检索结果-内蒙古大学图书馆

Traffic Simulator: A Traffic Risk Hotspot Identification Platform

学校读者我要写书评

暂无评论

Traffic Simulator: A Traffic Risk Hotspot Identification Pla...

Smart World Congress (SWC), IEEE

作者： Qingxian Tang Changzhen Liu Jiannan Gao Liwei Si Longbiao Chen Cheng Wang Fujian Key Laboratory of Sensing and Computing for Smart Cities Xiamen University P.R. China Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University P.R. China School of Information Xiamen University P.R. China

With the increment of urban population, the number of vehicles on the road is also constantly increasing, leading to a rise in traffic risks. Frequent urban traffic accidents significantly threaten people’s lives, property, and urban traffic operation. Moreover, traffic violations on the road can cause disorderly traffic, resulting in even more accidents. In order to reduce traffic accidents and ensure people’s safety, urban authorities have to formulate targeted traffic safety strategies for traffic accident risk areas in cities. In this paper, we develop Traffic Simulator, a simulator that can comprehensively, dynamically, and efficiently infer and diagnose traffic risk hotspots in the city. Firstly, we import multi-source heterogeneous data sources from Xiamen, including 3D models, vehicle trajectory data, POIs, and weather into Unity. Secondly, we propose several traffic risk identification algorithms based on the simulator. Thirdly, we perform weighted clustering on identified traffic risk behaviors to obtain traffic risk hotspots. To evaluate the Traffic-Simulator, we conducted extensive research on large-scale and real vehicle GPS trajectories collected in Xiamen. The results show that the framework can effectively and efficiently infer traffic risk hotspot areas in cities.

关键词：

Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective

学校读者我要写书评

暂无评论

Solving Oscillation Problem in Post-Training Quantization Th...

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yuexiao Ma Huixia Li Xiawu Zheng Xuefeng Xiao Rui Wang Shilei Wen Xin Pan Fei Chao Rongrong Ji Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China School of Informatics Xiamen University P.R. China ByteDance Inc. Peng Cheng Laboratory Shenzhen China Shenzhen Research Institute of Xiamen University

Post-training quantization (PTQ) is widely regarded as one of the most efficient compression methods practically, benefitting from its data privacy and low computation costs. We argue that an overlooked problem of oscillation is in the PTQ methods. In this paper, we take the initiative to explore and present a theoretical proof to explain why such a problem is essential in PTQ. And then, we try to solve this problem by introducing a principled and generalized frame-work theoretically. In particular, we first formulate the oscillation in PTQ and prove the problem is caused by the difference in module capacity. To this end, we define the module capacity (ModCap) under data-dependent and data-free scenarios, where the differentials between adjacent modules are used to measure the degree of oscillation. The problem is then solved by selecting top-k differentials, in which the corresponding modules are jointly optimized and quantized. Extensive experiments demonstrate that our method successfully reduces the performance drop and is generalized to different neural networks and PTQ methods. For example, with 2/4 bit ResNet-50 quantization, our method surpasses the previous state-of-the-art method by 1.9%. It becomes more significant on small model quantization, e.g. surpasses BRECQ method by 6.61% on MobileNetV2 × 0.5.

关键词：

Personalized Federated Learning on Heterogeneous and Long-Tailed Data via Expert Collaborative Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lv, Fengling Shang, Xinyi Zhou, Yang Zhang, Yiqun Li, Mengke Lu, Yang Key Laboratory of Multimedia Trusted Perception and Efficient Computing Xiamen University China University College London United Kingdom A*STAR Institute of High Performance Computing Singapore School of Computer Science and Technology Guangdong University of Technology Guangzhou China Guangdong Laboratory of Artificial Intelligence and Digital Economy Shenzhen China Fujian Key Laboratory of Sensing and Computing for Smart City School of Informatics Xiamen University China

Personalized Federated Learning (PFL) aims to acquire customized models for each client without disclosing raw data by leveraging the collective knowledge of distributed clients. However, the data collected in real-world scenarios is likely to follow a long-tailed distribution. For example, in the medical domain, it is more common for the number of general health notes to be much larger than those specifically related to certain diseases. The presence of long-tailed data can significantly degrade the performance of PFL models. Additionally, due to the diverse environments in which each client operates, data heterogeneity is also a classic challenge in federated learning. In this paper, we explore the joint problem of global long-tailed distribution and data heterogeneity in PFL and propose a method called Expert Collaborative Learning (ECL) to tackle this problem. Specifically, each client has multiple experts, and each expert has a different training subset, which ensures that each class, especially the minority classes, receives sufficient training. Multiple experts collaborate synergistically to produce the final prediction output. Without special bells and whistles, the vanilla ECL outperforms other state-of-the-art PFL methods on several benchmark datasets under different degrees of data heterogeneity and long-tailed distribution. Copyright © 2024, The Authors. All rights reserved.

关键词： Federated learning

Training-Free Hierarchical Scene Understanding for Gaussian Splatting with Superpoint Graphs

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Dai, Shaohui Qu, Yansong Li, Zheyan Li, Xinyang Zhang, Shengchuan Cao, Liujuan Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University China

Bridging natural language and 3D geometry is a crucial step toward flexible, language-driven scene understanding. While recent advances in 3D Gaussian Splatting (3DGS) have enabled fast and high-quality scene reconstruction, research has also explored incorporating open-vocabulary understanding into 3DGS. However, most existing methods require iterative optimization over per-view 2D semantic feature maps, which not only results in inefficiencies but also leads to inconsistent 3D semantics across views. To address these limitations, we introduce a training-free framework that constructs a superpoint graph directly from Gaussian primitives. The superpoint graph partitions the scene into spatially compact and semantically coherent regions, forming view-consistent 3D entities and providing a structured foundation for open-vocabulary understanding. Based on the graph structure, we design an efficient reprojection strategy that lifts 2D semantic features onto the superpoints, avoiding costly multi-view iterative training. The resulting representation ensures strong 3D semantic coherence and naturally supports hierarchical understanding, enabling both coarse- and fine-grained open-vocabulary perception within a unified semantic field. Extensive experiments demonstrate that our method achieves state-of-the-art open-vocabulary segmentation performance, with semantic field reconstruction completed over 30× faster. Our code will be available at https://***/Atrovast/THGS. Copyright © 2025, The Authors. All rights reserved.

关键词： Gaussian distribution

Long-Tailed Visual Recognition via Self-Heterogeneous Integration with Knowledge Excavation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Jin, Yan Li, Mengke Lu, Yang Cheung, Yiu-Ming Wang, Hanzi Fujian Key Laboratory of Sensing and Computing for Smart City School of Informatics Xiamen University Xiamen China Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University Xiamen China Shenzhen China Department of Computer Science Hong Kong Baptist University Hong Kong

Deep neural networks have made huge progress in the last few decades. However, as the real-world data often exhibits a long-tailed distribution, vanilla deep models tend to be heavily biased toward the majority classes. To address this problem, state-of-the-art methods usually adopt a mixture of experts (MoE) to focus on different parts of the long-tailed distribution. Experts in these methods are with the same model depth, which neglects the fact that different classes may have different preferences to be fit by models with different depths. To this end, we propose a novel MoE-based method called Self-Heterogeneous Integration with Knowledge Excavation (SHIKE). We first propose Depth-wise Knowledge Fusion (DKF) to fuse features between different shallow parts and the deep part in one network for each expert, which makes experts more diverse in terms of representation. Based on DKF, we further propose Dynamic Knowledge Transfer (DKT) to reduce the influence of the hardest negative class that has a non-negligible impact on the tail classes in our MoE framework. As a result, the classification accuracy of long-tailed data can be significantly improved, especially for the tail classes. SHIKE achieves the state-of-the-art performance of 56.3%, 60.3%, 75.4% and 41.9% on CIFAR100-LT (IF100), ImageNet-LT, iNaturalist 2018, and Places-LT, respectively. The source code is available at https://***/jinyan-06/SHIKE. Copyright © 2023, The Authors. All rights reserved.

关键词： Excavation

Exploiting Point-Language Models with Dual-Prompts for 3D Anomaly Detection

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wang, Jiaxiang Xu, Haote Chen, Xiaolu Jakobsson, Andreas Xu, Haodi Huang, Yue Ding, Xinghao Tu, Xiaotng Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University Fujian Xiamen361005 China School of Informatics Xiamen University Fujian Xiamen361005 China Institute of Artificial Intelligence Xiamen University Fujian Xiamen361005 China Mathematical Statistics Lund University Sweden

Anomaly detection (AD) in 3D point clouds is crucial in a wide range of industrial applications, especially in various forms of precision manufacturing. Considering the industrial demand for reliable 3D AD, several methods have been developed. However, most of these approaches typically require training separate models for each category, which is memory-intensive and lacks flexibility. In this paper, we propose a novel Point-Language model with dual-prompts for 3D ANomaly dEtection (PLANE). The approach leverages multi-modal prompts to extend the strong generalization capabilities of pre-trained Point-Language Models (PLMs) to the domain of 3D point cloud AD, achieving impressive detection performance across multiple categories using a single model. Specifically, we propose a dual-prompt learning method, incorporating both text and point cloud prompts. The method utilizes a dynamic prompt creator module (DPCM) to produce sample-specific dynamic prompts, which are then integrated with class-specific static prompts for each modality, effectively driving the PLMs. Additionally, based on the characteristics of point cloud data, we propose a pseudo 3D anomaly generation method (Ano3D) to improve the model’s detection capabilities in unsupervised setting. Experimental results demonstrate that the proposed method, which is under the multi-class-one-model paradigm, achieves a +8.7%/+17% gain on anomaly detection and localization performance as compared to the state-of-the-art one-class-one-model methods for the Anomaly-ShapeNet dataset, and obtains +4.3%/+4.1% gain for the Real3D-AD dataset. Code will be available upon publication. Copyright © 2025, The Authors. All rights reserved.

关键词： Digital elevation model

Bridging Synthetic-to-Real Gaps: Frequency-Aware Perturbation and Selection for Single-shot Multi-Parametric Mapping Reconstruction

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Fan, Linyu Wang, Che Ye, Ming Yang, Qizhi Wu, Zejun Ding, Xinghao Huang, Yue Bao, Jianfeng Cai, Shuhui Cai, Congbo Department of Electronic Science Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance Xiamen University Xiamen361005 China Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University Xiamen361005 China Department of Magnetic Resonance Imaging The First Affiliated Hospital of Zhengzhou University Zhengzhou University Zhengzhou450052 China

Data-centric artificial intelligence (AI) has remarkably advanced medical imaging, with emerging methods using synthetic data to address data scarcity while introducing synthetic-to-real gaps. Unsupervised domain adaptation (UDA) shows promise in ground truth-scarce tasks, but its application in reconstruction remains underexplored. Although multiple overlapping-echo detachment (MOLED) achieves ultra-fast multi-parametric reconstruction, extending its application to various clinical scenarios, the quality suffers from deficiency in mitigating the domain gap, difficulty in maintaining structural integrity, and inadequacy in ensuring mapping accuracy. To resolve these issues, we proposed frequency-aware perturbation and selection (FPS), comprising Wasserstein distance-modulated frequency-aware perturbation (WDFP) and hierarchical frequency-aware selection network (HFSNet), which integrates frequency-aware adaptive selection (FAS), compact FAS (cFAS) and feature-aware architecture integration (FAI). Specifically, perturbation activates domain-invariant feature learning within uncertainty, while selection refines optimal solutions within perturbation, establishing a robust and closed-loop learning pathway. Extensive experiments on synthetic data, along with diverse real clinical cases from 5 healthy volunteers, 94 ischemic stroke patients, and 46 meningioma patients, demonstrate the superiority and clinical applicability of FPS. Furthermore, FPS is applied to diffusion tensor imaging (DTI), underscoring its versatility and potential for broader medical applications. The code is available at https://***/flyannie/FPS. Copyright © 2025, The Authors. All rights reserved.

关键词： Diffusion tensor imaging

Approximated Prompt Tuning for Vision-Language Pre-trained Models

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wu, Qiong Huang, Shubin Zhou, Yiyi Dai, Pingyang Shu, Annan Jiang, Guannan Ji, Rongrong Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University 361005 China Institute of Artificial Intelligence Xiamen University 361005 China Intelligent Manufacturing Department Contemporary Amperex Technology Co. Limited China

Prompt tuning is a parameter-efficient way to deploy large-scale pre-trained models to downstream tasks by adding task-specific tokens. In terms of vision-language pre-trained (VLP) models, prompt tuning often requires a large number of learnable tokens to bridge the gap between the pre-training and downstream tasks, which greatly exacerbates the already high computational overhead. In this paper, we revisit the principle of prompt tuning for Transformer-based VLP models, and reveal that the impact of soft prompt tokens can be actually approximated via independent information diffusion steps, thereby avoiding the expensive global attention modeling and reducing the computational complexity to a large extent. Based on this finding, we propose a novel Approximated Prompt Tuning (APT) approach towards efficient VL transfer learning. To validate APT, we apply it to two representative VLP models, namely ViLT and METER, and conduct extensive experiments on a bunch of downstream tasks. Meanwhile, the generalization of APT is also validated on CLIP for image classification and StableDiffusion for text-to-image generation. The experimental results not only show the superior performance gains and computation efficiency of APT against the conventional prompt tuning methods, e.g., +7.01% accuracy and −82.30% additional computation overhead on METER, but also confirm its merits over other parameter-efficient transfer learning approaches1 © 2023, CC BY.

关键词： Text processing

CIMI4D: A Large Multimodal Climbing Motion Dataset under Human-scene Interactions

学校读者我要写书评

暂无评论

CIMI4D: A Large Multimodal Climbing Motion Dataset under Hum...

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Ming Yan Xin Wang Yudi Dai Siqi Shen Chenglu Wen Lan Xu Yuexin Ma Cheng Wang Fujian Key Laboratory of Sensing and Computing for Smart Cities Xiamen University National Institute for Data Science in Health and Medicine Xiamen University Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China School of Informatics Xiamen University Shanghai Engineering Research Center of Intelligent Vision and Imaging ShanghaiTech University

Motion capture is a long-standing research problem. Although it has been studied for decades, the majority of research focus on ground-based movements such as walking, sitting, dancing, etc. Off- grounded actions such as climbing are largely overlooked. As an important type of action in sports and firefighting field, the climbing movements is challenging to capture because of its complex back poses, intricate human-scene interactions, and difficult global localization. The research community does not have an indepth understanding of the climbing action due to the lack of specific datasets. To address this limitation, we collect CIMI4D, a large rock Climbing Motion dataset from 12 persons climbing 13 different climbing walls. The dataset consists of around 180,000 frames of pose inertial measurements, LiDAR point clouds, RGB videos, high-precision static point cloud scenes, and reconstructed scene meshes. Moreover, we frame-wise annotate touch rock holds to facilitate a detailed exploration of human-scene interaction. The core of this dataset is a blending optimization process, which corrects for the pose as it drifts and is affected by the magnetic conditions. To evaluate the merit of CIMI4D, we perform four tasks which include human pose estimations (with/without scene constraints), pose prediction, and pose generation. The experimental results demonstrate that CIMI4D presents great challenges to existing methods and enables extensive research opportunities. We share the dataset with the research community in http://***/cimi4d/.

关键词：