检索结果-内蒙古大学图书馆

2024 Conference on Lasers and Electro-Optics, CLEO 2024

作者： Han, Changhao Qin, Jun Yang, Qipeng Zheng, Zhao Shu, Haowen Zhang, Yunhao Wu, Yichen Sun, Yu Lu, Junde Zhou, Yan Ge, Zhangfeng Wang, Lei He, Zhixue Yu, Shaohua Hu, Weiwei Peng, Chao Bowers, John E. Wang, Xingjun State Key Laboratory of Advanced Optical Communications System and Networks School of Electronics Peking University Beijing100871 China Department of Electrical and Computer Engineering University of California Santa BarbaraCA93106 United States Key Laboratory of Information and Communication Systems Ministry of Information Industry Beijing Information Science and Technology University Beijing100192 China Frontiers Science Center for Nano-Optoelectronics Peking University Beijing100871 China Peng Cheng Laboratory Shenzhen518055 China Peking University Yangtze Delta Institute of Optoelectronics Nantong226010 China

We experimentally demonstrate PAM-4 optical transmission beyond 224 Gbps based on an ultrahigh-bandwidth slow-light silicon modulator in C-band with the combination of the artificial neural network equalizers. CLEO 20... 详细信息

ISBN: (纸本)9781957171395

关键词： Silicon photonics

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Performance to Detecting Topic Shift of Large Language Models: A Study 9

Evaluating the Performance to Detecting Topic Shift of Large...

引用

9th International Conference on Intelligent Computing and Signal Processing, ICSP 2024

作者： Tian, Pingfang Liu, Deting Department of Computer Science and Technology Wuhan University of Science and Technology Wuhan430065 China Institute of Scientific and Technical Information of China The Key Laboratory of the Rich Media Knowledge Organisation and Service of Digital Publishing Content Beijing100038 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan China Big Data Science and Engineering Research Institute Wuhan University of Science and Technology Wuhan430065 China

ISBN: (纸本)9798350376548

Topic shift detection aims to identify whether there is a change in the current topic of conversation or if a change is needed. The study found previous work did not evaluate the performance of large language models like ChatGPT on the task of topic shift. Therefore, this paper's main task and innovation lie in analyzing ChatGPT's performance on topic shift detection. To provide a more comprehensive evaluation, we conducted topic shift detection tasks on ChatGPT from three aspects: single utterances, adjacent utterances, and contextual levels. Additionally, to gauge the performance of large language models, we conducted experiments on multiple small-scale models and compared the results of the two models. Experimental results on the publicly available English TIAGE dataset showed that small-scale models exhibited lower recall in all three aspects, while ChatGPT performed better in the recall. This suggests that compared to small-scale models, large models are more capable of accurately detecting topic shifts. However, large models also exhibited lower precision, indicating that while ChatGPT can recognize content differences in utterances, its judgment on whether these different contents belong to the same topic is poor. © 2024 IEEE.

关键词： adjacent utterances level ChatGPT contextual level single utterances level topic shift detection

来源：评论

学校读者我要写书评

暂无评论

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Learning 22

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Lea...

引用

22nd IEEE International Conference on Industrial Informatics, INDIN 2024

作者： Cao, Weipeng Yao, Xuyang Xu, Zhiwu Pan, Yinghui Sun, Yixuan Li, Dachuan Qiu, Bohua Wei, Muheng Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Stony Brook University New York United States Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China ZhenDui Industry Artificial Intelligence Co. Ltd Shenzhen China Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China

ISBN: (纸本)9798331527471

Realizing Generalized Zero-Shot Learning (GZSL) based on large models is emerging as a prevailing trend. However, most existing methods merely regard large models as black boxes, solely leveraging the features output by the final layer while disregarding potential performance enhancements from other layers. Indeed, numerous researchers have visually depicted variations in the features learned across different layers of neural networks. Motivated by this observation, we propose a Vision Transformer (ViT)-based GZSL method named Depth-Aware Multi-Modal ViT (DAM2ViT), which exploits multi-level features of ViT. DAM2ViT incorporates a multi-modal interaction block to align semantic information of categories across multiple layers, thereby augmenting the model’s capacity to learn associations between visual and semantic spaces. Extensive experiments conducted on three benchmark datasets (i.e., CUB, SUN, AWA2) have showcased that DAM2ViT achieves competitive results compared to state-of-the-art methods. © 2024 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Semantic recommendation through Reinforcement Learning and weighted meta-paths

Semantic recommendation through Reinforcement Learning and w...

引用

2022 International Conference on Electronic information engineering, Big Data, and computer Technology, EIBDCT 2022

作者： Yu, Jing Lang, Yue Li, Xuewen Zhang, Jin Zheng, Shaojie Gong, Jibing School of Information Science and Engineering Yanshan University Qinhuangdao066004 China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Yanshan University Qinhuangdao066004 China Key Laboratory for Software Engineering of Hebei Province Yanshan University Qinhuangdao066004 China

ISBN: (纸本)9781510655133

Explainable recommendation systems, which can produce high-accuracy recommendations and help users make quick decisions, have become a hotspot in research field. Most of existing research algorithms committed to improving the accuracy of recommendation, but ignored the interpretability of recommendation. We propose a semantic recommendation algorithm through Reinforcement Learning and weighted meta-paths which analyzes and selects the meta-path, and uses Reinforcement Learning network to train the weight of meta-path. This method can effectively solve data sparsity, improve the accuracy of recommendation, and increase interpretability. Compared with the baseline method, indicators of the recommended methods for integrating Reinforcement Learning with Heterogeneous information Networks have been greatly improved, as verified and compared on a real MovieLens 1M dataset. Experimental results prove that the algorithm can effectively improve the accuracy and interpretability of the recommendation. © 2022 SPIE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Object Tracking by Jointly Utilizing Template Updating and Relocation Mechanisms⋆

SSRN

引用

SSRN 2023年

作者： Wen, Jia Ren, Kejun School of Information Science and Engineering Yanshan University Qinhuangdao066099 China The Key Laboratory for Computer Virtual Technology System Integration of Hebei Province China

The Siamese network-based tracker has achieved competitive performance in the field of single target tracking because of its excellent tracking speed and tracking accuracy. When faced with target deformations, most Siamese trackers rely on fixed template features from the initial frame, severely constraining the tracker’s performance. To mitigate this situation, we introduce a novel tracking framework(SiamTAR) that allows adaptive template updates based on past tracking information. In addition, we design a feature refinement module which can capture the target information more accurately at the full scale on the search image through an integrated attention mechanism, thus enabling the tracker to pay less attention to redundant information. Notably, we introduce a relocalization mechanism to solve the problems of random drift of the tracking box and inaccurate scale estimation in online tracking. Extensive experiments on GOT-10K, UAV123, OTB100 and DTB70 datasets show that the tracker achieves good tracking results and real-time performance. © 2023, The Authors. All rights reserved.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

S2KAN-SLAM: Elastic Neural LiDAR SLAM with SDF Submaps and Kolmogorov-Arnold Networks

引用

IEEE Transactions on Circuits and systems for Video Technology 2025年

作者： Wang, Zhong Zhang, Lin Wang, Hesheng Shanghai Jiao Tong University State Key Laboratory of Avionics Integration and Aviation System-of-Systems Synthesis Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Shanghai200240 China Tongji University School of Computer Science and Technology National Pilot Software Engineering School with Chinese Characteristics Shanghai201804 China

Traditional LiDAR SLAM approaches prioritize localization over mapping, yet high-precision dense maps are essential for numerous applications involving intelligent agents. Recent advancements have introduced methods leveraging neural fields to enhance mapping capabilities;however, these approaches still face several limitations. Firstly, concerning scene representation, they typically employ neural fields with high-dimensional features and multi-layer perceptron decoders utilizing non-continuous activation functions. This results in low learning efficiency and challenges in capturing high-frequency signals. Secondly, in terms of scene organization, these methods often treat the entire scene as a singular neural field, leading to inefficiencies, inflexibility, and difficulties in rectifying accumulated errors when mapping large-scale environments over extended periods. To tackle the first issue, we propose a lightweight continuous SDF regression approach by encoding the scene in single-valued embeddings and decoding SDF values from a Kolmogorov-Arnold Network. By minimizing discrepancies in measuring range, sampling distance, and decoded SDF values, we facilitate iterative frame-to-model tracking and bundle adjustment neural mapping. To mitigate the second challenge, we propose structuring the whole scene into multiple neural SDF submaps. By establishing node-node, node-submap, and loop closure constraints into a global pose graph, the system can create dense neural maps with global consistency across large-scale scenes. Experimental evaluations in both real-world and simulated settings indicate that our system achieves superior mapping completeness and accuracy, enhanced learning efficiency, reduced memory consumption, and greater flexibility compared to its counterparts. © 2025 IEEE.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Prediction-Based Thunderstorm Path Recovery Method Using CNN-BiLSTM

引用

Intelligent Automation & Soft Computing 2023年第8期37卷 1637-1654页

作者： Xu Yang Ling Zhuang Yuqiang Sun Wenjie Zhang School of Electronics and Information Engineering Nanjing University of Information Science and TechnologyNanjing210044China Department of Electrical and Computer Engineering University of AlbertaEdmontonAB T6G 2R3Canada CCCC Highway Consultants Co. Ltd.Beijing100101China School of Geographical Sciences Nanjing University of Information Science and TechnologyNanjing210044China State Key Laboratory of Resources and Environmental Information System Institute of Geographic Sciences and Natural Resources ResearchChinese Academy of SciencesBeijing100101China

The loss of three-dimensional atmospheric electric field(3DAEF)data has a negative impact on thunderstorm *** paper proposes a method for thunderstorm point charge path *** on the relation-ship between a point charge and 3DAEF,we derive corresponding localization formulae by establishing a point charge localization ***,point charge movement paths are obtained after fitting time series localization ***,AEF data losses make it difficult to fit and visualize ***,using available AEF data without loss as input,we design a hybrid model combining the convolutional neural network(CNN)and bi-directional long short-term memory(BiLSTM)to predict and recover the lost *** paths are not present during sunny weather,we propose an extreme gradient boosting(XGBoost)model combined with a stacked autoencoder(SAE)to further determine the weather conditions of the recovered ***,historical AEF data of known weathers are input into SAE-XGBoost to obtain the distribution of predicted values(PVs).With threshold adjustments to reduce the negative effects of invalid PVs on SAE-XGBoost,PV intervals corresponding to different weathers are *** recovered AEF is then input into the fixed SAE-XGBoost *** paths need to be fitted is determined by the interval to which the output PV *** results confirm that the proposed method can effectively recover point charge paths,with a maximum path deviation of approximately 0.018 km and a determination coefficient of 94.17%.This method provides a valid reference for visual thunderstorm monitoring.

关键词： Thunderstorm point charge atmospheric electric field(AEF) recovery

来源：评论

学校读者我要写书评

暂无评论

FIRE: A Dataset for Feedback integration and Refinement Evaluation of Multimodal Models 38

FIRE: A Dataset for Feedback Integration and Refinement Eval...

引用

38th Conference on Neural information Processing systems, NeurIPS 2024

作者： Li, Pengxiang Gao, Zhi Zhang, Bofei Yuan, Tao Wu, Yuwei Harandi, Mehrtash Jia, Yunde Zhu, Song-Chun Li, Qing Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology China State Key Laboratory of General Artificial Intelligence BIGAI China State Key Laboratory of General Artificial Intelligence Peking University China Department of Electrical and Computer System Engineering Monash University Australia Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University China Department of Automation Tsinghua University China

Vision language models (VLMs) have achieved impressive progress in diverse applications, becoming a prevalent research direction. In this paper, we build FIRE, a feedback-refinement dataset, consisting of 1.1M multi-turn conversations that are derived from 27 source datasets, empowering VLMs to spontaneously refine their responses based on user feedback across diverse tasks. To scale up the data collection, FIRE is collected in two components: FIRE-100K and FIRE-1M, where FIRE-100K is generated by GPT-4V, and FIRE-1M is freely generated via models trained on FIRE-100K. Then, we build FIRE-Bench, a benchmark to comprehensively evaluate the feedback-refining capability of VLMs, which contains 11K feedback-refinement conversations as the test data, two evaluation settings, and a model to provide feedback for VLMs. We develop the FIRE-LLaVA model by fine-tuning LLaVA on FIRE-100K and FIRE-1M, which shows remarkable feedback-refining capability on FIRE-Bench and outperforms untrained VLMs by 50%, making more efficient user-agent interactions and underscoring the significance of the FIRE dataset. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Integrating VGGSK and BEATs for Enhanced Sound Event Detection: A Semi-Supervised GRU-Based system with Weak Labels and Synthetic Soundscapes

Integrating VGGSK and BEATs for Enhanced Sound Event Detecti...

引用

Asia-Pacific Signal and information Processing Association Annual Summit and Conference (APSIPA)

作者： Po Cheng Chan Wei-Yu Chen Chung Li Lu Hsiang-Feng Chuang Yu-Han Cheng Jia Ching Wang Advanced Technology Laboratory Chunghwa Telecom Laboratories Taoyuan Taiwan Department of Computer Science and Information Engineering National Central University

ISBN: (数字)9798350367331

ISBN: (纸本)9798350367348

This paper presents the architecture we developed for the Detection and Classification of Acoustic Scenes and Events (DCASE) 2023 Challenge, specifically Task 4 on Sound Event Detection using Weak Labels and Synthetic Soundscapes. We integrated embeddings from VGGSK and BEATs, and employed a GRU-based model to classify sound events in each time frame. The system employs thresholding and smoothing techniques in its post-processing phase. For semi-supervised learning, we used the mean teacher approach with an Exponential Moving Average (EMA) strategy to update the teacher model’s parameters. Pseudo-labels, generated by the student model, help leverage unlabeled data. Additionally, we applied data augmentation methods including mix-up, Gaussian noise, and embedding masking. With additional training data, our system achieved a Polyphonic Sound Detection Score (PSDS) of 0.529 for PSDS1 and 0.78 for PSDS2 on the validation dataset.

关键词： Training Measurement Smoothing methods Gaussian noise Training data information processing Semisupervised learning Data augmentation Data models information and communication technology

来源：评论

学校读者我要写书评

暂无评论

Automatic web page data extraction through MD5 trigeminal tree and improved BIRCH

Automatic web page data extraction through MD5 trigeminal tr...

引用

2022 International Conference on Electronic information engineering, Big Data, and computer Technology, EIBDCT 2022

作者： Gong, Jibing Kou, Xiaomeng Zhang, Hanyun Peng, Jiquan Gong, Shishan Wang, Shuli School of Information Science and Engineering Yanshan University Qinhuangdao066004 China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Yanshan University Qinhuangdao066004 China Key Laboratory for Software Engineering of Hebei Province Yanshan University Qinhuangdao066004 China School of Information Science Yanshan University Qinhuangdao066004 China

ISBN: (纸本)9781510655133

This paper proposes an automatic data extraction algorithm for web pages based on noise reduction and visualization blocks' construction. In this algorithm, we first build an MD5 trigeminal tree of the web page's source files using a Message-Digest Algorithm. And then we arrange some noise reduction. Finally, we construct visualization blocks by an optimized cluster algorithm named BIRCH A-CF which could create an area clustering feature forest and complete the clustering by dynamically changing the circle's radius according to the correction factor. We perform experiments on eight different datasets to compare our method with eight baseline methods. The experimental results show that our approach outperforms current methods by providing more accuracy and robustness, it also accelerates noise reduction and reduces the number of nodes effectively. © 2022 SPIE.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：