检索结果-内蒙古大学图书馆

17th Asian Conference on computer Vision, ACCV 2024

作者： Li, Yunhao Chen, Zibin Yan, Junming Ding, Ziyu Li, Jie Huang, Teng Pei, Xiaoqing Zhang, Zheng Wang, Qiong Pang, Yan Institute of Artificial Intelligence Guangzhou University Guangzhou China Cancer Center Sun Yat-sen University Guangzhou China Moxibustion and Rehabilitation Guangzhou University of Chinese Medicine Guangzhou China Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Beijing China

ISBN: (纸本)9789819609659

Medical video segmentation plays a crucial role in clinical diagnosis and therapeutic procedures by enabling dynamic tracking of breast lesions across frames in ultrasound videos, thereby improving segmentation accuracy. However, the existing methods struggle to strike a balance between segmentation accuracy and inference speed, which impedes their real-time deployment in resource-limited medical environments. To overcome these challenges, we introduce a rapid breast lesion segmentation framework named RbS. RbS employs the Stem module and RbSBlock to enhance representations through intra-frame analysis of ultrasound videos. Moreover, we have developed two versions of RbS: RbS-S boasts enhanced segmentation accuracy, while RbS-L ensures faster inference speeds. Experimental evidence indicates that RbS surpasses current leading models in both segmentation efficiency and prediction accuracy, particularly on resource-limited devices. Our contribution significantly propels the progress of developing efficient medical video segmentation frameworks suitable for various medical platforms. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Semantics-Aware Avatar Locomotion Adaption for Indoor Cross-Scene AR Telepresence

引用

IEEE Transactions on Visualization and computer Graphics 2025年 PP卷 PP页

作者： Li, Yi-Jun Yang, Hao-Zhong Shu, Wen-Tong Wang, Miao Tsinghua University Department of Computer Science and Technology Beijing100084 China Beihang University China Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beijing100191 China Zhongguancun Laboratory Beijing100094 China

Geographically dispersed users often rely on virtual avatars as intermediaries to facilitate interactive communication and collaboration. However, existing methods for augmented reality (AR) telepresence applications exhibit limitations, including restricted movement within confined sub-areas, lack of smooth transitions, and the necessity for manually establishing object mapping between dissimilar environments. We present a novel interactive AR framework for virtual avatar locomotion adaption while preserving semantic coherence across dissimilar indoor scenes. Initially, we conduct a preliminary user study to identify key attributes influencing preferred avatar movement. These attributes are quantified as features, and a dataset of user annotations on avatar movements is created. Based on the user interaction and scene configurations, we employ a deep reinforcement learning neural network to guide the avatar to the ideal position while maximizing semantic coherence. We validate our proposed framework through simulations and user studies by implementing an AR-based 3D telepresence prototype, demonstrating the efficacy of our framework in conveying user intentions across dissimilar environments, enabling natural and immersive 3D telepresence interactions. © 1995-2012 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous Learning

arXiv

引用

arXiv 2025年

作者： Zhong, Hanwen Chen, Jiaxin Zhang, Yutong Huang, Di Wang, Yunhong State Key Laboratory of Virtual Reality Technology and Systems Beihang University China School of Computer Science and Engineering Beihang University Beijing China

Multi-Task Learning (MTL) for Vision Transformer aims at enhancing the model capability by tackling multiple tasks simultaneously. Most recent works have predominantly focused on designing Mixture-of-Experts (MoE) structures and integrating Low-Rank Adaptation (LoRA) to efficiently perform multi-task learning. However, their rigid combination hampers both the optimization of MoE and the effectiveness of reparameterization of LoRA, leading to sub-optimal performance and low inference speed. In this work, we propose a novel approach dubbed Efficient Multi-Task Learning (EMTAL) by transforming a pre-trained Vision Transformer into an efficient multi-task learner during training, and reparameterizing the learned structure for efficient inference. Specifically, we firstly develop the MoEfied LoRA structure, which decomposes the pre-trained Transformer into a low-rank MoE structure and employ LoRA to fine-tune the parameters. Subsequently, we take into account the intrinsic asynchronous nature of multi-task learning and devise a learning Quality Retaining (QR) optimization mechanism, by leveraging the historical high-quality class logits to prevent a well-trained task from performance degradation. Finally, we design a router fading strategy to integrate the learned parameters into the original Transformer, archiving efficient inference. Extensive experiments on public benchmarks demonstrate the superiority of our method, compared to the state-of-the-art multi-task learning approaches. The project page is available at https://***/Yewen1486/EMTAL. Copyright © 2025, The Authors. All rights reserved.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Relational Clustering-Based Parallel Spaces Construction and Embedding for Dynamic Knowledge Graph

引用

IEEE Transactions on Big Data 2025年

作者： Liu, Yao Zhang, Yongfei Beihang University Beijing Key Laboratory of Digital Media School of Computer Science and Engineering Beijing100191 China Beihang University School of Computer Science and Engineering China Beihang University State Key Laboratory of Virtual Reality Technology and Systems Beijing100191 China Pengcheng Laboratory Shenzhen518055 China

With the increasing amount of data in various domains, knowledge graphs (KGs) have become powerful tools for representing complex and heterogeneous information in a structured way, and for extracting valuable information from knowledge graphs through embedding techniques to support downstream tasks such as recommendation and Q&A systems. Knowledge graphs consist of triples that are continuously added as knowledge is updated. However, most existing embedding models are designed for static graphs, requiring the entire model to be retrained for each update, which is time-consuming. Existing global dynamic embedding models focus on exploiting the structural and relational information of the whole graph to achieve embedding quality, resulting in reduced dynamic efficiency. To address this problem, we propose a relational clustering-based parallel space model in which knowledge from different domains is embedded in different subspaces, allowing each subspace to focus on the data characteristics of a specific domain, thereby improving the quality of knowledge. Second, the new data only affects some subspaces but not the performance of other spaces, improving the model's adaptability to dynamics. Furthermore, we employ two incremental approaches based on the type of added data to improve the efficiency of dynamic embedding while ensuring that the added data preserves the characteristics of the parallel space. The experimental results show that the dynamic embedding efficiency of our model is improved by an average of 50.3% compared to the SOTA dynamic embedding model for the link prediction task. Particularly on FB15K, our model not only improves the efficiency by 41% but also increases the accuracy by 7.5%, demonstrating the accuracy and efficiency of our model. © 2015 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Fg-T2M++: LLMs-Augmented Fine-Grained Text Driven Human Motion Generation

arXiv

引用

arXiv 2025年

作者： Wang, Yin Li, Mu Liu, Jiapeng Leng, Zhiying Li, Frederick W.B. Zhang, Ziyao Liang, Xiaohui B. State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Department of Computer Science University of Durham United Kingdom Zhongguancun Laboratory Beijing China

We address the challenging problem of fine-grained text-driven human motion generation. Existing works generate imprecise motions that fail to accurately capture relationships specified in text due to: (1) lack of effective text parsing for detailed semantic cues regarding body parts, (2) not fully modeling linguistic structures between words to comprehend text comprehensively. To tackle these limitations, we propose a novel fine-grained framework Fg-T2M++ that consists of: (1) an LLMs semantic parsing module to extract body part descriptions and semantics from text, (2) a hyperbolic text representation module to encode relational information between text units by embedding the syntactic dependency graph into hyperbolic space, and (3) a multi-modal fusion module to hierarchically fuse text and motion features. Extensive experiments on HumanML3D and KIT-ML datasets demonstrate that Fg-T2M++ outperforms SOTA methods, validating its ability to accurately generate motions adhering to comprehensive text semantics. 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

Multilevel features cascade fusion network for infrared video human behavior recognition

引用

Displays 2025年 87卷

作者： Han, Huiyan Ouyang, Nannan Kuang, Xinhe Wang, Song Xiong, Fengguang School of Computer Science and Technology North University of China Taiyuan030051 China Sydney Smart Technology College Northeastern University Qinhuangdao066004 China Shanxi Key Laboratory of Machine Vision and Virtual Reality Taiyuan030051 China

Human behavior recognition stands as a pivotal task in video analysis and understanding. While this field has garnered considerable attention within the visible spectrum, infrared imagery introduces distinct challenges, primarily due to its inherently blurry surface textures and less distinct features. Current mainstream methods typically rely on complex multi-stream networks to extract a range of human behavioral features. However, these methods frequently fall short in effectively utilizing complementary feature information directly, which can hinder the accuracy of behavior recognition. This study presents an end-to-end approach to address these challenges by proposing a Multilevel Features Cascade Fusion (MFCF) network. By using raw infrared video data as the direct input, this method simplifies the model architecture, thereby enhancing efficiency without sacrificing accuracy. Our approach incorporates a Non-local attention module to capture both global and hierarchical feature information—essential for decoding complex behaviors within infrared imagery. This is complemented by a deepwise features fusion module that integrates and cascades features at various levels. Through this multistage fusion process, the model develops a comprehensive understanding of the features, significantly improving its ability to interpret and classify nuanced human behaviors. Experimental results from benchmark datasets validate the effectiveness of our proposed method. Comparative analyses reveal that our approach surpasses existing state-of-the-art methods, demonstrating an average recognition accuracy improvement of 3.3% on the InfAR dataset and 2.3% on the IITR-IAR dataset, achieving overall accuracies of 90.00% and 85.56%, respectively. © 2024 The Author(s)

关键词： Infrared imaging

来源：评论

学校读者我要写书评

暂无评论

DSAA: Cross-modal transferable double sparse adversarial attacks from images to videos

引用

Neurocomputing 2025年 639卷

作者： Han, Xueqiang Zhang, Shihui Wang, Houlin Tian, Qing School of Information Science and Engineering Yanshan University Hebei Qinhuangdao China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Hebei Qinhuangdao China Department of Computer Science University of Alabama at Birmingham AL United States

Recent preliminary research has examined cross-modal attacks, enabling the transition of unlabeled attacks from images to videos. The current cross-modal attacks are mainly dense attacks, while sparse attacks have not been explored. To bridge this gap, this paper proposes a cross-modal transferable double sparse adversarial attack (DSAA) method. Specifically, DSAA incorporates both spatial sparsity and temporal sparsity. Firstly, we design a novel double-cross-shaped patch paradigm to achieve spatial sparsity. Leveraging this patch for perturbation addition enables a more effective global impact on video frames. Subsequently, we propose a uniform temporal sparsity strategy to achieve temporal sparsity. Even if only half of the frames are perturbed, the resulting average attack success rate remains comparable to that of perturbing all frames. Furthermore, we take into account the luminance, contrast, and structure of images and propose a structural similarity loss function (SSLF). By utilizing SSLF to measure the similarity of intermediate feature maps and incorporating it into perturbation optimization, DSAA achieves excellent attack performance. Extensive experiments demonstrate DSAA's superiority over state-of-the-art approaches in terms of attack success rate. The proposed DSAA uses video adversarial examples generated by four ImageNet-pretrained image models on Kinetics-400 and UCF-101 to attack six video recognition models, achieving average attack success rates of 85.83% and 82.02%, respectively. © 2025 Elsevier B.V.

关键词： Cross-modal attacks Spatial sparsity Temporal sparsity Unlabeled attacks Video adversarial examples

来源：评论

学校读者我要写书评

暂无评论

Audio-visual aware Foveated Rendering

引用

IEEE Transactions on Visualization and computer Graphics 2025年 PP卷 PP页

作者： Shi, Xuehuai Li, Yucheng Li, Jiaheng Wu, Jian Yin, Jieming Chen, Xiaobai Wang, Lili Nanjing University of Posts and Telecommunications School of Computer Science Jiangsu 210023 China Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beijing100191 China Beihang University School of Computer Science and Engineering Beijing100191 China

With the increasing complexity of geometry and rendering effects in virtual reality (VR) scenes, existing foveated rendering methods for VR head-mounted displays (HMDs) struggle to meet users' demands for VR scene rendering with high frame rates (≥ 60 f ps for rendering binocular foveated images in VR scenes containing over 50M triangles). Current research validates that auditory content affects the perception of the human visual system (HVS). However, existing foveated rendering methods primarily model the HVS's eccentricity-dependent visual perception ability on the visual content in VR while ignoring the impact of auditory content on the HVS's visual perception. In this paper, we introduce an auditory-content-based perceived rendering quality analysis to quantify the impact of visual perception under different auditory conditions in foveated rendering. Based on the analysis results, we propose an audio-visual aware foveated rendering method (AvFR). AvFR first constructs an audio-visual feature-driven perception model that predicts the eccentricity-based visual perception in real time by combining the scene's audio-visual content, and then proposes a foveated rendering cost optimization algorithm to adaptively control the shading rate of different regions with the guidance of the perception model. In complex scenes with visual and auditory content containing over 1.17M triangles, AvFR renders high-quality binocular foveated images at an average frame rate of 116 f ps. The results of the main user study and performance evaluation validate that AvFR achieves significant performance improvement (up to 1.4× speedup) without lowering the perceived visual quality compared with the state-of-the-art VR-HMD foveated rendering method. © 1995-2012 IEEE.

关键词： Foveated Rendering Perception-driven Rendering virtual Reality

来源：评论

学校读者我要写书评

暂无评论

Language-Inspired Relation Transfer for Few-shot Class-Incremental Learning

arXiv

引用

arXiv 2025年

作者： Zhao, Yifan Li, Jia Song, Zeyin Tian, Yonghong State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China School of Electronic and Computer Engineering Peking University Shenzhen518055 China School of Computer Science Peking University Beijing100871 China Pengcheng Laboratory Shenzhen518055 China

Depicting novel classes with language descriptions by observing few-shot samples is inherent in human-learning systems. This lifelong learning capability helps to distinguish new knowledge from old ones through the increase of open-world learning, namely Few-Shot Class-Incremental Learning (FSCIL). Existing works to solve this problem mainly rely on the careful tuning of visual encoders, which shows an evident trade-off between the base knowledge and incremental ones. Motivated by human learning systems, we propose a new Language-inspired Relation Transfer (LRT) paradigm to understand objects by joint visual clues and text depictions, composed of two major steps. We first transfer the pretrained text knowledge to the visual domains by proposing a graph relation transformation module and then fuse the visual and language embedding by a text-vision prototypical fusion module. Second, to mitigate the domain gap caused by visual finetuning, we propose context prompt learning for fast domain alignment and imagined contrastive learning to alleviate the insufficient text data during alignment. With collaborative learning of domain alignments and text-image transfer, our proposed LRT outperforms the state-of-the-art models by over 13% and 7% on the final session of miniImageNet and CIFAR-100 FSCIL benchmarks. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Geo-Enhanced High-Order Feature Interaction Network for Cloud API QoS Prediction 19th

Geo-Enhanced High-Order Feature Interaction Network for Clou...

引用

19th CCF Conference on computer Supported Cooperative Work and Social Computing, ChineseCSCW 2024

作者： Ma, Xinhong Zeng, Yehong Qi, Mingyang Si, Yali Chen, Zhen School of Information Science and Engineering Yanshan University Qinhuangdao066004 China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Yanshan University Qinhuangdao066004 China Changshu Institute of Technology Jiangsu Changshu215500 China

ISBN: (纸本)9789819623754

In the era of open cloud, cloud API is an important component and key enabling technology to achieve efficient data transmission, artificial intelligence algorithm empowerment, and software development cost reduction and efficiency. With the proliferation of cloud API with similar functionality, quality of service (QoS) becomes essential for differentiating cloud API performance, and QoS-driven prediction for cloud API has emerged as a critical topic for high quality cloud API selection. However, existing methods often inadequately utilize contextual information in resource-constrained scenario, limiting the improvement of cloud API prediction performance. We in this paper propose a geo-enhanced high-order feature interaction network (GHFIN) for cloud API QoS prediction. Firstly, a correlation analysis was conducted on real-world QoS dataset to explore the relationship between QoS data and geospatial context. Then, we design a geo-enhanced strategy that effectively utilizes the hierarchical relationships of geospatial entities (country, province, city, and district) through an offline real-time coordinate conversion module. On this basis, a geo-enhanced cloud API QoS prediction network GHFIN was designed, which aims to learn the high-order feature interactions through layer-wise feature stacking. Experimental results on two real-world QoS datasets illustrate the effectiveness of GHFIN compared to the classic and state-of-the-art methods, and our extensive analysis shows how the geospatial context and high-order feature interaction positively impact the performance of cloud API QoS prediction. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Quality of service

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：