检索结果-内蒙古大学图书馆

2025 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2025

作者： Xu, Zhuo Xiang, Xiang School of Artificial Intelligence and Automation Huazhong University of Science and Technology National Key Lab of Multi-Spectral Information Intelligent Processing Technology Wuhan China Peng Cheng Lab China

ISBN: (纸本)9798331510831

In the field of open-set recognition, conventional models often focus on addressing challenges within a single hierarchical category, and these methods frequently lack inter-pretability. In this paper, we propose a novel solution that utilizes attributes and hierarchical relationships to achieve interpretable open-set recognition. Our method is centered around the visual-semantic attribute space. By leveraging hierarchy division, we can decompose the attributes into more granular components, thereby yielding additional performance improvements. When confronted with an unfamiliar object, our method not only classifies it as an unknown category but also provides insights into the broader category and its associated attributes. This capability enhances interpretability by offering valuable information regarding the potential category and characteristics of the object. Experimental results demonstrate great performance improvements compared to existing methods. © 2025 IEEE.

关键词： Hierarchical systems

来源：评论

学校读者我要写书评

暂无评论

Target Parameter Estimation with Deep Unfolding networks for MIMO-OFDM Based Integrated Sensing and Communication Systems 15

Target Parameter Estimation with Deep Unfolding Networks for...

引用

15th IEEE International Conference on Wireless Communications and Signal processing, WCSP 2023

作者： Lin, Jingcai Zheng, Haifeng Feng, Xinxin Fuzhou University Fujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information College of Physics and Information Engineering Fuzhou350108 China

ISBN: (纸本)9798350324662

The multiple-input multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) technology shows great potential in integrated sensing and communication (ISAC) systems. To address the challenges posed by the high computational complexity and low estimation accuracy of traditional target parameter estimation methods in a MIMO-OFDM based ISAC system, this paper introduces a compressed sensing based approach for target parameter estimation. We first derive the channel model within the MIMO-OFDM system, and then reformulate the problem of target parameter estimation as a least absolute shrinkage and selection operator (LASSO) problem. Furthermore, we propose a model-driven network, termed FISTA-Net, which deeply unfolds the fast iterative shrinkage thresholding algorithm (FISTA) into a deep neural network to solve the LASSO problem. Experimental results show that the proposed FISTA-Net algorithm outperforms the existing methods in terms of estimation accuracy and computation efficiency for MIMO-OFDM based target parameter estimation. © 2023 IEEE.

关键词： compressed sensing deep unfolding FISTA MIMO-OFDM parameter estimation

来源：评论

学校读者我要写书评

暂无评论

Weakly-Supervised Graph Classification with Even a Single key Subgraph Per Class 24

Weakly-Supervised Graph Classification with Even a Single Ke...

引用

24th IEEE International Conference on Data Mining, ICDM 2024

作者： Zhang, Lu Zhang, Chenbo Guan, Jihong Zhou, Shuigeng School of Computer Science Fudan University Shanghai Key Lab of Intelligent Information Processing China Tongji University Department of Computer Science & Technology China

ISBN: (纸本)9798331506681

Traditional graph classification requires large amounts of labeled data, which is expensive and time-consuming to acquire, especially in some special scenarios that domain knowledge is indispensable for labeling graphs. Observing that some key subgraphs can determine the properties of graphs (e.g. the toxicity of drug molecules depend on some toxic functional groups), in this paper we explore to classify graphs using unlabeled graphs plus a small number of key subgraphs for each class, which is called weakly-supervised graph classification. To this end, we develop the WeGraph method, where the graph classifier is trained with subgraph-based self-supervised learning and divergence- minimization based fine-tuning. Moreover, we design a key subgraph extraction algorithm to iteratively extract and update the key subgraphs, which makes the training process a closed loop. We conduct extensive experiments on different types of graph datasets to evaluate the effectiveness of WeGraph. Experimental results show that WeGraph can achieve high performance even when only one key subgraph is provided for each class. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Flexible TiO_(2)-WO_(3−x) hybrid memristorwith enhanced linearity and synaptic plasticity for precise weight tuning in neuromorphic computing

引用

npj Flexible Electronics 2024年第1期8卷 180-191页

作者： Jianyong Pan Hao Kan Zhaorui Liu Song Gao Enxiu Wu Yang Li Chunwei Zhang Shandong Provincial Key Laboratory of Network Based Intelligent Computing School of Information Science and EngineeringUniversity of JinanJinanChina State Key Lab of Transducer Technology Shanghai Institute of Microsystem and Information TechnologyChinese Academy of SciencesShanghaiChina School of Integrated Circuits Shandong UniversityJinanChina

Tungsten oxide(WO_(3))-based memristors show promising applications in neuromorphic ***,single-layer WO_(3) memristors suffer from issues such as weak memory performance and nonlinear conductance *** this work,a functional layer based on the hybrids of WO_(3−x) and TiO_(2) is proposed for constructing flexible memristors featuring outstanding synaptic *** diverse electrical stimulations to the memristor enables a range of synaptic functions,elucidating its conduction mechanism through the conductive filament *** incorporation of TiO_(2) not only enhances the memristor’s memory characteristics but makes its conductance more linear,symmetrical and uniform during the long-term ***,in view of the enhanced device performance by TiO_(2) doping,the potential of this device for simple behavioral simulation and processing of complex computing problems is ***“learning-forgetting-relearning”characteristics and device integrability are visually *** the device to a convolutional neural network,the recognition accuracy of MNIST handwritten digits reaches 98.7%.

关键词： computing tuning precise

来源：评论

学校读者我要写书评

暂无评论

Hi-NeRF: Hybridizing 2D Inpainting with Neural Radiance Fields for 3D Scene Inpainting 17th

Hi-NeRF: Hybridizing 2D Inpainting with Neural Radiance Fie...

引用

17th Asian Conference on Computer Vision, ACCV 2024

作者： Huang, Xianliang Chen, Shuhang Zhong, Zhizhou Gou, Jiajie Guan, Jihong Zhou, Shuigeng Shanghai Key Lab of Intelligent Information Processing and School of Computer Science Fudan University Shanghai China School of Computer Science and Technology Tongji University Shanghai China

ISBN: (纸本)9789819609710

Recent developments in Neural Radiance Fields (NeRF) have showcased notable progress in the synthesis of novel views. Nevertheless, there is limited research on inpainting 3D scenes using implicit representations. Traditional approaches utilizing 3D networks for direct 3D inpainting often falter in high-resolution settings, mainly due to GPU memory constraints. This paper introduces Hi-NeRF, an innovative 3D inpainting approach designed to remove arbitrary 3D objects by hybridizing 2D inpainting strategies with NeRF techniques. Recognizing that prevailing 2D inpainting methods often fail to grasp the 3D geometric intricacies of scenes, we leverage the unique capability of NeRF in capturing these structures. Additionally, we propose a multi-view perceptual loss (MVPL) to harness multi-view data, ensuring that 2D inpainting and implicit 3D representations can mutually compensate for each other. Furthermore, we refine the output from the Segment Anything Model (SAM) using image dilation to produce accurate multi-view masks. To finalize the process, we employ Instant-NGP to efficiently retrieve 3D-consistent scenes from 3D-consistent inpainted images. As there is no multi-view 3D scene datasets with corresponding masks, we construct both real-world and synthetic scenes for the multi-view 3D scene inpainting task, which serves as a benchmark dataset. Experimental results on both indoor and outdoor scenes highlight the superiority of our approach over the existing 2D inpainting methods and NeRF-based baselines. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

CPT: a pre-trained unbalanced transformer for both Chinese language understanding and generation

引用

Science China(information Sciences) 2024年第5期67卷 43-55页

作者： Yunfan SHAO Zhichao GENG Yitao LIU Junqi DAI Hang YAN Fei YANG Zhe LI Hujun BAO Xipeng QIU School of Computer Science Fudan University Shanghai Key Laboratory of Intelligent Information Processing Fudan University Zhejiang Lab

In this paper, we take the advantage of previous pre-trained models(PTMs) and propose a novel Chinese pre-trained unbalanced transformer(CPT). Different from previous Chinese PTMs, CPT is designed to utilize the shared knowledge between natural language understanding(NLU) and natural language generation(NLG) to boost the performance. CPT consists of three parts: a shared encoder, an understanding decoder, and a generation decoder. Two specific decoders with a shared encoder are pretrained with masked language modeling(MLM) and denoising auto-encoding(DAE) tasks, *** the partially shared architecture and multi-task pre-training, CPT can(1) learn specific knowledge of both NLU or NLG tasks with two decoders and(2) be fine-tuned flexibly that fully exploits the potential of the model. Moreover, the unbalanced transformer saves the computational and storage cost, which makes CPT competitive and greatly accelerates the inference of text generation. Experimental results on a wide range of Chinese NLU and NLG tasks show the effectiveness of CPT.

关键词： pre-trained model transformer language model generation unified model

来源：评论

学校读者我要写书评

暂无评论

R&B: REGION AND BOUNDARY AWARE ZERO-SHOT GROUNDED TEXT-TO-IMAGE GENERATION 12

R&B: REGION AND BOUNDARY AWARE ZERO-SHOT GROUNDED TEXT-TO-IM...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Xiao, Jiayu Lv, Henglei Li, Liang Wang, Shuhui Huang, Qingming Key Lab of Intelligent Information Processing ICT CAS Beijing China University of Chinese Academy of Sciences Beijing China Peng Cheng Laboratory Shenzhen China

Recent text-to-image (T2I) diffusion models have achieved remarkable progress in generating high-quality images given text-prompts as input. However, these models fail to convey appropriate spatial composition specified by a layout instruction. In this work, we probe into zero-shot grounded T2I generation with diffusion models, that is, generating images corresponding to the input layout information without training auxiliary modules or finetuning diffusion models. We propose a Region and Boundary (R&B) aware cross-attention guidance approach that gradually modulates the attention maps of diffusion model during generative process, and assists the model to synthesize images (1) with high fidelity, (2) highly compatible with textual input, and (3) interpreting layout instructions accurately. Specifically, we leverage the discrete sampling to bridge the gap between consecutive attention maps and discrete layout constraints, and design a region-aware loss to refine the generative layout during diffusion process. We further propose a boundary-aware loss to strengthen object discriminability within the corresponding regions. Experimental results show that our method outperforms existing state-of-the-art zero-shot grounded T2I generation methods by a large margin both qualitatively and quantitatively on several benchmarks. Project page: https://***/Region-and-Boundary. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Bridges

来源：评论

学校读者我要写书评

暂无评论

Relation Reconstructive Binarization of word embeddings

引用

Frontiers of Computer Science 2022年第2期16卷 47-54页

作者： Feiyang PAN Shuokai LI Xiang AO Qing HE Key Lab of Intelligent Information Processing of Chinese Academy of Sciences(CAS) Institute of Computing TechnologyCASBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China

Word-embedding acts as one of the backbones of modern natural language processing(NLP).Recently,with the need for deploying NLP models to low-resource devices,there has been a surge of interest to compress word embeddings into hash codes or binary vectors so as to save the storage and memory ***,existing work learns to encode an embedding into a compressed representation from which the original embedding can be *** these methods aim to preserve most information of every individual word,they often fail to retain the relation between words,thus can yield large loss on certain *** this end,this paper presents Relation Reconstructive Binarization(R2B)to transform word embeddings into binary codes that can preserve the relation between *** its heart,R2B trains an auto-encoder to generate binary codes that allow reconstructing the wordby-word relations in the original embedding *** showed that our method achieved significant improvements over previous methods on a number of tasks along with a space-saving of up to 98.4%.Specifically,our method reached even better results on word similarity evaluation than the uncompressed pre-trained embeddings,and was significantly better than previous compression methods that do not consider word relations.

关键词： embedding compression variational auto-encoder binary word embedding

来源：评论

学校读者我要写书评

暂无评论

A Privacy-friendly sequential progressive framework for segmented decision making

A Privacy-friendly sequential progressive framework for segm...

引用

2023 International Conference on Artificial Intelligence of Things and Systems, AIoTSys 2023

作者： Liu, Peng Yu, Zhiyong Huang, Fangwan Fuzhou University College of Computer and Data Science Fuzhou China Fuzhou University Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou China

ISBN: (纸本)9798350312270

To achieve progressive and accurate decision-making for long-term time series data while meeting the needs of privacy-friendly and early, this paper proposes a universal framework for sequential progressive decision-making (SPD). This framework first segments the data and sets up multiple columns of neural networks according to the number of segments. Each column can make segmented decisions based on the inputs for the period. Additionally, without sharing the original data, the framework leverages lateral hidden layer connections between preceding and succeeding columns to obtain useful features for subsequent decision-making, gradually improving accuracy while avoiding the risk of data leakage. SPD has the advantages of privacy friendliness, column model diversification, prior knowledge reuse, and easy scalability, making it an effective framework for continuous decision-making. The effectiveness of that was validated using various network models in handwritten digit recognition and electrocardiogram classification tasks. The obtained experimental results reveal that SPD not only enables early decision-making while ensuring accuracy but also achieves accuracy levels comparable to or even surpassing those obtained using complete data, with the added benefit of privacy protection. © 2023 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Scheduling Multiple Mobile Agents with Abilities of Sensing and Executing Simultaneously

Scheduling Multiple Mobile Agents with Abilities of Sensing ...

引用

2023 International Conference on Artificial Intelligence of Things and Systems, AIoTSys 2023

作者： Guo, Zhipeng Yu, Zhiyong Huang, Fangwan Tu, Chunyu Fuzhou University College of Computer and Data Science Fuzhou China Fuzhou University Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou China

ISBN: (纸本)9798350312270

How to schedule public resources to maximize the coverage of crowds has always been a hot topic. There are mainly two types of research. One is the scheduling of static resources, whose coverage efficiency is lower because the resources cannot be moved;the other is the dynamic scheduling of movable public resources, but the existing methods require additional devices to collect crowd volume data. To address this issue, this article introduces a new category of mobile agents that can sense and execute simultaneously. This means that an agent can simultaneously perform crowd volume data collection tasks and crowds coverage tasks in its area. Taking these multi-ability agents as public resources, this article proposes a scheduling method called GE-STMC (Greedy Execute - Spatial and Temporal Monte-Carlo dropout). The method considers the spatiotemporal correlation between areas and evaluates the sensing value and the executing value of areas comprehensively to allocate the agents accordingly. Through the experimental on the real data of Beijing Happy Valley, this method can get 16% larger crowds volume coverage than other baseline methods with the same number of agents. © 2023 IEEE.

关键词： Mobile agents

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：