检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Niu, Ke Chen, Yuwen Yu, Haiyang Chen, Zhuofan Que, Xianghui Li, Bin Xue, Xiangyang Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University China

computer-Aided Design (CAD) plays a pivotal role in industrial manufacturing, yet 2D Parametric Primitive Analysis (PPA) remains underexplored due to two key challenges: structural constraint reasoning and advanced semantic understanding. To tackle these challenges, we first propose an Efficient Hybrid Parametrization (EHP) for better representing 2D engineering drawings. EHP contains four types of atomic component (i.e., point, line, circle, and arc). Additionally, we propose PHT-CAD, a novel 2D PPA framework that harnesses the modality alignment and reasoning capabilities of Vision-Language Models (VLMs) for precise engineering drawing analysis. In PHT-CAD, we introduce four dedicated regression heads to predict corresponding atomic components. To train PHT-CAD, a three-stage training paradigm Progressive Hierarchical Tuning (PHT) is proposed to progressively enhance PHT-CAD’s capability to perceive individual primitives, infer structural constraints, and align annotation layers with their corresponding geometric representations. Considering that existing datasets lack complete annotation layers and real-world engineering drawings, we introduce ParaCAD, the first large-scale benchmark that explicitly integrates both the geometric and annotation layers. ParaCAD comprises over 10 million annotated drawings for training and 3,000 real-world industrial drawings with complex topological structures and physical constraints for test. Extensive experiments demonstrate the effectiveness of PHT-CAD and highlight the practical significance of ParaCAD in advancing 2D PPA research. The code and adopted datasets are available at https://***/yuwen-chen616/ PHT-CAD. 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

Diabetic Retinopathy Grading with Weakly-Supervised Lesion Priors 48

Diabetic Retinopathy Grading with Weakly-Supervised Lesion P...

引用

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

作者： Hou, Junlin Xiao, Fan Xu, Jilan Feng, Rui Zhang, Yuejie Zou, Haidong Lu, Lina Xue, Wenwen Fudan University School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Shanghai China Fudan University Academy for Engineering and Technology Shanghai China Shanghai Eye Diseases Prevention & Treatment Center Shanghai China

ISBN: (纸本)9781728163277

Explicit information of lesions can provide visual instructions for diabetic retinopathy (DR) grading on fundus images. However, pixel-level lesion annotations are extremely difficult and time-consuming to acquire. In this work, we propose a novel weakly-supervised lesion-aware network for DR grading, which enhances the discriminative features with lesion priors by only image-level supervision. Specifically, we design a lesion attention module that generates lesion activation maps by introducing an auxiliary task of binary DR identification. Lesion activation maps are utilized to assist the network to focus on the most relevant regions for boosting DR grading performance. Besides, we particularly devise an adaptive joint loss to balance the DR identification and DR grading tasks dynamically. Extensive results on the public DR dataset demonstrate the superiority and generality of our proposed lesion-aware network. The interpretability of generated lesion activation maps is also verified by the comparison with ground truth segmentation masks. © 2023 IEEE.

关键词： Activation map Diabetic retinopathy grading Fundus image Lesion priors Weakly-supervised

来源：评论

学校读者我要写书评

暂无评论

Detecting compromised accounts caused by phone number recycling on e-commerce platforms: taking Meituan as an example

引用

Frontiers of information Technology & Electronic Engineering 2024年第8期25卷 1077-1095页

作者： Min GAO Shutong CHEN Yangbo GAO Zhenhua ZHANG Yu CHEN Yupeng LI Qiongzan YE Xin WANG Yang CHEN School of Computer Science Fudan UniversityShanghai 200438China Shanghai Key Lab of Intelligent Information Processing Fudan UniversityShanghai 200438China Meituan Beijing 100005China Department of Interactive Media Hong Kong Baptist UniversityHong Kong 999077China

Phone number recycling(PNR)refers to the event wherein a mobile operator collects a disconnected number and reassigns it to a new *** has posed a threat to the reliability of the existing authentication solution for e-commerce ***,a new owner of a reassigned number can access the application account with which the number is associated,and may perform fraudulent *** solutions that employ a reassigned number database from mobile operators are costly for e-commerce platforms with large-scale ***,alternative solutions that depend on only the information of the applications are *** this work,we study the problem of detecting accounts that have been compromised owing to the reassignment of phone *** analysis on Meituan's real-world dataset shows that compromised accounts have unique statistical features and temporal *** on the observations,we propose a novel model called temporal pattern and statistical feature fusion model(TSF)to tackle the problem,which integrates a temporal pattern encoder and a statistical feature encoder to capture behavioral evolutionary interaction and significant operation *** experiments on the Meituan and IEEE-CIS datasets show that TSF significantly outperforms the baselines,demonstrating its effectiveness in detecting compromised accounts due to reassigned numbers.

关键词： Phone number recycling Neural networks E-commerce Compromised account detection

来源：评论

学校读者我要写书评

暂无评论

A Multitask Learning Approach for Chinese National Instruments Recognition and Timbre Space Regression 9th

A Multitask Learning Approach for Chinese National Instrumen...

引用

9th Conference on Sound and Music Technology, CSMT 2021

作者： Xu, Shenyang Jiang, Yiliang Li, Zijin Sun, Xiaoheng Li, Wei Central Conservatory of Music Beijing100031 China School of Computer Science and Technology Fudan University Shanghai200438 China Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai200433 China

ISBN: (纸本)9789811947025

Musical instrument recognition is an essential task in the domain of music information retrieval. So far, most existing research are focused on western instruments. In this research, we turn to Chinese national instruments recognition. First, a dataset containing 30 Chinese national instruments is created. Then, a well-designed end-to-end Convolutional Recurrent Neural Network is proposed. Moreover, we combine instrument recognition with instrument timbre space regression using a multitask learning approach to improve performances of both tasks. We conduct experiments in instrument recognition and timbre space regression to evaluate our model and multitask learning approach. Experimental results show that our proposed model outperforms previous algorithms, and the multitask approach can further improve the results. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Music

来源：评论

学校读者我要写书评

暂无评论

BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation

BERTScore is Unfair: On Social Bias in Language Model-Based ...

引用

2022 Conference on Empirical Methods in Natural Language processing, EMNLP 2022

作者： Sun, Tianxiang He, Junliang Qiu, Xipeng Huang, Xuanjing School of Computer Science Fudan University China Shanghai Key Laboratory of Intelligent Information Processing Fudan University China

Automatic evaluation metrics are crucial to the development of generative systems. In recent years, pre-trained language model (PLM) based metrics, such as BERTScore (Zhang et al., 2020), have been commonly adopted in various generation tasks. However, it has been demonstrated that PLMs encode a range of stereotypical societal biases, leading to a concern on the fairness of PLMs as metrics. To that end, this work presents the first systematic study on the social bias in PLM-based metrics. We demonstrate that popular PLM-based metrics exhibit significantly higher social bias than traditional metrics on 6 sensitive attributes, namely race, gender, religion, physical appearance, age, and socioeconomic status. In-depth analysis suggests that choosing paradigms (matching, regression, or generation) of the metric has a greater impact on fairness than choosing PLMs. In addition, we develop debiasing adapters that are injected into PLM layers, mitigating bias in PLM-based metrics while retaining high performance for evaluating text generation. © 2022 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Late Prompt Tuning: A Late Prompt Could Be Better Than Many Prompts

Late Prompt Tuning: A Late Prompt Could Be Better Than Many ...

引用

2022 Findings of the Association for Computational Linguistics: EMNLP 2022

作者： Liu, Xiangyang Sun, Tianxiang Huang, Xuanjing Qiu, Xipeng School of Computer Science Fudan University China Shanghai Key Laboratory of Intelligent Information Processing Fudan University China

Prompt tuning is a parameter-efficient tuning (PETuning) method for utilizing pre-trained models (PTMs) that simply prepends a soft prompt to the input and only optimizes the prompt to adapt PTMs to downstream tasks. Although it is parameter- and deployment-efficient, its performance still lags behind other state-of-the-art PETuning methods. Besides, the training cost of prompt tuning is not significantly reduced due to the back-propagation through the entire model. Through empirical analyses, we shed some light on the lagging performance of prompt tuning and recognize a trade-off between the propagation distance from label signals to the inserted prompt and the influence of the prompt on model outputs. Further, we present Late Prompt Tuning (LPT) that inserts a late prompt into an intermediate layer of the PTM instead of the input layer or all layers. The late prompt is obtained by a neural prompt generator conditioned on the hidden states before the prompt insertion layer and therefore is instance-dependent. Through extensive experimental results across various tasks and PTMs, we show that LPT can achieve competitive performance to full model tuning and other PETuning methods under both full-data and few-shot scenarios while possessing faster training speed and lower memory cost. © 2022 Association for Computational Linguistics.

关键词： Backpropagation

来源：评论

学校读者我要写书评

暂无评论

FacialFlowNet: Advancing Facial Optical Flow Estimation with a Diverse Dataset and a Decomposed Model

arXiv

引用

arXiv 2024年

作者： Lu, Jianzhi He, Ruian Zhou, Shili Tan, Weimin Yan, Bo Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai China

Facial movements play a crucial role in conveying altitude and intentions, and facial optical flow provides a dynamic and detailed representation of it. However, the scarcity of datasets and a modern baseline hinders the progress in facial optical flow research. This paper proposes FacialFlowNet (FFN), a novel large-scale facial optical flow dataset, and the Decomposed Facial Flow Model (DecFlow), the first method capable of decomposing facial flow. FFN comprises 9,635 identities and 105,970 image pairs, offering unprecedented diversity for detailed facial and head motion analysis. DecFlow features a facial semantic-aware encoder and a decomposed flow decoder, excelling in accurately estimating and decomposing facial flow into head and expression components. Comprehensive experiments demonstrate that FFN significantly enhances the accuracy of facial flow estimation across various optical flow methods, achieving up to an 11% reduction in Endpoint Error (EPE) (from 3.91 to 3.48). Moreover, DecFlow, when coupled with FFN, outperforms existing methods in both synthetic and real-world scenarios, enhancing facial expression analysis. The decomposed expression flow achieves a substantial accuracy improvement of 18% (from 69.1% to 82.1%) in micro-expressions recognition. These contributions represent a significant advancement in facial motion analysis and optical flow estimation. Codes and datasets can be found here. Copyright © 2024, The Authors. All rights reserved.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

RankDNN: Learning to Rank for Few-Shot Learning 37

RankDNN: Learning to Rank for Few-Shot Learning

引用

37th AAAI Conference on Artificial Intelligence, AAAI 2023

作者： Guo, Qianyu Haotong, Gong Wei, Xujun Fu, Yanwei Yu, Yizhou Zhang, Wenqiang Ge, Weifeng Nebula AI Group School of Computer Science Fudan University Shanghai China Shanghai Key Laboratory of Intelligent Information Processing Shanghai China Academy for Engineering & Technology Fudan University Shanghai China Department of Computer Science The University of Hong Kong Hong Kong

ISBN: (纸本)9781577358800

This paper introduces a new few-shot learning pipeline that casts relevance ranking for image retrieval as binary ranking relation classification. In comparison to image classification, ranking relation classification is sample efficient and domain agnostic. Besides, it provides a new perspective on few-shot learning and is complementary to state-of-the-art methods. The core component of our deep neural network is a simple MLP, which takes as input an image triplet encoded as the difference between two vector-Kronecker products, and outputs a binary relevance ranking order. The proposed RankMLP can be built on top of any state-of-the-art feature extractors, and our entire deep neural network is called the ranking deep neural network, or RankDNN. Meanwhile, RankDNN can be flexibly fused with other post-processing methods. During the meta test, RankDNN ranks support images according to their similarity with the query samples, and each query sample is assigned the class label of its nearest neighbor. Experiments demonstrate that RankDNN can effectively improve the performance of its baselines based on a variety of backbones and it outperforms previous state-of-the-art algorithms on multiple few-shot learning benchmarks, including miniImageNet, tieredImageNet, Caltech-UCSD Birds, and CIFAR-FS. Furthermore, experiments on the cross-domain challenge demonstrate the superior transferability of *** code is available at: https://***/guoqianyu-alberta/RankDNN. Copyright © 2023, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Facial Micro-Motion-Aware Mixup for Micro-Expression Recognition

Facial Micro-Motion-Aware Mixup for Micro-Expression Recogni...

引用

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

作者： Zhuoyao Gu Miao Pang Zhen Xing Weimin Tan Xuhao Jiang Bo Yan School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai China

Data-driven learning models have demonstrated strong benefits in capturing subtle facial movements for micro-expression recognition (MER), but are limited by the available data. Generative models can generate a variety of new data, but are typically computationally prohibitive compared to efficient Mixup-like methods. In this paper, we propose a novel Facial Micro-Motion-Aware Mixup approach for MER, namely MEMix. Our MEMix constructs a micro-motion-aware mask to select the most salient facial motions and generate a new sample with a mixed motion feature. This mixed motion feature can effectively expand the data distribution, leading to smoother decision boundaries for MER models. To demonstrate the good generality of MEMix, we integrate it with three advanced vision transformer-based models. The results show that the three integrated models consistently achieve performance improvements ranging from 4.07% to 7.32% in accuracy and from 6.54% to 9.18% in F1-score. Besides, to further explore the ability of MEMix, we propose a two-stream network called MixMeFormer, which unlocks the potential of the transformer by simply integrating mixed motion features with facial semantics for MER. Extensive experiments demonstrate that our MixMeFormer outperforms other state-of-the-art methods on three well-known micro-expression datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GenRec: Unifying Video Generation and Recognition with Diffusion Models 38

GenRec: Unifying Video Generation and Recognition with Diffu...

引用

38th Conference on Neural information processing Systems, NeurIPS 2024

作者： Weng, Zejia Yang, Xitong Xing, Zhen Wu, Zuxuan Jiang, Yu-Gang Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University China Shanghai Collaborative Innovation Center of Intelligent Visual Computing China Department of Computer Science University of Maryland United States

Video diffusion models are able to generate high-quality videos by learning strong spatial-temporal priors on large-scale datasets. In this paper, we aim to investigate whether such priors derived from a generative process are suitable for video recognition, and eventually joint optimization of generation and recognition. Building upon Stable Video Diffusion, we introduce GenRec, the first unified framework trained with a random-frame conditioning process so as to learn generalized spatial-temporal representations. The resulting framework can naturally supports generation and recognition, and more importantly is robust even when visual inputs contain limited information. Extensive experiments demonstrate the efficacy of GenRec for both recognition and generation. In particular, GenRec achieves competitive recognition performance, offering 75.8% and 87.2% accuracy on SSV2 and K400, respectively. GenRec also performs the best on class-conditioned image-to-video generation, achieving 46.5 and 49.3 FVD scores on SSV2 and EK-100 datasets. Furthermore, GenRec demonstrates extraordinary robustness in scenarios that only limited frames can be observed. Code will be available at https://***/wengzejia1/GenRec. © 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

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：