检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Sun, Yuqi He, Ruian Tan, Weimin Yan, Bo School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University Shanghai China

Recent neural talking radiance field methods have shown great success in photorealistic audio-driven talking face synthesis. In this paper, we propose the first novel interactive framework that utilizes human instructions to edit talking radiance fields to achieve personalized talking face generation. Given a short speech video, we first build an efficient talking radiance field and then apply the latest conditional diffusion model to edit images with human instructions during the optimization. To ensure audio-lip synchronization during the editing process, we propose a progressive dataset updating strategy to ensure successful editing while preventing distortion of lip shapes. We also introduce a lightweight refinement network for complementing image details and achieving controllable detail generation in the final rendered image. Our method enables real-time rendering at up to 30FPS on consumer hardware. Multiple metrics and user verification show that our approach significantly improves rendering quality compared to state-of-the-art methods. © 2023, CC BY-NC-ND.

关键词： Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

Exploring Query Efficient Data Generation Towards Data-Free Model Stealing in Hard Label Setting 39

Exploring Query Efficient Data Generation Towards Data-Free ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Pei, Gaozheng Lyu, Shaojie Ma, Ke Yang, Pinci Xu, Qianqian Sun, Yingfei School of Electronic Electrical and Communication Engineering UCAS Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China Tencent Corporate China

ISBN: (纸本)157735897X

Data-free model stealing involves replicating the functionality of a target model into a substitute model without accessing the target model’s structure, parameters, or training data. The adversary can only access the target model’s predictions for generated samples. Once the substitute model closely approximates the behavior of the target model, attackers can exploit its white-box characteristics for subsequent malicious activities, such as adversarial attacks. Existing methods within cooperative game frameworks often produce samples with high confidence for the prediction of the substitute model, which makes it difficult for the substitute model to replicate the behavior of the target model. This paper presents a new data-free model stealing approach called Query Efficient Data Generation (QEDG). We introduce two distinct loss functions to ensure the generation of sufficient samples that closely and uniformly align with the target model’s decision boundary across multiple classes. Building on the limitation of current methods, which typically yield only one piece of supervised information per query, we propose the query-free sample augmentation that enables the acquisition of additional supervised information without increasing the number of queries. Motivated by theoretical analysis, we adopt the consistency rate metric, which more accurately evaluates the similarity between the substitute and target models. We conducted extensive experiments to verify the effectiveness of our proposed method, which achieved better performance with fewer queries compared to the state-of-the-art methods on the real MLaaS scenario and five datasets. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Multi-level Approach to Learning Early Warning based on Cognitive Diagnosis and Learning Behaviors Analysis 26

A Multi-level Approach to Learning Early Warning based on Co...

引用

26th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2023

作者： Ma, Hua Zhao, Wen Jiang, Zixu Huang, Peiji Tang, Wensheng Zhang, Hongyu Hunan Normal University Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Changsha China Hunan Normal University College of Information Science and Engineering Changsha China Co. Ltd China Central South University School of Business Changsha China

ISBN: (纸本)9798350331684

Learning early warning is of great significance for coping with students' learning risks. The existing research fails in modeling the fluctuation of students' learning states and providing the multi-level early warning for students at different levels. To address them, a new approach of learning early warning is proposed to predict at-risk students in e-learning environment by combining cognitive diagnosis with learning behaviors analysis. In this approach, the students' learning process is modeled from four dimensions, i.e., learning quality, learning engagement, latent learning state, and historical learning performance. The convolutional neural network and long short-term memory network are used to explore the students' latent learning features. Then, the Adaboost algorithm is applied to predict students' learning performance. Based on the predicted performance, the evaluation rules are designed to provide multi-level learning early warning for students. Finally, the experiments demonstrate that the proposed method could predict at-risk students efficiently and accurately. © 2023 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Fine-Grained Blind Face Inpainting with 3D Face Component Disentanglement

Fine-Grained Blind Face Inpainting with 3D Face Component Di...

引用

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

作者： Yu Bai Ruian He Weimin Tan Bo Yan Yangle Lin School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University Shanghai China

Inpainting is a task to restore occlusion or other corruption on images. However, previous works require mask of the occluded area to restore the occluded image, which is inconvenient for application. Blind face inpainting aims to automatically restore the occluded face without position information of the corrupt region. In this paper, we propose a novel fine-grained blind face inpainting framework, combining 3D face components disentanglement with generative network. Canonical face texture and shape disentangled by unsupervised 3D face model is restored separately to get occlusion-free rendered result. Finally, the pixel-to-pixel generative module utilize the occlusion image and the coarse de-occlusion face to get refined inpainted result. We also build up a new dataset called CelebO-3D which consists of occluded face images synthesized with 3D occlusion and rendered by 3D face model. Extensive experiments show that the proposed method is effective and robust in face blind inpainting both in synthesized and real images. Extensive evaluations and comparison with previous methods also show our superior effectiveness and lightweight architecture.

关键词： Solid modeling Three-dimensional displays Shape Speech enhancement signal processing Acoustics Image restoration

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-Guided Spatial Pruning Architecture for Efficient Frame Interpolation

arXiv

引用

arXiv 2023年

作者： Cheng, Ri Jiang, Xuhao He, Ruian Zhou, Shili Tan, Weimin Yan, Bo School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University Shanghai China

The video frame interpolation (VFI) model applies the convolution operation to all locations, leading to redundant computations in regions with easy motion. We can use dynamic spatial pruning method to skip redundant computation, but this method cannot properly identify easy regions in VFI tasks without supervision. In this paper, we develop an Uncertainty-Guided Spatial Pruning (UGSP) architecture to skip redundant computation for efficient frame interpolation dynamically. Specifically, pixels with low uncertainty indicate easy regions, where the calculation can be reduced without bringing undesirable visual results. Therefore, we utilize uncertainty-generated mask labels to guide our UGSP in properly locating the easy region. Furthermore, we propose a self-contrast training strategy that leverages an auxiliary non-pruning branch to improve the performance of our UGSP. Extensive experiments show that UGSP maintains performance but reduces FLOPs by 34%/52%/30% compared to baseline without pruning on Vimeo90K/UCF101/MiddleBury datasets. In addition, our method achieves state-of-the-art performance with lower FLOPs on multiple benchmarks. Copyright © 2023, 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

MVFlow: Deep Optical Flow Estimation of Compressed Videos with Motion Vector Prior

arXiv

引用

arXiv 2023年

作者： Zhou, Shili Jiang, Xuhao Tan, Weimin He, Ruian Yan, Bo School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University Shanghai China

In recent years, many deep learning-based methods have been proposed to tackle the problem of optical flow estimation and achieved promising results. However, they hardly consider that most videos are compressed and thus ignore the pre-computed information in compressed video streams. Motion vectors, one of the compression information, record the motion of the video frames. They can be directly extracted from the compression code stream without computational cost and serve as a solid prior for optical flow estimation. Therefore, we propose an optical flow model, MVFlow, which uses motion vectors to improve the speed and accuracy of optical flow estimation for compressed videos. In detail, MVFlow includes a key Motion-Vector Converting Module, which ensures that the motion vectors can be transformed into the same domain of optical flow and then be utilized fully by the flow estimation module. Meanwhile, we construct four optical flow datasets for compressed videos containing frames and motion vectors in pairs. The experimental results demonstrate the superiority of our proposed MVFlow, which can reduce the AEPE by 1.09 compared to existing models or save 52% time to achieve similar accuracy to existing models. Copyright © 2023, 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

Broadband High Gain Composite VHF Monopole Antenna Design

Broadband High Gain Composite VHF Monopole Antenna Design

引用

IEEE International Conference on Electronic Information and Communication Technology (ICEICT)

作者： Lihua Wang Baofeng Cao Peng Li Zongxiang Li Yingsong Li College of Information and Communication Engineering Harbin Engineering University Harbin China State Key Laboratory of Nuclear and Biochemical Calamity Protection for Civilian Beijing China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei China

A novel wideband miniaturized composite monopole antenna is proposed, analysed and investigated in detail, where the antenna consists of a conical monopole structure with a loaded capacitive disc. The antenna is composed of multiple nested section, aiming to reduce the profile of the antenna. The loading disc at its top is equivalent to a capacitive structure to improve the antenna matching and the stability of the pattern. According to the simulation results, the impedance bandwidth $(\mathbf{S}_{\mathbf{11}} < -\mathbf{10})$ is 132.9% $(\mathbf{60.45}\sim \mathbf{300}\ \mathbf{MHz})$ , or even wider. The gain at the entire frequency averages 3 dBi. The performance of the antenna is very suitable for remote wireless communication.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ReconBoost: Boosting Can Achieve Modality Reconcilement 41

ReconBoost: Boosting Can Achieve Modality Reconcilement

引用

41st International Conference on Machine Learning, ICML 2024

作者： Hua, Cong Xu, Qianqian Bao, Shilong Yang, Zhiyong Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores a novel multi-modal alternating learning paradigm pursuing a reconciliation between the exploitation of uni-modal features and the exploration of cross-modal interactions. This is motivated by the fact that current paradigms of multi-modal learning tend to explore multi-modal features simultaneously. The resulting gradient prohibits further exploitation of the features in the weak modality, leading to modality competition, where the dominant modality overpowers the learning process. To address this issue, we study the modality-alternating learning paradigm to achieve reconcilement. Specifically, we propose a new method called ReconBoost to update a fixed modality each time. Herein, the learning objective is dynamically adjusted with a reconcilement regularization against competition with the historical models. By choosing a KL-based reconcilement, we show that the proposed method resembles Friedman's Gradient-Boosting (GB) algorithm, where the updated learner can correct errors made by others and help enhance the overall performance. The major difference with the classic GB is that we only preserve the newest model for each modality to avoid overfitting caused by ensembling strong learners. Furthermore, we propose a memory consolidation scheme and a global rectification scheme to make this strategy more effective. Experiments over six multi-modal benchmarks speak to the efficacy of the method. We release the code at https://***/huacong/ReconBoost. Copyright 2024 by the author(s)

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Optimized Gradient Clipping for Noisy Label Learning 39

Optimized Gradient Clipping for Noisy Label Learning

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Ye, Xichen Wu, Yifan Zhang, Weizhong Li, Xiaoqiang Chen, Yifan Jin, Cheng Shanghai University China Fudan University China Hong Kong Baptist University Hong Kong Shanghai Key Laboratory of Intelligent Information Processing China Shanghai Collaborative Innovation Center of Intelligent Visual Computing China

ISBN: (纸本)157735897X

Previous research has shown that constraining the gradient of loss function w.r.t. model-predicted probabilities can enhance the model robustness against noisy labels. These methods typically specify a fixed optimal threshold for gradient clipping through validation data to obtain the desired robustness against noise. However, this common practice overlooks the dynamic distribution of gradients from both clean and noisy-labeled samples at different stages of training, significantly limiting the model capability to adapt to the variable nature of gradients throughout the training process. To address this issue, we propose a simple yet effective approach called Optimized Gradient Clipping (OGC), which dynamically adjusts the clipping threshold based on the ratio of noise gradients to clean gradients after clipping, estimated by modeling the distributions of clean and noisy samples. This approach allows us to modify the clipping threshold at each training step, effectively controlling the influence of noise gradients. Additionally, we provide statistical analysis to certify the noise-tolerance ability of OGC. Our extensive experiments across various types of label noise, including symmetric, asymmetric, instance-dependent, and real-world noise, demonstrate the effectiveness of our approach. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EDA: Enhanced Domain-Adversarial Training for Anatomical Landmark Detection 22

EDA: Enhanced Domain-Adversarial Training for Anatomical Lan...

引用

22nd IEEE International Symposium on Biomedical Imaging, ISBI 2025

作者： Yang, Fan Zhou, S. Kevin School of Biomedical Engineering Division of Life Sciences and Medicine University of Science and Technology of China Anhui Hefei 230026 China Center for Medical Imaging Robotics Analytic Computing & Learning (MIRACLE) Suzhou Institute for Advanced Research University of Science and Technology of China Jiangsu Suzhou 215123 China Key Laboratory of Precision and Intelligent Chemistry Ustc Anhui Hefei 230026 China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology Cas Beijing 100190 China

ISBN: (纸本)9798331520526

Manually annotating anatomical landmarks in medical images requires experienced clinicians and is a labor-intensive process. However, recent AI-assisted methods for landmark detection often rely on the training and test data originating from the same domain. This work introduces a novel unsupervised domain adaptation (UDA) framework aimed at anatomical landmark detection from a medical image, designed to bridge the gap between a source domain with labels and an unlabeled target domain. Specifically, we have developed a new Domain-Adversarial Network that incorporates skip connections to transfer and fuse high-resolution feature maps. Additionally, we proposed Dynamic Gaussian Learning, which allows the model to escape from local error regions. We carry out experiments on landmark detection for both head and chest, and the results demonstrate that our method achieves state-of-the-art performances in each experiment. © 2025 IEEE.

关键词： Anatomical Landmark Detection Unsupervised Domain Adaptation

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：