检索结果-内蒙古大学图书馆

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Yi, Jinhan Liu, Xin Cheung, Yiu-Ming Xu, Xing Fan, Wentao He, Yi Department of Computer Science and Technology Huaqiao University Xiamen361021 China Xiamen Key Lab. of Computer Vision and Pattern Recognition Fujian Key Lab. of Big Data Intelligence and Security China Department of Computer Science Hong Kong Baptist University Kowloon Hong Kong School of Computer Science and Engineering University of Electronic Science and Technology of China China Provincial Key Laboratory for Computer Information Processing Technology Soochow University China

ISBN: (纸本)9781665438643

Existing cross-modal hashing still faces three challenges: (1) Most batch-based methods are unsuitable for processing large-scale and streaming data. (2) Current online methods often suffer from insufficient semantic association, while lacking flexibility to learn the hash functions for varying streaming data. (3) Existing supervised methods always require much computation time or accumulate large quantization loss to learn hash codes. To address above challenges, we present an efficient Online lab.l Consistent Hashing (OLCH) for cross-modal retrieval, which aims to incrementally learn hash codes for the current arriving data, while updating the hash functions at a streaming manner. To be specific, an online semantic representation learning framework is designed to adaptively preserve the semantic similarity across different modalities, and a mini-batch online gradient descent approach associated with forward-backward splitting is developed to optimize the hash functions. Accordingly, the hash codes are adaptively learned online with the high discriminative capability, while avoiding high computation complexity to process the streaming data. Experimental results show its outstanding performance in comparison with the-state-of-arts. © 2021 IEEE computer Society. All rights reserved.

关键词： Hash functions

来源：评论

学校读者我要写书评

暂无评论

Disentangling Hierarchical Features for Anomalous Sound Detection Under Domain Shift

arXiv

引用

arXiv 2025年

作者： Guan, Jian Tian, Jiantong Zhu, Qiaoxi Xiao, Feiyang Zhang, Hejing Liu, Xubo Group of Intelligent Signal Processing College of Computer Science and Technology Harbin Engineering University Harbin150001 China Acoustics Lab. University of Technology Sydney UltimoNSW2007 Australia Centre for Vision Speech and Signal Processing University of Surrey GuildfordGU2 7XH United Kingdom

Anomalous sound detection (ASD) encounters difficulties with domain shift, where the sounds of machines in target domains differ significantly from those in source domains due to varying operating conditions. Existing methods typically employ domain classifiers to enhance detection performance, but they often overlook the influence of domain-unrelated information. This oversight can hinder the model’s ability to clearly distinguish between domains, thereby weakening its capacity to differentiate normal from abnormal sounds. In this paper, we propose a Gradient Reversal-based Hierarchical feature Disentanglement (GRHD) method to address the above challenge. GRHD uses gradient reversal to separate domain-related features from domain-unrelated ones, resulting in more robust feature representations. Additionally, the method employs a hierarchical structure to guide the learning of fine-grained, domain-specific features by leveraging availab.e metadata, such as section IDs and machine sound attributes. Experimental results on the DCASE 2022 Challenge Task 2 dataset demonstrate that the proposed method significantly improves ASD performance under domain shift. Copyright © 2025, The Authors. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Autoregressive Queries for Adaptive Tracking with Spatio-Temporal Transformers

arXiv

引用

arXiv 2024年

作者： Xie, Jinxia Zhong, Bineng Mo, Zhiyi Zhang, Shengping Shi, Liangtao Song, Shuxiang Ji, Rongrong Key Laboratory of Education Blockchain and Intelligent Technology Ministry of Education China Guangxi Key Lab of Multi-Source Information Mining & Security China Guangxi Normal University Guilin541004 China Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou University China School of Computer Science and Technology Harbin Institute of Technology China Media Analytics and Computing Lab School of Informatics Xiamen University China

The rich spatio-temporal information is crucial to capture the complicated target appearance variations in visual tracking. However, most top-performing tracking algorithms rely on many hand-crafted components for spatio-temporal information aggregation. Consequently, the spatio-temporal information is far away from being fully explored. To alleviate this issue, we propose an adaptive tracker with spatio-temporal transformers (named AQATrack), which adopts simple autoregressive queries to effectively learn spatio-temporal information without many hand-designed components. Firstly, we introduce a set of learnable and autoregressive queries to capture the instantaneous target appearance changes in a sliding window fashion. Then, we design a novel attention mechanism for the interaction of existing queries to generate a new query in current frame. Finally, based on the initial target template and learnt autoregressive queries, a spatio-temporal information fusion module (STM) is designed for spatio-temporal formation aggregation to locate a target object. Benefiting from the STM, we can effectively combine the static appearance and instantaneous changes to guide robust tracking. Extensive experiments show that our method significantly improves the tracker’s performance on six popular tracking benchmarks: LaSOT, LaSOText, TrackingNet, GOT-10k, TNL2K, and *** and models will be here. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Boundary-aware Shadow Detection via Mask Decoupling and Feature Correction

Boundary-aware Shadow Detection via Mask Decoupling and Feat...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Jueyu Chen Guanyu Xing Jingwei Liao Housheng Wei Yanli Liu College of Computer Science Sichuan University Chengdu China National Key Lab. of Fundamental Science on Synthetic Vision Sichuan University Chengdu China Department of Information Sciences and Technology George Mason University Fairfax Virginia USA

It is well-recognized that correctly detecting shadow boundaries is much more difficult than shadow interior pixels in real-world situations due to the rapid intensity and color transitions near shadow boundaries and the complex background textures. This paper presents a novel boundary-aware shadow detection network to enhance the overall detection performance, especially on challenging shadow boundaries. To enable the network aware of shadow boundaries and balance the supervision between image pixels on the boundary and inside of shadows, the shadow mask is decoupled into a body mask and boundary mask. The feature correction module is designed after feature interaction to eliminate various shadow inferences further. Experimental results show that the proposed network outperforms the state-of-the-art shadow detection methods on four shadow detection benchmark datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Autoregressive Queries for Adaptive Tracking with Spatio-Temporal Transformers

Autoregressive Queries for Adaptive Tracking with Spatio-Tem...

引用

Conference on computer vision and Pattern Recognition (CVPR)

作者： Jinxia Xie Bineng Zhong Zhiyi Mo Shengping Zhang Liangtao Shi Shuxiang Song Rongrong Ji Key Laboratory of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin China Guangxi Key Lab of Multi-Source Information Mining & Security Guangxi Normal University Guilin China Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou University School of Computer Science and Technology Harbin Institute of Technology Media Analytics and Computing Lab School of Informatics Xiamen University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

The rich spatio-temporal information is crucial to capture the complicated target appearance variations in visual tracking. However, most top-performing tracking algorithms rely on many hand-crafted components for spatio-temporal information aggregation. Consequently, the spatio-temporal information is far away from being fully explored. To alleviate this issue, we propose an adaptive tracker with spatio-temporal transformers (named AQA-Track), which adopts simple autoregressive queries to effectively learn spatio-temporal information without many hand-designed components. Firstly, we introduce a set of learnable and autoregressive queries to capture the instantaneous target appearance changes in a sliding window fashion. Then, we design a novel attention mechanism for the interaction of existing queries to generate a new query in current frame. Finally, based on the initial target template and learnt autoregressive queries, a spatio-temporal information fusion module (STM) is designed for spatiotemporal formation aggregation to locate a target object. Benefiting from the STM, we can effectively combine the static appearance and instantaneous changes to guide robust tracking. Extensive experiments show that our method significantly improves the tracker's performance on six popular tracking benchmarks: LaSOT, LaSOT ext , TrackingNet, GOT-10k, TNL2K, and UAV123. Code and models will be https://***/orgs/GXNU-Zhonglab.

关键词： Adaptation models Visualization computer vision Target tracking Computational modeling Transformers Market research

来源：评论

学校读者我要写书评

暂无评论

Bridging Gaps in HCI: Advancing Education, Research, and Careers in Asia

Bridging Gaps in HCI: Advancing Education, Research, and Car...

引用

2025 CHI Conference on Human Factors in Computing Systems, CHI EA 2025

作者： Gamage, Dilrukshi Cheng, Shiwei Mudliar, Preeti Lu, Zhicong Zhao, Shengdong Ahmed, Nova Ma, Xiaojuan Lee, Uichin Wang, Ding Department of Computation and Intelligent Systems University of Colombo School of Computing Colombo Sri Lanka Zhejiang University of Technology Hangzhou China International Institute of Information Technology Bangalore Bangalore India Department of Computer Science City University of Hong Kong Hong Kong School of Creative Media City University of Hong Kong Hong Kong Design Inclusion and Access Lab. Department of Electrical and Computer Engineering North South University Dhaka Dhaka Bangladesh Hong Kong University of Science and Technology Hong Kong Hong Kong School of Computing KAIST Daejeon Korea Republic of Google AtlantaGA United States

ISBN: (纸本)9798400713958

Asia’s Human-computer Interaction (HCI) landscape is rapidly evolving, yet it faces distinct challenges in curriculum development, research establishment, and career navigation. This panel discussion, hosted by Asia SIGCHI Committee (ASC) at CHI2025, will bring together distinguished experts to address these challenges and explore strategies for fostering a robust and inclusive HCI community in Asia. Panelists will discuss the integration of culturally relevant content in HCI education, approaches to enhancing research visibility on international platforms, and initiatives to bridge gaps between academic training and industry expectations. Through an engaging discussion and audience interaction, the panel aims to identify actionable solutions, promote collab.ration, and inspire future initiatives that strengthen HCI’s growth across the region. Participants will gain valuable insights into overcoming systemic barriers while building sustainable and impactful HCI programs tailored to Asia’s unique sociocultural dynamics. This panel seeks to advance the global relevance and contributions of HCI in Asia. © 2025 Copyright held by the owner/author(s).

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

NeurIPS’22 Cross-Domain MetaDL Challenge: Results and lessons learned 36

NeurIPS’22 Cross-Domain MetaDL Challenge: Results and lesso...

引用

36th Annual Conference on Neural Information Processing Systems - Competition Track, NeurIPS 2022

作者： Carrión-Ojeda, Dustin Alam, Mahbubul Escalera, Sergio Farahat, Ahmed Ghosh, Dipanjan Diaz, Teresa Gonzalez Gupta, Chetan Guyon, Isabelle Ky, Joël Roman Lee, Xian Yeow Liu, Xin Mohr, Felix Nguyen, Manh Hung Pintelas, Emmanuel Roth, Stefan Schaub-Meyer, Simone Sun, Haozhe Ullah, Ihsan Vanschoren, Joaquin Vidyaratne, Lasitha Wu, Jiamin Yin, Xiaotian Department of Computer Science Technical University of Darmstadt Germany hessian.AI Germany Industrial AI Lab. Hitachi America Ltd. R&D United States ChaLearn United States Universitat de Barcelona Barcelona Spain Computer Vision Center Bellaterra Barcelona Spain LISN INRIA CNRS Université Paris-Saclay France Google Brain United States RESIST INRIA CNRS Université de Lorraine France Universidad de La Sabana Chía Colombia Department of Mathematics University of Patras Greece Eindhoven University of Technology Netherlands University of Science and Technology of China China

Deep neural networks have demonstrated the ability to outperform humans in multiple tasks, but they often require substantial amounts of data and computational resources. These resources may be limited in certain fields. Meta-learning seeks to overcome these challenges by utilizing past task experiences to efficiently solve new tasks, achieving better performance with limited training data and modest computational resources. To further advance the ChaLearn MetaDL competition series, we organized the Cross-Domain MetaDL Challenge for NeurIPS’22. This challenge aimed to solve "any-way" and "any-shot" tasks from 10 domains through cross-domain meta-learning. In this paper, authored collab.ratively by the competition organizers, top-ranked participants, and external collab.rators, we describe the technical aspects of the competition, baseline methods, and top-ranked approaches that have been open-sourced. Additionally, we provide a detailed analysis of the competition results. Lessons learned from this competition include the critical role of pre-trained backbones, the necessity of preventing overfitting, and the significance of using data augmentation or domain adaptation techniques in conjunction with extra optimizations to improve performance. © 2023 D. Carrión-Ojeda et al.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Inconsistency Distillation For Consistency:Enhancing Multi-View Clustering via Mutual Contrastive Teacher-Student Leaning

Inconsistency Distillation For Consistency:Enhancing Multi-V...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Dunqiang Liu Shu-Juan Peng Xin Liu Lei Zhu Zhen Cui Taihao Li Dept. of Comput. Sci. & Fujian Key Lab. of Big Data Intelligence and Security Huaqiao University Xiamen China Zhejiang Lab Hangzhou China Xiamen Key Lab. of Computer Vision and Pattern Recognition Huaqiao University Xiamen China Key Lab. of Computer Vision and Machine Learning (Huaqiao University) Fujian Province University Xiamen China School of Information Sci. and Eng. Shandong Normal University Jinan China School of Computer Sci. and Eng. Nanjing University of Science and Technology Nanjing China

Multi-view clustering has attracted more attention recently since many real-world data are comprised of different representations or views. Recent multi-view clustering works mainly exploit the instance consistency to obtain the shared representations across different views, and apply a single-view clustering method to perform data partitions. However, these existing methods often ignore the inconsistency of instance associations within the views, which may enlarge the intra-class diversity among the views and therefore degrade the clustering performance. To address this issue, this paper proposes an efficient mutual contrastive teacher-student leaning (MC-TSL) model to enhance the multi-view clustering, which is the first attempt to study the inconsistency distillation for consistency learning. First, the proposed MC-TSL approach exploits a view-specific encoder with two heads, an instance encoding head and a semantic distillation head, respectively, for capturing the consistent and discriminative feature representations. To be specific, the former head exploits a cross-view contrastive learning method to obtain a redundancy-free consistent representation at the instance level, while the latter head designs a mutual teacher-student learning module to capture the intra-view information at semantic level. By training these two heads in an end-to-end manner, the discriminative multi-view embeddings are efficiently obtained and refined by minimizing the weighted sum of the reconstruction loss, contrastive loss and contrast distillation loss. Extensive experiments verify the superiorities of the proposed MC-TSL framework and show its competitive clustering performances.

关键词： Training Learning systems Clustering methods Semantics Encoding Data mining

来源：评论

学校读者我要写书评

暂无评论

Disambiguation of Chinese Polyphones in an End-to-End Framework with Semantic Features Extracted by Pre-trained BERT

arXiv

引用

arXiv 2025年

作者： Dai, Dongyang Wu, Zhiyong Kang, Shiyin Wu, Xixin Jia, Jia Su, Dan Yu, Dong Meng, Helen Tsinghua-CUHK Joint Research Center for Media Sciences Technologies and Systems Graduate School at Shenzhen Tsinghua University Shenzhen China Department of Computer Science and Technology Tsinghua University Beijing China Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Shatin N.T. Hong Kong Tencent AI Lab. Tencent Shenzhen China

Grapheme-to-phoneme (G2P) conversion serves as an essential component in Chinese Mandarin text-to-speech (TTS) system, where polyphone disambiguation is the core issue. In this paper, we propose an end-to-end framework to predict the pronunciation of a polyphonic character, which accepts sentence containing polyphonic character as input in the form of Chinese character sequence without the necessity of any preprocessing. The proposed method consists of a pre-trained bidirectional encoder representations from Transformers (BERT) model and a neural network (NN) based classifier. The pre-trained BERT model extracts semantic features from a raw Chinese character sequence and the NN based classifier predicts the polyphonic character’s pronunciation according to BERT output. In out experiments, we implemented three classifiers, a fully-connected network based classifier, a long short-term memory (LSTM) network based classifier and a Transformer block based classifier. The experimental results compared with the baseline approach based on LSTM demonstrate that, the pre-trained model extracts effective semantic features, which greatly enhances the performance of polyphone disambiguation. In addition, we also explored the impact of contextual information on polyphone disambiguation. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Towards efficient human-robot cooperation for socially-aware robot navigation in human-populated environments: the SNAPE framework

Towards efficient human-robot cooperation for socially-aware...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： A. Vega-Magro R. Gondkar L.J. Manso P. Núñez Robotics and Artificial Vision Lab. RoboLab Group University of Extremadura Spain Pune Institute of Computer Technology Pune University India College of Engineering and Physical Sciences Aston University Birmingham UK

It is widely accepted that in the future, robots will cooperate with humans in everyday tasks. Robots interacting with humans will require social awareness when performing their tasks which will require navigation. While navigating, robots should aim to avoid distressing people in order to maximize their chance of social acceptance. For instance, avoiding getting too close to people or disrupting interactions. Most research approaches these problems by planning socially accepted paths, however, in everyday situations, there are many examples where a simple path planner cannot solve all of the predicted robots’ navigation problems. For instance, requesting permission to interrupt a conversation if an alternative path cannot be determined requires deliberative skills. This article presents the Social Navigation framework for Autonomous robots in Populated Environments (SNAPE), where different software agents are integrated within a robotics cognitive architecture. SNAPE addresses action planning aimed at social-awareness navigation in realistic situations: it plans socially accepted paths and conversations to negotiate its trajectory to reach targets. In this article, the framework is evaluated in different use-cases where the robot, during its navigation, has to interact with different people in order to reach its goal. The results show that participants report that the robot’s behavior was realistic and human-like.

关键词： Navigation Conferences computer architecture Software agents Planning Trajectory Task analysis

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：