition model is likely to encounter targets of unseen categories. However, traditional methods focus on a close-set scenario, where all categories in the test set are known during training. To bridge this gap, this paper proposes an open-set recognition (OSR) method based on hierarchical classification, developed from prototype learning. This method improves the generalization performance for recognizing known categories and identifies unknown categories while providing information about how the unknown categories relate to the known ones. Specifically, first, a four-layer category hierarchy is built based on prior knowledge to guide the training and testing stages. Next, we propose a hierarchical prototype loss (HPL) to constrain the feature space extracted by the prototype network so that the feature distribution of objects is consistent with the hierarchical category structure. Lastly, the trained prototype network makes predictions following the hierarchical structure. This operation could provide relationship information between the unknown and known categories. Extensive experiments on measured HRRP data validate the effectiveness of our proposed method for open-set recognition.

关键词： Training Bridges Target recognition Prototypes Radar Feature extraction Testing