检索结果-内蒙古大学图书馆

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yuyi Liu Xinhang Song Weijie Li Xiaohan Wang Shuqiang Jiang Key Lab of Intelligent Information Processing Laboratory of the Chinese Academy of Sciences (CAS) Institute of Computing Technology Beijing University of Chinese Academy of Sciences Beijing

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

This paper presents a novel category agnostic model for visual rearrangement task, which can help an embodied agent to physically recover the shuffled scene configuration without any category concepts to the goal configuration. Previous methods usually follow a similar architecture, completing the rearrangement task by aligning the scene changes of the goal and shuffled configuration, according to the semantic scene graphs. However, constructing scene graphs requires the inference of category labels, which not only causes the accuracy drop of the entire task but also limits the application in real world scenario. In this paper, we delve deep into the essence of visual re-arrangement task and focus on the two most essential issues, scene change detection and scene change matching. We utilize the movement and the protrusion of point cloud to accurately identify the scene changes and match these changes depending on the similarity of category agnostic appearance feature. Moreover, to assist the agent to explore the environment more efficiently and comprehensively, we propose a closer-aligned-retrace exploration policy, aiming to observe more details of the scene at a closer distance. We conduct extensive experiments onAI2THOR Rearrangement Challenge based on RoomR dataset and a new multi-room multi-instance dataset MrMiR collected by us. The experimental results demonstrate the effectiveness of our proposed method.

关键词： Point cloud compression Visualization Computer vision Accuracy Semantics Feature extraction Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Cross-Modality Perturbation Synergy Attack for Person Re-identification 38

Cross-Modality Perturbation Synergy Attack for Person Re-ide...

引用

38th Conference on Neural information Processing Systems, NeurIPS 2024

作者： Gong, Yunpeng Zhong, Zhun Qu, Yansong Luo, Zhiming Ji, Rongrong Jiang, Min School of Informatics Xiamen University China School of Computer Science and Information Engineering Hefei University of Technology China The Department of Artificial Intelligence Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China School of Informatics Key Laboratory of Digital Protection and Intelligent Processing of Intangible CulturalHeritage of Fujian and Taiwan Ministry of Culture and Tourism Xiamen University Fujian Xiamen361005 China

In recent years, there has been significant research focusing on addressing security concerns in single-modal person re-identification (ReID) systems that are based on RGB images. However, the safety of cross-modality scenarios, which are more commonly encountered in practical applications involving images captured by infrared cameras, has not received adequate attention. The main challenge in cross-modality ReID lies in effectively dealing with visual differences between different modalities. For instance, infrared images are typically grayscale, unlike visible images that contain color information. Existing attack methods have primarily focused on the characteristics of the visible image modality, overlooking the features of other modalities and the variations in data distribution among different modalities. This oversight can potentially undermine the effectiveness of these methods in image retrieval across diverse modalities. This study represents the first exploration into the security of cross-modality ReID models and proposes a universal perturbation attack specifically designed for cross-modality ReID. This attack optimizes perturbations by leveraging gradients from diverse modality data, thereby disrupting the discriminator and reinforcing the differences between modalities. We conducted experiments on three widely used cross-modality datasets, namely RegDB, SYSU, and LLCM. The results not only demonstrate the effectiveness of our method but also provide insights for future improvements in the robustness of cross-modality ReID systems. © 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

A Dual Prompt Learning Framework for Few-Shot Dialogue State Tracking 23

A Dual Prompt Learning Framework for Few-Shot Dialogue State...

引用

2023 World Wide Web Conference, WWW 2023

作者： Yang, Yuting Lei, Wenqiang Huang, Pei Cao, Juan Li, Jintao Chua, Tat-Seng Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences Beijing China Sichuan University Sichuan China Stanford University CA United States National University of Singapore Singapore Singapore

ISBN: (纸本)9781450394161

Dialogue State Tracking (DST) module is an essential component of task-oriented dialog systems to understand users' goals and needs. Collecting dialogue state labels including slots and values can be costly, requiring experts to annotate all (slot, value) information for each turn in dialogues. It is also difficult to define all possible slots and values in advance, especially with the wide application of dialogue systems in more and more new-rising applications. In this paper, we focus on improving DST module to generate dialogue states in circumstances with limited annotations and knowledge about slot ontology. To this end, we design a dual prompt learning framework for few-shot DST. The dual framework aims to explore how to utilize the language understanding and generation capabilities of pre-trained language models for DST efficiently. Specifically, we consider the learning of slot generation and value generation as dual tasks, and two kinds of prompts are designed based on this dual structure to incorporate task-related knowledge of these two tasks respectively. In this way, the DST task can be formulated as a language modeling task efficiently under few-shot settings. To evaluate the proposed framework, we conduct experiments on two task-oriented dialogue datasets. The results demonstrate that the proposed method not only outperforms existing state-of-the-art few-shot methods, but also can generate unseen slots. It indicates that DST-related knowledge can be probed from pre-trained language models and utilized to address low-resource DST efficiently with the help of prompt learning. © 2023 Owner/Author.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Glancing Future for Simultaneous Machine Translation

Glancing Future for Simultaneous Machine Translation

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Shoutao Guo Shaolei Zhang Yang Feng Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences (ICT/CAS) University of Chinese Academy of Sciences Beijing China

Simultaneous machine translation (SiMT) outputs translation while reading the source sentence. Unlike conventional sequence-to-sequence (seq2seq) training, existing SiMT methods adopt the prefix-to-prefix (prefix2prefix) training, where the model predicts target tokens based on partial source tokens. However, the prefix2prefix training diminishes the ability of the model to capture global information and introduces forced predictions due to the absence of essential source information. Consequently, it is crucial to bridge the gap between the prefix2prefix training and seq2seq training to enhance the translation capability of the SiMT model. In this paper, we propose a novel method that glances future in curriculum learning to achieve the transition from the seq2seq training to prefix2prefix training. Specifically, we gradually reduce the available source information from the whole sentence to the prefix corresponding to that latency. Our method is applicable to a wide range of SiMT methods and experiments demonstrate that our method outperforms strong baselines 1 .

关键词：

来源：评论

学校读者我要写书评

暂无评论

Retinopathy Identification in OCT Images with A Semi-supervised Learning Approach via Complementary Expert Pooling and Expert-wise Batch Normalization

Retinopathy Identification in OCT Images with A Semi-supervi...

引用

Optoelectronics Global Conference (OGC)

作者： Arman Mohammad Nakib Yuan Li Yuemei Luo Jiangsu Provincial Key Laboratory of Intelligent Medical Image Computing (iMIC) School of Artificial Intelligence Nanjing University of Information Science and Technology Nanjing China

ISBN: (数字)9798350391466

ISBN: (纸本)9798350391473

In the medical field, the automatic detection of retinopathy using deep learning is an important application. However, traditional deep learning techniques face two significant challenges: the need for large amounts of labeled data, which are costly and difficult to obtain, and the imbalance of OCT ocular disease categories in practical applications, which can significantly affect model performance. This paper proposes a semi-supervised deep learning method based on complementary expert pooling (CEP). This method utilizes transfer learning with pre-trained models and enhances the model’s generalization capabilities through data augmentation strategies. Our approach implements a custom classification model on the VGG-16 architecture, employing CEP to model different category distributions across multiple experts and introducing Expert-wise Batch Normalization (EBN) to resolve feature distribution mismatches, thereby improving the model’s accuracy in recognizing minority classes. We evaluated our method on two datasets, using only 20% of the images as labeled data. Our method achieved $\mathbf{9 6. 5 5 \%}$ and $\mathbf{9 7. 7 8 \%}$ classification accuracies on these public datasets. Moreover, our approach demonstrated superior performance compared to various supervised learning methods using all available labeled data and other semi-supervised learning methods, proving its effectiveness in OCT ocular disease detection and its potential to assist clinicians in diagnosing ophthalmic diseases.

关键词： Accuracy Image resolution Retinopathy Transfer learning Supervised learning Semisupervised learning Data models Batch normalization Medical diagnostic imaging Diseases

来源：评论

学校读者我要写书评

暂无评论

LinNet: Linear Network for Efficient Point Cloud Representation Learning 38

LinNet: Linear Network for Efficient Point Cloud Representat...

引用

38th Conference on Neural information Processing Systems, NeurIPS 2024

作者： Deng, Hao Jing, Kunlei Cheng, Shengmei Liu, Cheng Ru, Jiawei Bo, Jiang Wang, Lin State-Province Joint Engineering and Research Center of Advanced Networking and Intelligent Information Services School of Information Science and Technology Northwest University China Shaanxi Key Laboratory of Higher Education Institution of Generative Artificial Intelligence and Mixed Reality China School of Software Engineering Xi'an Jiaotong University China Department of Computing The Hong Kong Polytechnic University Hong Kong

Point-based methods have made significant progress, but improving their scalability in large-scale 3D scenes is still a challenging problem. In this paper, we delve into the point-based method and develop a simpler, faster, stronger variant model, dubbed as LinNet. In particular, we first propose the disassembled set abstraction (DSA) module, which is more effective than the previous version of set abstraction. It achieves more efficient local aggregation by leveraging spatial anisotropy and channel anisotropy separately. Additionally, by mapping 3D point clouds onto 1D space-filling curves, we enable parallelization of downsampling and neighborhood queries on GPUs with linear complexity. LinNet, as a purely point-based method, outperforms most previous methods in both indoor and outdoor scenes without any extra attention, and sparse convolution but merely relying on a simple MLP. It achieves the mIoU of 73.7%, 81.4%, and 69.1% on the S3DIS Area5, NuScenes, and SemanticKITTI validation benchmarks, respectively, while speeding up almost 10x times over PointNeXt. Our work further reveals both the efficacy and efficiency potential of the vanilla point-based models in large-scale representation learning. Our code will be available at https://***/DengH293/LinNet. © 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

An Encoded Double Auxiliary Pilot Channel Estimation Method for Intrinsic Interference Cancellation in FBMC/OQAM Systems

An Encoded Double Auxiliary Pilot Channel Estimation Method ...

引用

IEEE International Conference on Artificial Intelligence in Engineering and technology (IICAIET)

作者： Sixuan Xing Jianhong Xiang Ying Wang Liangang Qi Yu Zhong College of Information and Communication Engineering Harbin Engineering University Harbin China Key Laboratory of Advanced Ship Communication and Information Technology Harbin Engineering University Harbin China Agile and Intelligent Computing Key Laboratory Chengdu China

ISBN: (数字)9798350389692

ISBN: (纸本)9798350389708

Filter bank multicarrier technique (FBMC) is considered as a promising modulation technique suitable for future communications. However, the presence of intrinsic interference prevents the efficient implementation of techniques such as channel estimation. This paper presents a encode double auxiliary pilot channel estimation method (EDAP) for filter bank multicarrier offset quadrature amplitude modulation (FBMC/OQAM) systems. In order to eliminate the intrinsic interference, we add auxiliary symbols around the pilot, and at the same time perform a precoding process to minimize the auxiliary pilot energy loss and computational complexity. In order to validate the above method, the OQAM/FBMC system is modeled. Theoretical analysis and numerical results show that the method improves the channel estimation accuracy by 2.15-3.22 dB in double selective channels while maintaining low power consumption and low complexity.

关键词： Power demand Spectral efficiency Quadrature amplitude modulation System performance Precoding Channel estimation Filter banks Symbols Filtering algorithms Numerical models

来源：评论

学校读者我要写书评

暂无评论

Research on patent recommendation method based on graph neural network 26

Research on patent recommendation method based on graph neur...

引用

26th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2023

作者： Zhang, Enchao Liu, Weidong Liu, Shi Cao, Yan Institute of Scientific and Technical Information of China China College of Computer Science Inner Mongolia University China Natl. Loc. Jt. Eng. Research Center of Intelligent Information Processing Technology for Mongolian China Inner Mongolia Key Laboratory of Social Computing and Data Processing China Inner Mongolia Engineering Laboratory for Big Data Analysis Technology China

ISBN: (纸本)9798350331684

Intellectual property transactions have shown a strong growth momentum in recent years, but the patent transaction market has been plagued by the matching degree of consumers and sellers, resulting in frequent problems such as low patent transformation efficiency and poor transaction quality. This paper proposes a method of recommending patents to consumers by experts to improve the environment of patent transactions. Through the analysis of the past transaction information of the patent, the effective path information of the target is extracted. The graph neural network is used to describe the characteristics and semantics among experts, patents and consumers, and then capture the potential weight among them through the common attention mechanism, and then dynamically integrate them to predict the occurrence of recommendation behavior. The paper makes reasonable use of social information and expert information in the transaction, which significantly improves the rationality and accuracy of expert recommendation. © 2023 IEEE.

关键词： Patents and inventions

来源：评论

学校读者我要写书评

暂无评论

EmoDubber: Towards High Quality and Emotion Controllable Movie Dubbing

arXiv

引用

arXiv 2024年

作者： Cong, Gaoxiang Pan, Jiadong Li, Liang Qi, Yuankai Peng, Yuxin van den Hengel, Anton Yang, Jian Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS China Macquarie University Australia Peking University China University of Adelaide Australia

Given a piece of text, a video clip, and a reference audio, the movie dubbing task aims to generate speech that aligns with the video while cloning the desired voice. The existing methods have two primary deficiencies: (1) They struggle to simultaneously hold audio-visual sync and achieve clear pronunciation;(2) They lack the capacity to express user-defined emotions. To address these problems, we propose EmoDubber, an emotion-controllable dubbing architecture that allows users to specify emotion type and emotional intensity while satisfying high-quality lip sync and pronunciation. Specifically, we first design Lip-related Prosody Aligning (LPA), which focuses on learning the inherent consistency between lip motion and prosody variation by duration level contrastive learning to incorporate reasonable alignment. Then, we design Pronunciation Enhancing (PE) strategy to fuse the video-level phoneme sequences by efficient conformer to improve speech intelligibility. Next, the speaker identity adapting module aims to decode acoustics prior and inject the speaker style embedding. After that, the proposed Flow-based User Emotion Controlling (FUEC) is used to synthesize waveform by flow matching prediction network conditioned on acoustics prior. In this process, the FUEC determines the gradient direction and guidance scale based on the user’s emotion instructions by the positive and negative guidance mechanism, which focuses on amplifying the desired emotion while suppressing others. Extensive experimental results on three benchmark datasets demonstrate favorable performance compared to several state-of-the-art methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Speech intelligibility

来源：评论

学校读者我要写书评

暂无评论

Edge-Preserving Multi-Exposure Fusion with Guided Filtering for Structural Patch Decomposition 6

Edge-Preserving Multi-Exposure Fusion with Guided Filtering ...

引用

6th IEEE International Conference on Electronic information and Communication technology, ICEICT 2023

作者： Zhen, Yang Qi, Junwei Li, Yingsong College of Information and Communication Engineering Harbin Engineering University Harbin150001 China Ministry of Education Anhui University Key Laboratory of Intelligent Computing and Signal Processing Hefei China College of Computer Science and Technology Harbin Engineering University Harbin150001 China

ISBN: (纸本)9798350399059

Multi-exposure image fusion (MEF) is one of the effective ways to obtain high dynamic range (HDR) images. Multi-scale structural patch decomposition based MEF(MSPD) and edge-preserving structural patch decomposition (MESPD) have achieved state-of-the-art fusion quality. MESPD incorporates edge-preserving factors into MSPD to preserve details in a single-scale setting. However, we find that the edge-preserving factors put too much emphasis on the edge, resulting in artifacts on some edges and loss of details. To tackle this issue, guided filter is introduced into MSPD, which is directly used as an edge-preserving filter instead of mean filter to implicitly decompose images. In addition, we have designed a flexible adaptive weight, which can further maintain details of the light and dark areas. Likewise, we inherit MESPD and MSPD to extend our method to multi-scale framework. Extensive experimental results demonstrate our method can produce satisfactory results in both static and dynamic scenes with fewer artifacts and low computational cost. © 2023 IEEE.

关键词： Image fusion

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：