检索结果-内蒙古大学图书馆

intelligent computing and Human-Computer Interaction (ICHCI), International Conference on

作者： Jiali Zhang Xiaoyan Qiao Yantai Key Laboratory of Big Data Modeling and Intelligent Computing Immersion Technology and Evaluation Shandong Engineering Research Center School of Computer Science and Technology Shandong Technology and Business University Yantai Shandong China Yantai Key Laboratory of Big Data Modeling and Intelligent Computing Immersion Technology and Evaluation Shandong Engineering Research Center School of Mathematics and Information Science Shandong Technology and Business University Yantai Shandong China

ISBN: (数字)9798350368284

ISBN: (纸本)9798350368291

Methods based on dynamically expanding architectures can effectively mitigate catastrophic forgetting in class incremental learning (CIL), but they often overlook information sharing and integration between subnetworks, leading to performance degradation and increased parameter count and memory consumption as the network expands. To address these complex issues, we introduce a new method called Task Separation and Knowledge Sharing (TSKS), which transfers knowledge at both the logical and feature levels through Hybrid Knowledge Distillation (HKD). In logical distillation, we combine Global Knowledge Distillation (GKD) and Task Knowledge Distillation (TKD) to establish connections between tasks. To prevent the model from favoring new classes, we design an Attention- Based Feature Fusion (ABFF) mechanism to capture important features. Additionally, we introduce a Soft-Margin Auxiliary Loss (SMAL) to help the model learn new concepts. Extensive experiments show that TSKS outperforms existing models on CIFAR100 and ImageNet100, regardless of whether memory samples are used. Notably, TSKS demonstrates superior performance in memory-free settings, indicating a reduced reliance on rehearsal memory.

关键词： Knowledge engineering Human computer interaction Degradation Incremental learning Computational modeling Memory management information sharing Network architecture Feature extraction Knowledge transfer

来源：评论

学校读者我要写书评

暂无评论

CGNet: Classification-Guided Multi-Task Interactive Network for Hyperspectral and Multispectral Image Fusion

CGNet: Classification-Guided Multi-Task Interactive Network ...

引用

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

作者： Guohua Lv Yanlong Xu Yongbiao Gao Guixin Zhao Guotao Wang Xiangcheng Sun 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) China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science China Shandong Key Laboratory of Ubiquitous Intelligent Computing China Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Application (Southeast University) Ministry of Education China Beihang University Beijing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The goal of fusing hyperspectral images (HSI) and multispectral images (MSI) is to generate high-resolution hyperspectral images for downstream tasks. However, most existing methods overlook the specific requirements of these tasks, leading to a gap between the fusion process and its subsequent applications due to insufficient guidance from downstream tasks. To address this issue, we propose a classification-guided multitask interactive network (CGNet) that integrates both fusion and classification tasks into a unified framework, with two branches producing the fused image and classification results, respectively. In the fusion branch, we design a multi-level residual refinement module to efficiently integrate spatial and spectral information. Additionally, an attention-based multi-scale fusion module, incorporating both spatial and channel attention, is carefully crafted to enhance representation learning. In the classification branch, both 2-D and 3-D convolutions are employed to improve classification performance. Moreover, an information interaction module is proposed to guide the fusion task based on classification outcomes. Extensive experiments demonstrate that our method outperforms state-of-the-art approaches on the Pavia Centre and Pavia University datasets.

关键词： Representation learning Three-dimensional displays Attention mechanisms Convolution Streaming media Multitasking Speech processing Image fusion information exchange Hyperspectral imaging

来源：评论

学校读者我要写书评

暂无评论

Energy-Aware Task Offloading for Rotatable STAR-RIS-Enhanced Mobile Edge computing Systems

arXiv

引用

arXiv 2025年

作者： Yang, Dongdong Li, Bin Niyato, Dusit School of Computer Science Nanjing University of Information Science and Technology Nanjing210044 China Huzhou Key Laboratory of Urban Multidimensional Perception and Intelligent Computing Huzhou313000 China College of Computing and Data Science Nanyang Technological University Singapore

Simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) can expand the coverage of mobile edge computing (MEC) services by reflecting and transmitting signals simultaneously, enabling full-space coverage. The orientation of the STAR-RIS plays a crucial role in optimizing the gain of received and transmitted signals, and a rotatable STAR-RIS offers potential enhancement for MEC systems. This paper investigates a rotatable STAR-RIS-assisted MEC system, operated under three protocols, namely energy splitting, mode switching, and time switching. The goal is to minimize energy consumption for multiple moving user devices through the joint optimization of STAR-RIS configurations, orientation, computation resource allocation, transmission power, and task offloading strategies. Considering the mobility of user devices, we model the original optimization problem as a sequential decision-making process across multiple time slots. The high-dimensional, highly coupled, and nonlinear nature makes it a challenging non-convex decision-making problem for traditional optimization algorithms. Therefore, a deep reinforcement learning (DRL) approach is employed, specifically utilizing soft actor-critic algorithm to train the DRL model. Simulation results demonstrate that the proposed algorithm outperforms the benchmarks in both convergence speed and energy efficiency, while reducing energy consumption by up to 52.7% compared to the fixed STAR-RIS scheme. Among three operating protocols, the energy splitting yields the best performance. © 2025, CC BY.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

DASpeech: directed acyclic transformer for fast and high-quality speech-to-speech translation 23

DASpeech: directed acyclic transformer for fast and high-qua...

引用

Proceedings of the 37th International Conference on Neural information Processing Systems

作者： Qingkai Fang Yan Zhou Yang Feng Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences (ICT/CAS) and University of Chinese Academy of Sciences Beijing China

Direct speech-to-speech translation (S2ST) translates speech from one language into another using a single model. However, due to the presence of linguistic and acoustic diversity, the target speech follows a complex multimodal distribution, posing challenges to achieving both high-quality translations and fast decoding speeds for S2ST models. In this paper, we propose DASpeech, a non-autoregressive direct S2ST model which realizes both fast and high-quality S2ST. To better capture the complex distribution of the target speech, DASpeech adopts the two-pass architecture to decompose the generation process into two steps, where a linguistic decoder first generates the target text, and an acoustic decoder then generates the target speech based on the hidden states of the linguistic decoder. Specifically, we use the decoder of DA-Transformer as the linguistic decoder, and use FastSpeech 2 as the acoustic decoder. DA-Transformer models translations with a directed acyclic graph (DAG). To consider all potential paths in the DAG during training, we calculate the expected hidden states for each target token via dynamic programming, and feed them into the acoustic decoder to predict the target mel-spectrogram. During inference, we select the most probable path and take hidden states on that path as input to the acoustic decoder. Experiments on the CVSS Fr→En benchmark demonstrate that DASpeech can achieve comparable or even better performance than the state-of-the-art S2ST model Translatotron 2, while preserving up to 18.53× speedup compared to the autoregressive baseline. Compared with the previous non-autoregressive S2ST model, DASpeech does not rely on knowledge distillation and iterative decoding, achieving significant improvements in both translation quality and decoding speed. Furthermore, DASpeech shows the ability to preserve the speaker's voice of the source speech during translation. Audio samples are available at https://***/daspeech-demo/. Code is pu

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Cross-direction Task Decoupling Network for Small Logo Detection

arXiv

引用

arXiv 2023年

作者： Hou, Sujuan Li, Xingzhuo Min, Weiqing Li, Jiacheng Wang, Jing Zheng, Yuanjie Jiang, Shuqiang School of Information Science and Engineering Shandong Normal University Jinan China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

Logo detection plays an integral role in many applications. However, handling small logos is still difficult since they occupy too few pixels in the image, which burdens the extraction of discriminative features. The aggregation of small logos also brings a great challenge to the classification and localization of logos. To solve these problems, we creatively propose Cross-direction Task Decoupling Network (CTDNet) for small logo detection. We first introduce Cross-direction Feature Pyramid (CFP) to realize cross-direction feature fusion by adopting horizontal transmission and vertical transmission. In addition, Multi-frequency Task Decoupling Head (MTDH) decouples the classification and localization tasks into two branches. A multi-frequency attention convolution branch is designed to achieve more accurate regression by combining discrete cosine transform and convolution creatively. Comprehensive experiments on four logo datasets demonstrate the effectiveness and efficiency of the proposed method. Copyright © 2023, 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

Temsa:Text Enhanced Modal Representation Learning for Multimodal Sentiment Analysis

SSRN

引用

SSRN 2025年

作者： Chen, Jingwen Song, Shuxiang Tan, Yumei Xia, Haiying The Key Lab of Education Blockchain and Intelligent Technology Ministry of Education China Guangxi Key Laboratory of Brain-inspired Computing and Intelligent Chips School of Electronic and Information Engineering Guangxi Normal University Guilin China Education Department of Guangxi Zhuang Autonomous Region Guilin China

Multimodal sentiment analysis aims to identify human emotions by leveraging multimodal information, including language, visual, and audio data. Different modalities contribute unequally to sentiment analysis, with text being more effective than non-linguistic modalities in multimodal sentiment analysis (MSA) due to its intuitive emotional expressiveness. A major challenge lies in leveraging the strengths of text to create fused representations that capture rich emotional content while preserving both inter-modal and intra-modal relationships. To address this challenge, we propose a Text-Enhanced Modal Representation Learning Model (TEMSA), which builds robust and unified multimodal representations through the design of text-guided pairwise cross-modal mapping modules. Specifically, TEMSA employs a text-guided multi-head cross-attention mechanism to embed linguistic information into the emotion-related representation learning of non-linguistic modalities, thereby enhancing the representations of visual and audio modalities. In addition to preserving consistent information through cross-modal mapping, TEMSA also incorporates text-guided reconstruction modules, which leverage text-enhanced non-linguistic modal features to decouple modality-specific representations from non-linguistic modalities. This dual representation learning framework captures inter-modal consistent information through cross-modal mapping, and extracts modal difference information through intra-modal decoupling, thus improving the understanding of cross-modal affective associations. The experimental results on the CMU-MOSI, CMU-MOSEI, and CH-SIMS datasets demonstrate that TEMSA achieves state-of-the-art performance, highlighting the critical role of text-guided cross-modal and intra-modal representation learning in multimodal sentiment analysis. © 2025, The Authors. All rights reserved.

关键词： Linguistics

来源：评论

学校读者我要写书评

暂无评论

A Cross-direction Task Decoupling Network for Small Logo Detection

A Cross-direction Task Decoupling Network for Small Logo Det...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Sujuan Hou Xingzhuo Li Weiqing Min Jiacheng Li Jing Wang Yuanjie Zheng Shuqiang Jiang School of Information Science and Engineering Shandong Normal University Jinan China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

关键词：

来源：评论

学校读者我要写书评

暂无评论

TEMSA:Text enhanced modal representation learning for multimodal sentiment analysis

引用

Computer Vision and Image Understanding 2025年 258卷

Multimodal sentiment analysis aims to identify human emotions by leveraging multimodal information, including language, visual, and audio data. Most existing models focus on extracting common features across modalities or simply integrating heterogeneous multimodal data. However, such approaches often overlook the unique representation advantages of individual modalities, as they treat all modalities equally and use bidirectional information transfer mechanisms. This can lead to information redundancy and feature conflicts. To address this challenge, we propose a Text-Enhanced Modal Representation Learning Model (TEMSA), which builds robust and unified multimodal representations through the design of text-guided pairwise cross-modal mapping modules. Specifically, TEMSA employs a text-guided multi-head cross-attention mechanism to embed linguistic information into the emotion-related representation learning of non-linguistic modalities, thereby enhancing the representations of visual and audio modalities. In addition to preserving consistent information through cross-modal mapping, TEMSA also incorporates text-guided reconstruction modules, which leverage text-enhanced non-linguistic modal features to decouple modality-specific representations from non-linguistic modalities. This dual representation learning framework captures inter-modal consistent information through cross-modal mapping, and extracts modal difference information through intra-modal decoupling, thus improving the understanding of cross-modal affective associations. The experimental results on the CMU-MOSI, CMU-MOSEI, and CH-SIMS datasets demonstrate that TEMSA achieves superior performance, highlighting the critical role of text-guided cross-modal and intra-modal representation learning in multimodal sentiment analysis. © 2025 Elsevier Inc.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

GP-Net: Global Perceptual Network with Adaptive Gradient Clipping for Emotional Image Classification

GP-Net: Global Perceptual Network with Adaptive Gradient Cli...

引用

6th International Conference on intelligent computing and Signal Processing (ICSP)

作者： Xiaohua Wang Jie Yang Min Hu Xia Wu Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine School of Computer Science and Information Engineering Hefei University of Technology Hefei China

Traditional image emotion recognition focuses only on the emotion information embedded in the subject or part of the image, while ignoring the global emotion information. In this paper, we propose a new network based on Vision Transformer: a global perception network, containing a main module and a background module. The main module enhances the weighting of objects by showing the interdependencies between modelled channels. The background module further searches for emotional information in the background. In addition, we employ multi-task learning and Adaptive Gradient Clipping to improve the network. Extensive experiments show that our proposed method outperforms the state-of-the-art methods for image sentiment analysis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Layout-based Causal Inference for Object Navigation

Layout-based Causal Inference for Object Navigation

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Sixian Zhang Xinhang Song Weijie Li Yubing Bai Xinyao Yu 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

Previous works for ObjectNav task attempt to learn the association (e.g. relation graph) between the visual inputs and the goal during training. Such association contains the prior knowledge of navigating in training environments, which is denoted as the experience. The experience performs a positive effect on helping the agent infer the likely location of the goal when the layout gap between the unseen environments of the test and the prior knowledge obtained in training is minor. However, when the layout gap is significant, the experience exerts a negative effect on navigation. Motivated by keeping the positive effect and removing the negative effect of the experience, we propose the layout-based soft Total Direct Effect (L-sTDE) framework based on the causal inference to adjust the prediction of the navigation policy. In particular, we propose to calculate the layout gap which is defined as the KL divergence between the posterior and the prior distribution of the object layout. Then the sTDE is proposed to appropriately control the effect of the experience based on the layout gap. Experimental results on AI2THOR, RoboTHOR, and Habitat demonstrate the effectiveness of our method. The code is available at https://***/sx-zhang/***.

关键词：

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：