检索结果-内蒙古大学图书馆

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

作者： Zhibo Zhang Zhenyu Yang Yan Huang Baojie Xu Wenyue Hu 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 Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Multimodal dialogue emotion recognition integrates data from multiple modalities to accurately identify emotional states in conversations. However, differences in expression and information density across modalities complicate the fusion of features. Traditional methods may introduce redundant information from other utterances, reducing the accuracy of emotion recognition. Existing one-hot labels often fail to capture the full range of emotional expressions, leading to biased results. To address these issues, we propose a model that fuses different modalities within the same utterance to avoid redundancy. It employs a progressive classification process, refining emotion recognition from coarse to fine granularity. Additionally, we use emotion polarity probabilities as weights for fine-grained classification and introduce a multimodal information-rich label that considers both the data and their interactions. Experiments on IEMOCAP and MELD datasets demonstrate the model’s effectiveness, significantly improving dialog emotion recognition accuracy. Our code is available at https://***/r/LOCG-188E.

关键词： Emotion recognition Accuracy Fuses Refining Termination of employment Speech recognition Signal processing Speech processing Optimization Faces

来源：评论

学校读者我要写书评

暂无评论

MQADet: A Plug-and-Play Paradigm for Enhancing Open-Vocabulary Object Detection via Multimodal Question Answering

arXiv

引用

arXiv 2025年

作者： Li, Caixiong Zhao, Xiongwei Zhang, Jinhang Zhang, Xing Sun, Qihao Wu, Zhou School of Computer and Information Science Qinghai Institute of Technology China School of Information Science and Technology Harbin Institute of Technology Shen Zhen China The State Key Laboratory of Robotics and System Harbin Institute of Technology China School of Computer Science and Technology Qinghai University China Eryuan Digital Technology Co. Ltd. China

Open-vocabulary detection (OVD) is a challenging task to detect and classify objects from an unrestricted set of categories, including those unseen during training. Existing open-vocabulary detectors are limited by complex visual-textual misalignment and long-tailed category imbalances, leading to suboptimal performance in challenging scenarios. To address these limitations, we introduce MQADet, a universal paradigm for enhancing existing open-vocabulary detectors by leveraging the cross-modal reasoning capabilities of multimodal large language models (MLLMs). MQADet functions as a plug-and-play solution that integrates seamlessly with pre-trained object detectors without substantial additional training costs. Specifically, we design a novel three-stage Multimodal Question Answering (MQA) pipeline to guide the MLLMs to precisely localize complex textual and visual targets while effectively enhancing the focus of existing object detectors on relevant objects. To validate our approach, we present a new benchmark for evaluating our paradigm on four challenging open-vocabulary datasets, employing three state-of-the-art object detectors as baselines. Experimental results demonstrate that our proposed paradigm significantly improves the performance of existing detectors, particularly in unseen complex categories, across diverse and challenging scenarios. To facilitate future research, we will publicly release our code. © 2025, CC BY.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Towards Depth-continuous Scene Representation with Displacement Field for Robust Light Field Depth Estimation

引用

IEEE Transactions on Multimedia 2025年

作者： Chen, Rongshan Sheng, Hao Yang, Da Cong, Ruixuan Cui, Zhenglong Wang, Sizhe Wang, Tun Zhao, Mingyuan Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beijing100191 China Beihang University Key Laboratory of Data Science and Intelligent Computing International Innovation Institute 166 Shuanghongqiao Street Pingyao Town Yuhang District Hangzhou31 1115 China Macao Polytechnic University Faculty of Applied Sciences Macao999078 China

The light field (LF) captures both the spatial and angular information of scenes, enabling accurate depth estimation. However, previous deep learning methods typically model surface depth only while ignoring the continuous nature of depth in 3D scenes. In this paper, we use the displacement field (DF) to describe this continuous property, and propose a novel depth-continuous scene representation for robust LF depth estimation. Experiments demonstrate that our representation enables the network to generate highly detailed depth maps with fewer parameters and faster speeds. Specifically, inspired by the signed distance field in 3D object descriptions, we aim to exploit the intrinsic depth-continuous property of 3D scenes via DF and define a novel depth-continuous scene representation. Then, we introduce a simple, yet general, learning framework for depth-continuous scene embedding, and the proposed network, DepthDF, achieves state-of-the-art performance on both synthetic and real-world LF datasets, ranking 1st on the HCI 4D light field benchmark. Furthermore, previous LF depth estimation methods can also be seamlessly integrated into this framework. Finally, we extend this framework beyond LF depth estimation to various tasks, including multiview stereo depth inference, LF superresolution, and LF salient object detection. Our experiments demonstrate an improved performance when continuous scene representation is applied, suggesting that our framework can potentially provide insights for more fields. © 1999-2012 IEEE.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

Fire Detection Based on Flame Enhancement for Weak Fires 19th

Fire Detection Based on Flame Enhancement for Weak Fires

引用

19th Chinese Conference on Image and Graphics Technologies and Applications, IGTA 2024

作者： Chen, Kuan Wen, Wen Feng, Fujian Xu, Xiang Liang, Yihui School of Computer Guangdong University of Technology Guangzhou510000 China School of Computer Science Zhongshan Institute University of Electronic Science and Technology of China Zhongshan528400 China Guizhou Key Laboratory of Pattern Recognition and Intelligent System Guizhou Minzu University Guiyang550025 China

ISBN: (纸本)9789819799183

Detecting weak fire, such as overexposed and highly transparent flames, remains a significant challenge in vision-based fire detection. Convolutional Neural Network (CNN) based methods are widely used for automatic fire feature extraction, but they struggle to accurately recognize overexposed flames similar to the background and highly transparent flames that blend with the background, leading to false negative fire detection results. To address this issue, we have established a large-scale fire detection dataset with weak flames and introduce a fire detection method based on flame context enhancement. While employing a flame feature extraction module to identify and delineate the potential flame area, the proposed method primarily introduces a flame context module to capture the effective features of weak flames from this area, significantly enhancing the understanding of fires. Experimental results show that the proposed method can effectively reduce false negatives and improves the recall rate for detecting weak flames. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Premixed flames

来源：评论

学校读者我要写书评

暂无评论

Adaptive Pixel Pair Generation Strategy for Image Matting Methods Based on Pixel Pair Optimization 19th

Adaptive Pixel Pair Generation Strategy for Image Matting Me...

引用

19th Chinese Conference on Image and Graphics Technologies and Applications, IGTA 2024

作者： Zheng, Jiamin Wen, Wen Liang, Yihui Feng, Fujian Xu, Xiang School of Computer Guangdong University of Technology Guangzhou510000 China School of Computer Science Zhongshan Institute University of Electronic Science and Technology of China Zhongshan528400 China Guizhou Key Laboratory of Pattern Recognition and Intelligent System Guizhou Minzu University Guiyang550025 China

ISBN: (纸本)9789819799183

Natural image matting plays a crucial role in numerous real-world applications. Image matting methods based on pixel pair optimization is a type of matting algorithm, which has significant advantages in parallel computation, handling images with similar foreground and background, and operating under limited computing time. However, these methods cannot provide high-quality alpha mattes for high-resolution images within limited computational resources. In this paper, we design an adaptive pixel pair generation strategy to solve the above problem. This strategy adaptively generates pixel pair for the unknown pixel according to its estimated alpha value, which promotes diversity of pixel pair and improves the efficiency of pixel pair optimization. It categorizes unknown pixels into three types and additionally incorporates nearby foreground and background pixels to generate pixel pair. Experimental results show that using our strategy can achieve high-quality alpha mattes and competitive matting performance under limited computational resources. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Byzantine-Robust Federated Learning Framework via a Server-Client Defense Mechanisms

引用

IEEE Internet of Things Journal 2025年

作者： Song, Anxiao Zhang, Tao Cheng, Ke Cao, Yang Zhu, Xinghui Shen, Yulong Xidian University School of Computer Science and Technology Xi’an China Shaanxi Key Laboratory of Network and System Security Shaanxi Xi’an710071 China Xidian University School of Computer Science and Technology Shaanxi Xi’an710071 China Xi’an University of Posts and Telecommunications Shaanxi Key Laboratory of Information Communication Network and Security Shaanxi Xi’an710121 China Institute of Science Tokyo Department of Computer Science Tokyo Japan

Federated Learning (FL), a distributed machine learning (ML) framework, is susceptible to Byzantine attacks since the attacker can manipulate clients' local data or models to compromise the performance of the global model. There has been a wealth of defenses developed to mitigate the attacks by limiting the impact of malicious models. Nevertheless, the attacker can easily circumvent these approaches that rely solely on a single server-side defense, stemming from the high dimensionality of models and the variety of Byzantine attacks. Therefore, we propose Basalt, a Byzantine-robust federated learning framework with a server-client joint defense mechanism that enables multiple clients to train a global ML model under Byzantine attacks. On the client side, we design an efficient self-defense approach with model-level penalty loss that restricts local-benign divergence and decreases local-malicious correlation to prevent misclassification. On the server side, we present an efficient defense strategy based on the manifold and maximum clique, further strengthening the FL's resilience against Byzantine attacks. We provide theoretical guarantees for global model convergence in FL with Byzantine attacks. Our extensive experiments demonstrate that Basalt outperforms existing state-of-the-art works. Especially, it achieves nearly 100% accuracy for detecting malicious clients in nonindependent and nonidentically distributed (Non-IID) MNIST datasets under various Byzantine attacks. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Parameter-Efficient Multi-Modal Tuning for Salient Object Detection

SSRN

引用

SSRN 2025年

作者： Zhang, Zixuan Shi, Fan Jia, Chen Wang, Mianzhao Louis, Assale Adje Cheng, Xu Engineering Research Center of Learning-Based Intelligent System Ministry of Education Tianjin University of Technology Tianjin300384 China Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin300384 China Yamoussoukro999063 Ivory Coast Smart Innovation Norway Norway

Salient object detection (SOD) is a key preprocessing step in various computer vision tasks, aiming to replicate the human visual system to identify the most significant objects or regions in images or videos. However, existing multi-modal SOD works introduce expensive fusion modules with a large number of parameters to integrate cues across modalities. This cannot effectively reduce the resource overhead required for computing devices. To address this issue, we propose a parameter-efficient multi-modal tuning method for salient object detection. Our method employs a hierarchical progressive encoder with a limited set of learnable parameters to capture aligned and intrinsic representations. Based on the encoder, we further introduce a learnable weighting parameter λ to exploit semantic understanding across different levels and patterns. Extensive experiments on 11 benchmark datasets with 32 state-of-the-art (SOTA) methods demonstrate the effectiveness of our method, which requires only 4.4M training parameters. © 2025, The Authors. All rights reserved.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

An Image Semantic Communication system Based on GAN and Relative Position-Encoding

引用

IEEE Communications Letters 2025年

作者： Zhang, Ziqi Tan, Weijie Li, Chunguo Guizhou University College of Big Data and Information Engineering Guiyang550025 China Guizhou University State Key Laboratory of Public Big Data College of Computer Science and Technology Guiyang550025 China Advanced Cryptography and System Security Key Laboratory of Sichuan Province Chengdu610025 China Ministry of Industry and Information Technology Laboratory of Cryptography Application Technology Innovation and Testing Verification Beijing100015 China Southeast University School of Information Science and Engineering Nanjing210096 China

In image semantic communication, the complex wireless channel environment leads to the loss of image details and performance degradation during transmission. To address this issue, we propose an image semantic communication system based on Generative Adversarial Networks (GAN) and Relative Position-Encoding (RPE), named GAN-RpeSC. Specifically, in the system design, we introduce the GAN network at the output of the semantic communication framework to enhance the image restoration. We integrate the RPE module into the Visual Transformer (ViT) module, adding the RPE module to its Multihead Self Attention (MHSA), so that the model can better capture the spatial location information of the image. Experimental results show that the proposed GAN-RpeSC has significant advantages in improving image transmission quality, with a 0.3 dB improvement in peak signal-to-noise ratio (PSNR) compared to the ViT module alone. © 1997-2012 IEEE.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Fine-Grained Scheme for Distinguishing the Hotness of Warm Data to Reduce Segment Cleaning Overhead

SSRN

引用

SSRN 2025年

作者： Yang, Lihua Wang, Fang Lin, Weizhao Zhang, Wei Xiao, Yang Tan, Zhipeng Li, Jiaxin Lu, Kai College of Computer Science and Technology National University of Defense Technology Yanwachi Street Changsha410073 China Wuhan National Laboratory for Optoelectronics Key Laboratory of Information Storage System Engineering Research Center of Data Storage Systems and Technology Ministry of Education of China Huazhong University of Science and Technology Luoyu Road Wuhan430074 China

With the widespread adoption of flash memory, the Flash Friendly File system (F2FS) designed to flash memory characteristics has become widely-used in large data centers. However, F2FS encounters from significant cleaning overheads due to its logging scheme writes. We observe that warm data in F2FS account for a substantial proportion, at least 80%. Nevertheless, the mixed storage of warm data with varying hotness exacerbates segment cleaning challenges. To address this issue, we propose a scheme called M2H, which involves a fine-grained management of warm data hotness identified by the K-means clustering algorithm. M2H determines hotness by considering factors such as file block update distance, most recently used distance, and workload characteristics. M2H facilitates {M}ulti-log delayed writing and {M}odified segment cleaning based on {H}otness. To reduce costs associated with distinguishing data hotness at the file block level, we employ Mini Batch K-means and refer to this variant as M2H_MBK. Moreover, for servers equipped with GPUs, the clustering process can be offloaded to the GPU, known as M2H_GPU. We conduct a comprehensive comparison of traditional F2FS, M2H, M2H_MBK, and M2H_GPU on a real platform. Results show that compared to traditional F2FS, M2H_GPU reduces the number of segment cleanings by 54.41% to 97.93%. © 2025, The Authors. All rights reserved.

关键词： Flash memory

来源：评论

学校读者我要写书评

暂无评论

Multi-Relational Variational Contrastive Learning for Next POI Recommendation

Multi-Relational Variational Contrastive Learning for Next P...

引用

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

作者： Lin Chen Peipei Wang Xiaohui Han Lijuan Xu 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) Jinan China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China Quan Cheng Laboratory Jinan China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Next point-of-interest (POI) recommendation aims to predict the next interested POI to the user based on their historical check-in data in location-based social services. Most existing studies have attempted to model user visiting behaviors via sequence-based and graph-based models, and have achieved impressive performance. However, there is still room to explore the implicit transition preferences and contextual multiple semantic relationships among various POIs. To this end, we propose a novel graph-based Multi-Relational Variational Contrastive Learning (MRVCL) method for next POI recommendation, which captures local similarity associations and global contextual dependencies among POIs. Specifically, an order-free local-relational adaptive weighting module is designed to alleviate the problem of insufficient utilization of multi-hop neighbor information caused by the limit of neighbor order of nodes. We then develop a contextaware global-relational encoding module to capture implicit semantic sequential relationships. Finally, generative variational-contrastive learning is employed to construct a continuous representation of the latent features and reinforce the quality of representation learning. Extensive experiments on two real-world datasets validate that our MRVCL outperforms existing state-of-the-art methods on various evaluation metrics. To facilitate future research, our code and data are open-sourced at https://***/LinCH-en/MRVCL.

关键词： Representation learning Measurement Correlation Semantics Neural networks Contrastive learning Signal processing Transformers Encoding Speech processing

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：