检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Cai, Wenrui Liu, Qingjie Wang, Yunhong State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Zhongguancun Laboratory Beijing China Hangzhou Innovation Institute Beihang University Hangzhou China

Most state-of-the-art trackers adopt one-stream paradigm, using a single Vision Transformer for joint feature extraction and relation modeling of template and search region images. However, relation modeling between different image patches exhibits significant variations. For instance, background regions dominated by target-irrelevant information require reduced attention allocation, while foreground, particularly boundary areas, need to be be emphasized. A single model may not effectively handle all kinds of relation modeling simultaneously. In this paper, we propose a novel tracker called SPMTrack based on mixture-of-experts tailored for visual tracking task (TMoE), combining the capability of multiple experts to handle diverse relation modeling more flexibly. Benefiting from TMoE, we extend relation modeling from image pairs to spatio-temporal context, further improving tracking accuracy with minimal increase in model parameters. Moreover, we employ TMoE as a parameter-efficient fine-tuning method, substantially reducing trainable parameters, which enables us to train SPMTrack of varying scales efficiently and preserve the generalization ability of pretrained models to achieve superior performance. We conduct experiments on seven datasets, and experimental results demonstrate that our method significantly outperforms current state-of-the-art trackers. The source code is available at https://***/WenRuiCai/SPMTrack. Copyright © 2025, The Authors. All rights reserved.

关键词： Tuning

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

A survey of deep learning methods for density estimation and crowd counting

引用

Vicinagearth 2025年第1期2卷 1-37页

作者： Gao, Guangshuai Gao, Junyu Liu, Qingjie Wang, Qi Wang, Yunhong School of Information and Communication Engineering Zhongyuan University of Technology Zhengzhou China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China School of Artificial Intelligence OPtics and ElectroNics (iOPEN) Northwestern Polytechnical University Xi’an China

Accurately estimating the number of objects in a single image is a challenging yet meaningful task and has been applied in many applications such as urban planning and public safety. In various object counting tasks, crowd counting is particularly prominent due to its specific significance to social security and development. Fortunately, the development of the techniques for crowd counting can be generalized to other related fields such as vehicle counting and environment survey, if without taking their characteristics into account. Therefore, many researchers are devoting to crowd counting, and many excellent works have spurted out and significantly promote the development of crowd counting. However, one question we should consider is how far are we from solving the counting problem?. Limited by the costs of time and energy, we cannot analyze all algorithms. In this paper, we have surveyed 300+ works to comprehensively and systematically study the crowd counting models, mainly involving CNN-based density map estimation methods. Finally, according to evaluation metrics, we select the top three performers on their crowd counting datasets and analyze their merits and drawbacks. Through our analysis, we expect to make a reasonable inference and prediction for the future development of crowd counting, and meanwhile, it can also provide feasible solutions for the problem of object counting in other fields. We provide density maps and prediction results of some mainstream algorithms on the validation set of NWPU dataset for comparison and testing. Meanwhile, density map generation and evaluation tools are also provided. All the codes and evaluation results are made publicly available at https://***/gaoguangshuai/survey-for-crowd-counting .

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive Score Alignment Learning for Continual Perceptual Quality Assessment of 360-Degree Videos in virtual reality

arXiv

引用

arXiv 2025年

作者： Zhou, Kanglei Hao, Zikai Wang, Liyuan Liang, Xiaohui State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Zhongguancun Laboratory Beijing China Beihang University Beijing China Tsinghua University Beijing China

virtual reality Video Quality Assessment (VR-VQA) aims to evaluate the perceptual quality of 360-degree videos, which is crucial for ensuring a distortion-free user experience. Traditional VR-VQA methods trained on static datasets with limited distortion diversity struggle to balance correlation and precision. This becomes particularly critical when generalizing to diverse VR content and continually adapting to dynamic and evolving video distribution variations. To address these challenges, we propose a novel approach for assessing the perceptual quality of VR videos, Adaptive Score Alignment Learning (ASAL). ASAL integrates correlation loss with error loss to enhance alignment with human subjective ratings and precision in predicting perceptual quality. In particular, ASAL can naturally adapt to continually changing distributions through a feature space smoothing process that enhances generalization to unseen content. To further improve continual adaptation to dynamic VR environments, we extend ASAL with adaptive memory replay as a novel Continul Learning (CL) framework. Unlike traditional CL models, ASAL utilizes key frame extraction and feature adaptation to address the unique challenges of non-stationary variations with both the computation and storage restrictions of VR devices. We establish a comprehensive benchmark for VR-VQA and its CL counterpart, introducing new data splits and evaluation metrics. Our experiments demonstrate that ASAL outperforms recent strong baseline models, achieving overall correlation gains of up to 4.78% in the static joint training setting and 12.19% in the dynamic CL setting on various datasets. This validates the effectiveness of ASAL in addressing the inherent challenges of VR-VQA. Our code is available at https://***/ZhouKanglei/ASAL_CVQA. Copyright © 2025, The Authors. All rights reserved.

关键词： virtual environments

来源：评论

学校读者我要写书评

暂无评论

LBPE: Long-token-first Tokenization to Improve Large Language Models

LBPE: Long-token-first Tokenization to Improve Large Languag...

引用

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

作者： Haoran Lian Yizhe Xiong Zijia Lin Jianwei Niu Shasha Mo Hui Chen Peng Liu Guiguang Ding Beihang University Tsinghua University BNRist State Key Laboratory of Virtual Reality Technology and Systems Beihang University Zhongguancun Laboratory Zhengzhou University Research Institute of Industrial Technology Zhengzhou University Beijing Institute of Technology

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The prevalent use of Byte Pair Encoding (BPE) in Large Language Models (LLMs) facilitates robust handling of subword units and avoids issues of out-of-vocabulary words. Despite its success, a critical challenge persists: long tokens, rich in semantic information, have fewer occurrences in tokenized datasets compared to short tokens, which can result in imbalanced learning issue across different tokens. To address that, we propose LBPE, which prioritizes long tokens during the encoding process. LBPE generates tokens according to their descending order of token length rather than their ranks in the vocabulary, granting longer tokens higher priority during the encoding process. Consequently, LBPE smooths the frequency differences between short and long tokens, and thus mitigates the learning imbalance. Extensive experiments across diverse language modeling tasks demonstrate that LBPE consistently outperforms the original BPE, well demonstrating its effectiveness.

关键词： Vocabulary Large language models Semantics Signal processing Encoding Tokenization Acoustics Speech processing

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

PACF: Prototype Augmented Compact Features for Improving Domain Adaptive Object Detection

arXiv

引用

arXiv 2025年

作者： Liu, Chenguang Feng, Yongchao Zhang, Yanan Liu, Qingjie Wang, Yunhong State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China School of Computer Science and Information Engineering Hefei University of Technology Hefei230601 China Hangzhou Innovation Institute Beihang University Hangzhou310051 China

In recent years, there has been significant advancement in object detection. However, applying off-the-shelf detectors to a new domain leads to significant performance drop, caused by the domain gap. These detectors exhibit higher-variance class-conditional distributions in the target domain than that in the source domain, along with mean shift. To address this problem, we propose the Prototype Augmented Compact Features (PACF) framework to regularize the distribution of intra-class features. Specifically, we provide an in-depth theoretical analysis on the lower bound of the target features-related likelihood and derive the prototype cross entropy loss to further calibrate the distribution of target RoI features. Furthermore, a mutual regularization strategy is designed to enable the linear and prototype-based classifiers to learn from each other, promoting feature compactness while enhancing discriminability. Thanks to this PACF framework, we have obtained a more compact cross-domain feature space, within which the variance of the target features’ class-conditional distributions has significantly decreased, and the class-mean shift between the two domains has also been further reduced. The results on different adaptation settings are state-of-the-art, which demonstrate the board applicability and effectiveness of the proposed approach. Copyright © 2025, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

GooDFlight: Goal-Oriented Diffusion Model for Flight Trajectory Prediction

引用

IEEE Transactions on Aerospace and Electronic systems 2025年

作者： Yang, Songru Liu, Liqin Chen, Bowen Cheng, Shaoyuan Shi, Zhenwei Zou, Zhengxia Beihang University Department of Aerospace Intelligent Science and Technology School of Astronautics China Beihang University State Key Laboratory of Virtual Reality Technology and Systems Beijing100191 China Shanghai Artificial Intelligence Laboratory Shanghai200232 China Beijing Institute of Space Mechanics and Electricity Beijing100076 China

Flight trajectory prediction is an essential task in the air traffic control field. Previous approaches to this problem usually follow a single-stage or short-term intention-guided prediction paradigm, which suffers from problems such as insufficient trajectory prediction diversity, limited accuracy and interpretability. Different from existing paradigms, in this paper, we present GooDFlight - A Goal-oriented Diffusion Model for Flight trajectory prediction. GooDFlight is a long-term intention-guided, diversity-emphasizing framework that decouples the flight trajectory prediction process into two stages: goal estimation and trajectory prediction. In the first stage, we propose a One-then-all goal estimation method to sufficiently cover the macro-uncertainty in flight patterns and then tailor the interaction-aware joint goal distribution, which extends the flight intention from a single, deterministic ground truth to the empirical intention distribution from the similar experience. In the second stage, we employ a transformer-based diffusion model to generate stochastic flight trajectories conditioned on the intention estimations, modeling the micro-uncertainty in flight operations under each pattern estimated in stage one. In terms of evaluation metrics, existing metrics have difficulties in accurately reflecting the model's ability to handle the natural uncertainty of trajectories. We further propose a simple yet effective Global-local endpoints Variance (GLeV) metric for evaluating the diversity of predicted trajectories under social acceptance. Our proposed method is validated in-depth on TrajAir, a large-scale dataset collected from the real-world air traffic control environment at the Pittsburgh-Butler Regional Airport, a non-towered general aviation airport. The experimental results demonstrate that the proposed method significantly outperforms other methods in terms of both accuracy and diversity with superior interpretability. © 1965-2011 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

RMGNet: The Progressive Relationship-Mining Graph Neural Network for Text-to-image Person Re-identification

引用

IEEE Transactions on Circuits and systems for Video technology 2025年

作者： Zhang, Xin Liu, Kun Wang, Xinwang Zhou, Zhong Chen, Haiyong Hebei University of Technology School of Artificial Intelligence Tianjin300130 China Beihang University State Key Laboratory of Virtual Reality Technology and Systems Beijing100191 China Southeast University School of Instrument Science and Engineering Jiangsu Nanjing210018 China Wuxi Institute of Technology School of Integrated Circuit Wuxi214121 China

The Text-to-Image Person Re-identification (TI-ReID) task objective is to precisely identify the person's images with the textual description of the person. The mainstream research methods focus on cross-modal aligning local features, and overlook the learning of intra-modal and cross-modal relationships between different features. This renders the person features lacking in high-level semantic information. To resolve such issues, we propose the Progressive Relationship-Mining Graph Network (RMGNet), including the Intra-Modal Relationship-Mining (IMRM) and the Cross-Modal Relationship-Mining (CMRM) module. These modules are employed to model and mine semantic relationship information among different features. Specifically, the IMRM module models and mines the high-level semantic interrelationships inherent in the image and text features. The CMRM module introduces the nearest neighbor method to model cross-modal semantic relationships to enhance the cross-modal semantic correspondence capabilities of person features. On this basis, we design the Adaptive Corner Center (Acc) loss and the Coarse-to-Fine Learning (C2FL) strategy. These ensure the network receives consistent and effective metric learning supervision throughout the entirety of the training process. To validate the efficacy of the proposed method, extensive experiments are conducted on three prevalent datasets: CHUK-PEDES, ICFC-PEDES, and RSTPReid. The achieved mAP of 70.59%, 41.62%, and 49.58% surpassed those current state-of-the-art methods. © 2025 IEEE.

关键词： Graph neural networks

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

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：