检索结果-内蒙古大学图书馆

Proceedings of the 41st International Conference on Machine Learning

作者： Xiaoyu Zhou Xingjian Ran Yajiao Xiong Jinlin He Zhiwei Lin Yongtao Wang Deqing Sun Ming-Hsuan Yang Wangxuan Institute of Computer Technology Peking University Wangxuan Institute of Computer Technology Peking University and National Key Laboratory for Multimedia Information Processing Google DeepMind Google DeepMind and University of California Merced

We present GALA3D, generative 3D GAussians with LAyout-guided control, for effective compositional text-to-3D generation. We first utilize large language models (LLMs) to generate the initial layout and introduce a layout-guided 3D Gaussian representation for 3D content generation with adaptive geometric constraints. We then propose an instance-scene compositional optimization mechanism with conditioned diffusion to collaboratively generate realistic 3D scenes with consistent geometry, texture, scale, and accurate interactions among multiple objects while simultaneously adjusting the coarse layout priors extracted from the LLMs to align with the generated scene. Experiments show that GALA3D is a user-friendly, end-to-end framework for state-of-the-art scene-level 3D content generation and controllable editing while ensuring the high fidelity of object-level entities within the scene. The source codes and models will be available at ***.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CMC_v2: Towards More Accurate COVID-19 Detection with Discriminative Video Priors 17th

CMC_v2: Towards More Accurate COVID-19 Detection with Discr...

引用

17th European Conference on computer Vision, ECCV 2022

作者： Hou, Junlin Xu, Jilan Zhang, Nan Wang, Yi Zhang, Yuejie Zhang, Xiaobo Feng, Rui School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai China Academy for Engineering and Technology Fudan University Shanghai China Shanghai AI Laboratory Shanghai China National Children’s Medical Center Children’s Hospital of Fudan University Shanghai China

ISBN: (纸本)9783031250811

This paper presents our solution for the 2nd COVID-19 Competition, occurring in the framework of the AIMIA Workshop at the European Conference on computer Vision (ECCV 2022). In our approach, we employ the winning solution last year which uses a strong 3D Contrastive Mixup Classification network (CMC_v1) as the baseline method, composed of contrastive representation learning and mixup classification. In this paper, we propose CMC_v2 by introducing natural video priors to COVID-19 diagnosis. Specifically, we adapt a pre-trained (on video dataset) video transformer backbone to COVID-19 detection. Moreover, advanced training strategies, including hybrid mixup and cutmix, slice-level augmentation, and small resolution training are also utilized to boost the robustness and the generalization ability of the model. Among 14 participating teams, CMC_v2 ranked 1st in the 2nd COVID-19 Competition with an average Macro F1 Score of 89.11%. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Identity and Modality Attributes Driven Multimodal Fusion Networks for Emotion Recognition in Conversations

引用

IEEE Transactions on Multimedia 2025年

作者： Shi, Wuzhen Chen, Xuping Yao, Biyun Wen, Yang Sheng, Bin Shenzhen University Guangdong Province Engineering Laboratory for Digital Creative Technology Guangdong Provincial Key Laboratory of Intelligent Information Processing College of Electronics and Information Engineering Shenzhen518060 China Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai China

Emotion recognition in conversations (ERC) is a crucial aspect of human-computer interaction and plays an important role in various domains, including healthcare, entertainment, and education. Since the conversation data in the form of multimodal sequences is well suited to be constructed into graphs, the methods based on graph convolutional network (GCN) show incomparable advantages. However, existing methods attempt to model the highly uncertain emotional relationships between different speakers, which is not an easy task and may even introduce interference information. Therefore, we propose an identity and modality attributes driven multimodality fusion network (dubbed IMDNet) for emotion recognition in conversations. Specifically, we construct a speaker-centric graph that only connects nodes of the same speaker within modalities to each other, reducing the interference between the emotions of different speakers. We also introduce the attribute embedding mechanism, which facilitates the correct calculation of correlations between nodes for better multimodal feature fusion. Considering that the emotional correlation between utterances will decrease over time, we present an utterance distance attention to make the fusion network pay more attention to the adjacent utterances. Furthermore, we explore the solution to the data imbalance problem suitable for conversation scenarios. Given the presence of possible anomalous samples in the dataset, we opt for the BoundaryFocalLoss. Experiments on the IEMOCAP and MELD datasets show that our IMDNet outperforms the state-of-the-art methods. © 1999-2012 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

L2GC: Lorentzian Linear Graph Convolutional Networks For Node Classification

arXiv

引用

arXiv 2024年

作者： Liang, Qiuyu Wang, Weihua Bao, Feilong Gao, Guanglai College of Computer Science Inner Mongolia University Hohhot China National and Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Hohhot China Inner Mongolia Key Laboratory of Mongolian Information Processing Technology Hohhot China

Linear Graph Convolutional Networks (GCNs) are used to classify the node in the graph data. However, we note that most existing linear GCN models perform neural network operations in Euclidean space, which do not explicitly capture the tree-like hierarchical structure exhibited in real-world datasets that modeled as graphs. In this paper, we attempt to introduce hyperbolic space into linear GCN and propose a novel framework for Lorentzian linear GCN. Specifically, we map the learned features of graph nodes into hyperbolic space, and then perform a Lorentzian linear feature transformation to capture the underlying tree-like structure of data. Experimental results on standard citation networks datasets with semi-supervised learning show that our approach yields new state-of-the-art results of accuracy 74.7% on Citeseer and 81.3% on PubMed datasets. Furthermore, we observe that our approach can be trained up to two orders of magnitude faster than other nonlinear GCN models on PubMed dataset. Our code is publicly available at https://***/llqy123/LLGC-master. Copyright © 2024, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Gesture Recognition of sEMG Based on Res-LSTM 17th

Gesture Recognition of sEMG Based on Res-LSTM

引用

17th International Conference on Intelligent Robotics and Applications, ICIRA 2024

作者： Zhao, Yujia Zou, Chunlong Yun, Juntong Jiang, Du Huang, Li Liu, Ying Jiang, Guozhang Xie, Yuanmin Key Laboratory of Metallurgical Equipment and Control Technology of Ministry of Education Wuhan University of Science and Technology Wuhan430081 China College of Mechanical Engineering Hubei University of Automotive Technology Shiyan442000 China Research Center for Biomimetic Robot and Intelligent Measurement and Control Wuhan University of Science and Technology Wuhan430081 China Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering Wuhan University of Science and Technology Wuhan430081 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan University of Science and Technology Wuhan430081 China College of Computer Science and Technology Wuhan University of Science and Technology Wuhan430081 China School of Mechanical Engineering Hubei Engineering University Xiaogan432000 China

ISBN: (纸本)9789819607761

sEMG (surface electromyography) signal control of bionic prostheses has been widely studied over the past few years. In particular, sparse sEMG signals are rapidly developing in the field of gesture recognition for their convenience, noninvasiveness, and ease of access. However, compared with high-density EMG signals, sparse EMG signals lack rich feature information, which in turn affects gesture recognition accuracy. In order to reduce the loss of feature information of sparse EMG signals in the spatio-temporal dimension, this paper proposes a hybrid neural network Res-LSTM combining residual network and long short-term memory network. The ordinary convolutional blocks in the CNN network are replaced with residual blocks, and the final fully connected layer is removed and a constant mapping layer is added to adequate extraction of spatial feature information of the data. The Res layer’s output is utilized as the input for the long and short-term memory (LSTM) network, which further extracts the features of the data in the temporal dimension, and finally completes the categorization output through a fully connected layer. The average accuracy of 91.11% for gesture-motion classification was verified by training on a homebrew dataset;and tested on a public dataset, NinaPro DB1, with an average accuracy of 91.03%. The experimental findings indicate that the proposed Res-LSTM network framework contributes to solving the problem of lack of feature information of sparse sEMG signals and improves the pattern recognition accuracy. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Ranking the Spreading Influence of Nodes in Complex Networks by Combining Local Average Weight and Average Normalized Link Entropy

Ranking the Spreading Influence of Nodes in Complex Networks...

引用

Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE), International Conference on

作者： Kaiyu Fan Fan Yang Dexin Tu Xinlai Tang Xiuyong Mao School of Computer Science and Technology Guangxi University of Science and Technology Liuzhou China Key Laboratory of Intelligent Information Processing and Graph Processing Guangxi University of Science and Technology Liuzhou China

Ranking the spreading influence of nodes is of great importance for controlling the spreading process on networks. Although a few measures are proposed for ranking nodes in weighted networks, it is still a challenge in accurately and efficiently ranking the spreading influence of nodes in weighted networks. In this paper, by utilizing both of the local and global topological structure information, a novel method is proposed. First, we define a local average weight (LAW) to describe the local topological structure information of nodes. Second, partly based on the link diversity, we define an average normalized link entropy (ANLE) to describe the global topological structure information of nodes. Further, by combining the LAW and ANLE, we propose a novel ranking measure termed as LAW-ANLE (LA) centrality. The proposed LA is verified by extensive experiments on a series of networks, and the results show that the LA is feasible and effective in accurately ranking the spreading influence of nodes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AutoSketch: automatic sketch-oriented compiler for query-driven network telemetry 24

AutoSketch: automatic sketch-oriented compiler for query-dri...

引用

Proceedings of the 21st USENIX Symposium on Networked Systems Design and Implementation

作者： Haifeng Sun Qun Huang Jinbo Sun Wei Wang Jiaheng Li Fuliang Li Yungang Bao Xin Yao Gong Zhang National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University Institute of Computing Technology CAS Northeastern University China Huawei Theory Department

ISBN: (纸本)9781939133397

Recent network telemetry witnesses tremendous progress in two directions: query-driven telemetry that targets expressiveness as the primary goal, and sketch-based algorithms that address resource-accuracy trade-offs. In this paper, we propose AutoSketch that aims to integrate the advantages of both classes. In a nutshell, AutoSketch automatically compiles high-level operators into sketch instances that can be readily deployed with low resource usage and incur limited accuracy drop. However, there remains a gap between the expressiveness of high-level operators and the underlying realization of sketch algorithms. AutoSketch bridges this gap in three aspects. First, AutoSketch extends its interface derived from existing query-driven telemetry such that users can specify the desired telemetry accuracy. The specified accuracy intent will be utilized to guide the compiling procedure. Second, AutoSketch leverages various techniques, such as syntax analysis and performance estimation, to construct efficient sketch instances. Finally, AutoSketch automatically searches for the most suitable parameter configurations that fulfill the accuracy intent with minimum resource usage. Our experiments demonstrate that AutoSketch can achieve high expressiveness, high accuracy, and low resource usage compared to state-of-the-art telemetry solutions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PosterLayout: A New Benchmark and Approach for Content-Aware Visual-Textual Presentation Layout

PosterLayout: A New Benchmark and Approach for Content-Aware...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： HsiaoYuan Hsu Xiangteng He Yuxin Peng Hao Kong Qing Zhang Wangxuan Institute of Computer Technology Peking University National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University Meituan

Content-aware visual-textual presentation layout aims at arranging spatial space on the given canvas for pre-defined elements, including text, logo, and underlay, which is a key to automatic template-free creative graphic design. In practical applications, e.g., poster designs, the canvas is originally non-empty, and both inter-element relationships as well as inter-layer relationships should be concerned when generating a proper layout. A few recent works deal with them simultaneously, but they still suffer from poor graphic performance, such as a lack of layout variety or spatial non-alignment. Since content-aware visual-textual presentation layout is a novel task, we first construct a new dataset named PKU PosterLayout, which consists of 9,974 poster- layout pairs and 905 images, i.e., non-empty canvases. It is more challenging and useful for greater layout variety, domain diversity, and content diversity. Then, we propose design sequence formation (DSF) that reorganizes elements in layouts to imitate the design processes of human designers, and a novel CNN-LSTM-based conditional generative adversarial network (GAN) is presented to generate proper layouts. Specifically, the discriminator is design-sequence- aware and will supervise the “design” process of the generator. Experimental results verify the usefulness of the new benchmark and the effectiveness of the proposed approach, which achieves the best performance by generating suitable layouts for diverse canvases. The dataset and the source code are available at https://***/PKU-ICST-MIPL/PosterLayout-CVPR2023.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SU-YOLO: Spiking Neural Network for Efficient Underwater Object Detection

arXiv

引用

arXiv 2025年

作者： Li, Chenyang Liu, Wenxuan Gong, Guoqiang Ding, Xiaobo Zhong, Xian College of Computer and Information Technology China Three Gorges University Yichang443002 China Hubei Key Laboratory of Transportation Internet of Things School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan430070 China State Key Laboratory for Multimedia Information Processing School of Computer Science Peking University Beijing100091 China State Key Laboratory of Maritime Technology and Safety Wuhan University of Technology Wuhan430063 China

Underwater object detection is critical for oceanic research and industrial safety inspections. However, the complex optical environment and the limited resources of underwater equipment pose significant challenges to achieving high accuracy and low power consumption. To address these issues, we propose Spiking Underwater YOLO (SU-YOLO), a Spiking Neural Network (SNN) model. Leveraging the lightweight and energy-efficient properties of SNNs, SU-YOLO incorporates a novel spike-based underwater image denoising method based solely on integer addition, which enhances the quality of feature maps with minimal computational overhead. In addition, we introduce Separated Batch Normalization (SeBN), a technique that normalizes feature maps independently across multiple time steps and is optimized for integration with residual structures to capture the temporal dynamics of SNNs more effectively. The redesigned spiking residual blocks integrate the Cross Stage Partial Network (CSPNet) with the YOLO architecture to mitigate spike degradation and enhance the model’s feature extraction capabilities. Experimental results on URPC2019 underwater dataset demonstrate that SU-YOLO achieves mAP of 78.8% with 6.97M parameters and an energy consumption of 2.98 mJ, surpassing mainstream SNN models in both detection accuracy and computational efficiency. These results underscore the potential of SNNs for engineering applications. The code is available in https://***/lwxfight/snn-underwater. Copyright © 2025, The Authors. All rights reserved.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

Sentiment classification method based on multitasking and multimodal interactive learning 23

引用

23rd Chinese National Conference on Computational Linguistics, CCL 2024

作者： Lei, Yang Wang, Suge Li, Shuqi Wang, Hao School of Computer and Information Technology Shanxi University Shanxi 030006 China Key Laboratory Computational Intelligence and Chinese Information Processing Ministry of Education Shanxi University Shanxi 030006 China

ISBN: (纸本)9780000000002

In prose reading comprehension, on one hand, the questions are usually concise and abstract, making it difficult for machines to directly understand the meaning and requirements of the questions. On the other hand, prose passages are lengthy, and candidate answer sentences are dispersed across multiple paragraphs in the passage, posing significant challenges for sentence extraction tasks. Therefore, this paper proposes a question-enhanced approach for extracting candidate answer sentences from prose passages. Firstly, relevant words in the passage are extracted using a large model to build a question word extension library. Subsequently, the powerful generative capability of the large model is utilized to rewrite the original question, and then the question word extension library is employed for further expansion. Lastly, by segmenting the prose passage, a model is established to assess the relevance between questions and sentences based on global context information and historical information, facilitating the extraction of candidate answer sentences. Experimental results on a prose reading comprehension dataset demonstrate that the proposed method improves the accuracy of extracting candidate answer sentences from prose passages, thereby providing technical support for answering generative-type questions in prose reading comprehension tasks. © 2024 China National Conference on Computational Linguistics.

关键词： Computational linguistics

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：