检索结果-内蒙古大学图书馆

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Liu, Yajie Xu, Xinmeng Tu, Weiping Yang, Yuhong Xiao, Li Wuhan University National Engineering Research Center for Multimedia Software School of Computer Science China Wuhan University Hubei Key Laboratory of Multimedia and Network Communication Engineering China

ISBN: (纸本)9781728163277

We propose MiT-Net, a novel mix-transformer neural network with a pyramid encoder operating in the time domain, for the task of acoustic echo cancellation. The MiT-Net formulates acoustic echo cancellation as a supervised speech separation problem, in which near-end speech is separated from a single microphone recording and sent to the far end, and consists of two key components. First, we apply a pyramid encoder, which adopts the coarse-to-fine structure, to extract the latent correlations between double-end signals and to fuse them in a multiscale manner. Second, we propose a mix-transformer, a combination of local and global attention in a parallel way, to leverage local and global speech information for separation. Experimental results show that the proposed method outperforms recent AEC methods in terms of objective evaluation metrics. In addition, exploring the correlation between speech local and global features by using the mix-transformer significantly improves the system performance and shows more robustness than the conventional transformer. © 2023 IEEE.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

HAPG-SAQAM: Human Auditory Perception Guided Spatial Audio Quality Assessment Metric

HAPG-SAQAM: Human Auditory Perception Guided Spatial Audio Q...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zheng, Yuanming Yao, Jiaxuan Deng, Xiangyu Yang, Yuhong Liao, Ruiqi Tu, Weiping Lin, Cedar National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan China Guangdong OPPO Mobile Telecommunications Corp. Guangdong China

ISBN: (纸本)9798350368741

Spatial audio quality evaluation is essential for applications like virtual and augmented reality, where accurate sound reproduction enhances user immersion. While subjective listening tests are the gold standard, they are costly and time-consuming. To address this, we propose HAPG-SAQAM, an objective metric for assessing timbre quality, spatial quality, and overall quality of binaural audio, guided by human auditory perception. Our contributions include: (1) the Multi-scale Auditory Guided Feature Extraction (MAGFE) module, incorporating gammatone frequency cepstral coefficients for better alignment with human perception;(2) Perceptual Weighted Loss (PWL), optimizing the weighting of timbre quality (TQ) and spatial quality (SQ) loss based on subjective test data;and (3) data augmentation techniques to enhance robustness by amplifying perceptual distortions. Experimental results show HAPG-SAQAM improves correlation with subjective scores by 10%, with ablation studies confirming the contributions of its components to enhanced spatial and overall audio quality. © 2025 IEEE.

关键词： auditory perception spatial audio Speech and audio quality assessment subjective experiment timbre quality

来源：评论

学校读者我要写书评

暂无评论

Optimal Illumination Distance Metrics for Person Re-identification 21st

Optimal Illumination Distance Metrics for Person Re-identif...

引用

21st Pacific Rim International Conference on Artificial Intelligence, PRICAI 2024

作者： Wang, Chao Wang, Zhongyuan Hu, Ruimin Wang, Xiaochen Zhou, Wen National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China College of Information Engineering Nanjing University of Finance Economics Nanjing China

ISBN: (纸本)9789819601240

Person re-identification (Re-ID) has been widely used in public security and surveillance. Due to the influence of different shooting times and locations, can lead to lighting variations in the images captured by the camera, and the lighting variations seriously affect the Re-ID performance. Existing methods utilize images under different lighting conditions to transform to uniform lighting conditions to eliminate the effect of lighting on Re-ID. However, these methods ignore the fact that different illumination metric distances have different recognition performances. Therefore, we propose the optimal illumination distance metric, by analyzing different light distances for pedestrians in different light conditions, we find that there exists an optimal light condition in which the distance between image pairs is smaller than the distance in other light conditions. The distance under the optimal lighting condition is used in the retrieval process as the distance between its final sorted image pairs. To verify the effectiveness of our method, Market-1501-IA and Duke-MTMC-IA datasets are constructed, and a large number of experiments are conducted under different lighting conditions to verify the existence of the optimal lighting conditions and the effectiveness of the proposed method. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Lighting

来源：评论

学校读者我要写书评

暂无评论

VEGAS: Towards Visually Explainable and Grounded Artificial Social Intelligence 39

VEGAS: Towards Visually Explainable and Grounded Artificial ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Li, Hao Fei, Hao Hu, Zechao Yang, Zhengwei Wang, Zheng National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University China School of Computing National University of Singapore Singapore

ISBN: (纸本)157735897X

Social Intelligence Queries (Social-IQ) serve as the primary multimodal benchmark for evaluating a model’s social intelligence level. While impressive multiple-choice question (MCQ) accuracy is achieved by current solutions, increasing evidence shows that they are largely, and in some cases entirely, dependent on language modality, overlooking visual context. Additionally, the closed-set nature further prevents the exploration of whether and to what extent the reasoning path behind selection is correct. To address these limitations, we propose the Visually Explainable and Grounded Artificial Social Intelligence (VEGAS) model. As a generative multimodal model, VEGAS leverages open-ended answering to provide explainable responses, which enhances the clarity and evaluation of reasoning paths. To enable visually grounded answering, we propose a novel sampling strategy to provide the model with more relevant visual frames. We then enhance the model’s interpretation of these frames through Generalist Instruction Fine-Tuning (GIFT), which aims to: i) learn multimodal-language transformations for fundamental emotional social traits, and ii) establish multimodal joint reasoning capabilities. Extensive experiments, comprising modality ablation, open-ended assessments, and supervised MCQ evaluations, consistently show that VEGAS effectively utilizes visual information in reasoning to produce correct and also credible answers. We expect this work to offer a new perspective on Social-IQ and advance the development of human-like social AI. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Emotional intelligence

来源：评论

学校读者我要写书评

暂无评论

Learning from Imperfect Data: Towards Efficient Knowledge Distillation of Autoregressive Language Models for Text-to-SQL

Learning from Imperfect Data: Towards Efficient Knowledge Di...

引用

2024 Findings of the Association for Computational Linguistics, EMNLP 2024

作者： Zhong, Qihuang Chen, Kunfeng Ding, Liang Liu, Juhua Du, Bo Tao, Dacheng School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China The University of Sydney Australia Nanyang Technological University Singapore

ISBN: (纸本)9798891761681

Large Language Models (LLMs) have shown promising performance in text-to-SQL, which involves translating natural language questions into SQL queries. However, current text-to-SQL LLMs are computationally expensive and challenging to deploy in real-world applications, highlighting the importance of compressing them. To achieve this goal, knowledge distillation (KD) is a common approach, which aims to distill the larger teacher model into a smaller student model. While numerous KD methods for autoregressive LLMs have emerged recently, it is still under-explored whether they work well in complex text-to-SQL scenarios. To this end, we conduct a series of analyses and reveal that these KD methods generally fall short in balancing performance and efficiency. In response to this problem, we propose to improve the KD with Imperfect Data, namely KID, which effectively boosts the performance without introducing much training budget. The core of KID is to efficiently mitigate the training-inference mismatch by simulating the cascading effect1 of inference in the imperfect training data. Extensive experiments on 5 text-to-SQL benchmarks show that, KID can not only achieve consistent and significant performance gains (up to +5.83% average score) across all model types and sizes, but also effectively improve the training efficiency. © 2024 Association for Computational Linguistics.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

MTGA: Multi-View Temporal Granularity Aligned Aggregation for Event-Based Lip-Reading 39

MTGA: Multi-View Temporal Granularity Aligned Aggregation fo...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhang, Wenhao Wang, Jun Luo, Yong Yu, Lei Yu, Wei He, Zheng Shen, Jialie School of Computer Science National Engineering Research Center for Multimedia Software Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China School of Electronics and Information Wuhan University China Department of Computer Science City University of London United Kingdom

ISBN: (纸本)157735897X

Lip-reading is to utilize the visual information of the speaker's lip movements to recognize words and sentences. Existing event-based lip-reading solutions integrate different frame rate branches to learn spatio-temporal features of varying granularities. However, aggregating events into event frames inevitably leads to the loss of fine-grained temporal information within frames. To remedy this drawback, we propose a novel framework termed Multi-view Temporal Granularity aligned Aggregation (MTGA). Specifically, we first present a novel event representation method, namely time-segmented voxel graph list, where the most significant local voxels are temporally connected into a graph list. Then we design a spatio-temporal fusion module based on temporal granularity alignment, where the global spatial features extracted from event frames, together with the local relative spatial and temporal features contained in voxel graph list are effectively aligned and integrated. Finally, we design a temporal aggregation module that incorporates positional encoding, which enables the capture of local absolute spatial and global temporal information. Experiments demonstrate that our method outperforms both the event-based and video-based lip-reading counterparts. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Error Analysis of Spherically Constrained Least Squares Reformulation in Solving the Stackelberg Prediction Game 38

Error Analysis of Spherically Constrained Least Squares Refo...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Li, Xiyuan Liu, Weiwei School of Computer Science Wuhan University China National Engineering Research Center for Multimedia Software Wuhan University China Institute of Artificial Intelligence Wuhan University China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China

The Stackelberg prediction game (SPG) is a popular model for characterizing strategic interactions between a learner and an adversarial data provider. Although optimization problems in SPGs are often NP-hard, a notable special case involving the least squares loss (SPG-LS) has gained significant research attention recently [1, 2, 3]. The latest state-of-the-art method for solving the SPG-LS problem is the spherically constrained least squares reformulation (SCLS) method proposed in the work of [3]. However, the paper [3] lacks theoretical analysis on the error of the SCLS method, which limits its large-scale applications. In this paper, we investigate the estimation error between the learner obtained by the SCLS method and the actual learner. Specifically, we reframe the estimation error of the SCLS method as a Primary Optimization (PO) problem and utilize the Convex Gaussian min-max theorem (CGMT) to transform the PO problem into an Auxiliary Optimization (AO) problem. Subsequently, we provide a theoretical error analysis for the SCLS method based on this simplified AO problem. This analysis not only strengthens the theoretical framework of the SCLS method but also confirms the reliability of the learner produced by it. We further conduct experiments to validate our theorems, and the results are in excellent agreement with our theoretical predictions. © 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

Semantic-Aware Pseudo-Labeling for Unsupervised Meta-Learning

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年第7期47卷 5475-5488页

作者： Ouyang, Tianran Dong, Xingping Ye, Mang Du, Bo Shao, Ling Shen, Jianbing Wuhan University School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan430072 China University of Chinese Academy of Sciences UCAS-Terminus AI Lab Beijing101408 China University of Macau State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science 314100 China

In unsupervised meta-learning, the clustering-based pseudo-labeling approach is an attractive framework, since it is model-agnostic, allowing it to synergize with supervised algorithms to learn from unlabeled data. However, the pseudo-labels suffer from clustering noise and semantic chaos problems, further impacting the effectiveness of meta-learning. In this paper, we analyze and optimize the pseudo-labeling process, including encoding and clustering, aiming to generate semantic-like pseudo-labels to narrow the gap between unsupervised and supervised meta-learning. First, during the encoding, we observe that the embedding space of existing methods lacks clustering-friendly properties, which is the primary reason for clustering noise. To address this issue, we minimize the inter-to-intra-class similarity ratio to generate clustering-friendly embedding features and validate our approach through comprehensive experiments. Then, during the clustering, we find that the semantic quality of pseudo-labels is not adequately controlled, resulting in semantic chaos of pseudo-labels. We propose a semantic-stability index to measure the semantic quality of pseudo-labels quantitatively. Based on this index, we propose the Semantic-aware Pseudo-label Reassignment mechanism to generate semantic-like pseudo-labels for all samples. Our approach is model-agnostic and can easily be integrated into existing supervised methods. To demonstrate its generalization ability, we integrate it into two representative algorithms: MAML and EP. The results on three main few-shot benchmarks clearly show that the proposed method achieves significant improvement compared to state-of-the-art models. Notably, our approach also outperforms the corresponding supervised method in three tasks. © 1979-2012 IEEE.

关键词： Latent semantic analysis

来源：评论

学校读者我要写书评

暂无评论

Parameter Disparities Dissection for Backdoor Defense in Heterogeneous Federated Learning 38

Parameter Disparities Dissection for Backdoor Defense in Het...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Huang, Wenke Ye, Mang Shi, Zekun Wan, Guancheng Li, He Du, Bo National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering School of Computer Science Wuhan University Wuhan China Taikang Center for Life and Medical Sciences Wuhan University Wuhan China

Backdoor attacks pose a serious threat to federated systems, where malicious clients optimize on the triggered distribution to mislead the global model towards a predefined target. Existing backdoor defense methods typically require either homogeneous assumption, validation datasets, or client optimization conflicts. In our work, we observe that benign heterogeneous distributions and malicious triggered distributions exhibit distinct parameter importance degrees. We introduce the Fisher Discrepancy Cluster and Rescale (FDCR) method, which utilizes Fisher Information to calculate the degree of parameter importance for local distributions. This allows us to reweight client parameter updates and identify those with large discrepancies as backdoor attackers. Furthermore, we prioritize rescaling important parameters to expedite adaptation to the target distribution, encouraging significant elements to contribute more while diminishing the influence of trivial ones. This approach enables FDCR to handle backdoor attacks in heterogeneous federated learning environments. Empirical results on various heterogeneous federated scenarios under backdoor attacks demonstrate the effectiveness of our method. © 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

Diverse Co-saliency Feature Learning for Text-Based Person Retrieval

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 5465-5477页

作者： You, Shuai Chen, Cuiqun Feng, Yujian Liu, Hai Ji, Yimu Ye, Mang School of Internet of Things Nanjing China Anhui University School of Computer Science and Technology Hefei China South China Normal University school of computer Guangdong China NJUPT School of Computer Science Nanjing China Wuhan University National Engineering Research Center for Multimedia Software Hubei Key Laboratory of Multimedia and Network Communication Engineering Institute of Artificial Intelligence School of Computer Science Wuhan430072 China

Text-based Person Retrieval (TPR) plays a pivotal role in video surveillance systems for safeguarding public safety. As a fine-grained retrieval task, TPR faces the significant challenge of precisely capturing highly discriminative features across image and text modalities. Existing methods primarily focus on establishing modality-shared feature spaces to bridge cross-modal discrepancies. However, these methods are prone to disturbances from irrelevant information, such as background noises in the visual modality, and often over-emphasize specific local regions while neglecting the capture of diverse discriminative modal features, thereby limiting the robustness of cross-modal matching. In this paper, we introduce a novel framework, termed the Diverse Co-saliency Feature Learning Network (DCFL), which mines the co-saliency information between image and text modalities and enhances the diversity of cross-modal discriminative features while mitigating the interference of noise. Specifically, to construct cross-modal co-saliency features, we devise the Intra-modal Saliency Feature Learning (ISFL) and Cross-modal Saliency Feature Matching (CSFM) modules. ISFL employs a weighted mask mechanism to guide the model in reducing the impact of noise information in both modalities. Complementing ISFL, CSFM establishes consistent relationships between saliency features across modalities, leveraging text descriptions to align pedestrian-relevant visual regions. Furthermore, we propose the Diverse Co-saliency Feature Mining (DCFM) to bolster the diversity of discriminative co-saliency features across both image and text modalities. This module integrates a diversity regularization term, enabling the extraction of varied visual cues and capturing comprehensive features of the target individual. Extensive benchmark experiments demonstrate a substantial superiority of our approach over the state-of-the-art methods. The code will be released publicly. © 2005-2012 IEEE.

关键词： Feature extraction

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：