检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Yu, Tianshu Xia, Changqun Li, Jia State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China Peng Cheng Laboratory Shenzhen518055 China

Video portrait segmentation (VPS), aiming at segmenting prominent foreground portraits from video frames, has received much attention in recent years. However, simplicity of existing VPS datasets leads to a limitation on extensive research of the task. In this work, we propose a new intricate large-scale Multi-scene Video Portrait Segmentation dataset MVPS consisting of 101 video clips in 7 scenario categories, in which 10,843 sampled frames are finely annotated at pixel level. The dataset has diverse scenes and complicated background environments, which is the most complex dataset in VPS to our best knowledge. Through the observation of a large number of videos with portraits during dataset construction, we find that due to the joint structure of human body, motion of portraits is part-associated, which leads that different parts are relatively independent in motion. That is, motion of different parts of the portraits is imbalanced. Towards this imbalance, an intuitive and reasonable idea is that different motion states in portraits can be better exploited by decoupling the portraits into parts. To achieve this, we propose a Part-Decoupling Network (PDNet) for video portrait segmentation. Specifically, an Inter-frame Part-Discriminated Attention (IPDA) module is proposed which unsupervisedly segments portrait into parts and utilizes different attentiveness on discriminative features specified to each different part. In this way, appropriate attention can be imposed to portrait parts with imbalanced motion to extract part-discriminated correlations, so that the portraits can be segmented more accurately. Experimental results demonstrate that our method achieves leading performance with the comparison to state-of-the-art methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

3D Face Reconstruction With Geometry Details From a Single Color Image Under Occluded Scenes

arXiv

引用

arXiv 2024年

作者： Zhao, Dapeng Qi, Yue State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Peng Cheng Laboratory Shenzhen China Qingdao Research Institute of Beihang University Qingdao China

3D face reconstruction technology aims to generate a face stereo model naturally and realistically. Previous deep face reconstruction approaches are typically designed to generate convincing textures and cannot generalize well to multiple occluded scenarios simultaneously. By introducing bump mapping, we successfully added mid-level details to coarse 3D faces. More innovatively, our method takes into account occlusion scenarios. Thus on top of common 3D face reconstruction approaches, we in this paper propose a unified framework to handle multiple types of obstruction simultaneously (e.g., hair, palms and glasses et al.).Extensive experiments and comparisons demonstrate that our method can generate high-quality reconstruction results with geometry details from captured facial images under occluded scenes. Copyright © 2024, The Authors. All rights reserved.

关键词： 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

WildPose: HRNet-based Lightweight and Efficient Wildlife Pose Estimation

WildPose: HRNet-based Lightweight and Efficient Wildlife Pos...

引用

Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)

作者： Sibusiso Reuben Bakana Yongfei Zhang Bhekisipho Twala School of Computer Science and Engineering Beihang University Beijing China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Faculty of Information and Communication Technology Tshwane University of Technology Tshwane South Africa

ISBN: (数字)9798350367331

ISBN: (纸本)9798350367348

Lightweight and efficient wildlife monitoring algorithms, including pose estimation, that can operate on edge devices with limited computational resources are urgently needed for wildlife studies and protections. To reduce computational costs while maintaining accuracy in animal pose estimation, this paper introduces WildPose, an HRNet-w32 based model, designed, which integrates Efficient Channel Attention (ECA) to enhance important feature representations without complex operations, Non-Local Blocks (NLB) to capture long-range contextual information and handle occlusions, and Depthwise Convolutions (DWConv) to reduce computational complexity and parameters. Additionally, the Online Hard keypoint Mining with Mean Squared Error (OHKMSE) loss function is employed to improve accuracy for occluded keypoints detection by focusing on harder keypoints. When evaluated on the largest wildlife dataset of Animal Kingdom, WildPose demonstrated a nice trade-off between accuracy and efficiency, 75% reduction in parameters and 65% reduction in GFLOPs, while achieving an increased Percentage of Correct keypoints (PCK) for occluded keypoints such as the hip, ankle, and tail. Therefore, WildPose can serve as a practical solution for real-time wildlife monitoring and artificial intelligence-based ecological studies, especially in resource-constrained environments.

关键词： Accuracy Biological system modeling Computational modeling Wildlife Pose estimation Tail Real-time systems Computational efficiency Monitoring Hip

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Survey of Action Quality Assessment: Method and Benchmark

arXiv

引用

arXiv 2024年

作者： Zhou, Kanglei Cai, Ruizhi Wang, Liyuan Shum, Hubert P.H. Liang, Xiaohui State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China The Department of Computer Science and Technology Institute for AI BNRist Center THBI Lab Tsinghua-Bosch Joint Center for ML Tsinghua University Beijing100190 China The Department of Computer Science Durham University DurhamDH1 3LE United Kingdom The State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Zhongguancun Laboratory Beijing China

Action Quality Assessment (AQA) quantitatively evaluates the quality of human actions, providing automated assessments that reduce biases in human judgment. Its applications span domains such as sports analysis, skill assessment, and medical care. Recent advances in AQA have introduced innovative methodologies, but similar methods often intertwine across different domains, highlighting the fragmented nature that hinders systematic reviews. In addition, the lack of a unified benchmark and limited computational comparisons hinder consistent evaluation and fair assessment of AQA approaches. In this work, we address these gaps by systematically analyzing over 150 AQA-related papers to develop a hierarchical taxonomy, construct a unified benchmark, and provide an in-depth analysis of current trends, challenges, and future directions. Our hierarchical taxonomy categorizes AQA methods based on input modalities (video, skeleton, multi-modal) and their specific characteristics, highlighting the evolution and interrelations across various approaches. To promote standardization, we present a unified benchmark, integrating diverse datasets to evaluate the assessment precision and computational efficiency. Finally, we review emerging task-specific applications and identify under-explored challenges in AQA, providing actionable insights into future research directions. This survey aims to deepen understanding of AQA progress, facilitate method comparison, and guide future innovations. The project web page can be found at https://***/AQA-Survey. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A homogenization method for nonlinear inhomogeneous elastic materials

引用

virtual Reality & Intelligent Hardware 2021年第2期3卷 156-170页

作者： Jing ZHAO Fei ZHU Liyou XU Yong TANG Sheng LI College of Information Science and Engineering Yanshan UniversityQinhuangdaoHebei 066004China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province QinhuangdaoHebei 066004China School of Electronics Engineering and Computer Science Peking UniversityBeijing 100871China Beijing Engineering Research Center for Virtual Simulation and Visualization Beijing 100871China

Background Fast simulation techniques are strongly favored in computer graphics,especially for the nonlinear inhomogeneous elastic *** homogenization theory is a perfect match to simulate inhomogeneous deformable objects with its coarse discretization,as it reveals how to extract information at a fine scale and to perform efficient computation with much less *** existing homogenization method is not applicable for ubiquitous nonlinear materials with the limited input deformation *** In this paper,we have proposed a homogenization method for the efficient simulation of nonlinear inhomogeneous elastic *** approach allows for a faithful approximation of fine,heterogeneous nonlinear materials with very coarse *** analysis provides the basis of a linear deformation space and modal derivatives extend the space to a nonlinear regime;based on this,we exploited modal derivatives as the input characteristic deformations for *** also present a simple elastic material model that is nonlinear and anisotropic to represent the homogenized *** nonlinearity of material deformations can be represented properly with this *** material properties for the coarsened model were solved via a constrained optimization that minimizes the weighted sum of the strain energy deviations for all input deformation *** arbitrary number of bases can be used as inputs for homogenization,and greater weights are placed on the more important low-frequency *** Based on the experimental results,this study illustrates that the homogenized material properties obtained from our method approximate the original nonlinear material behavior much better than the existing homogenization method with linear displacements,and saves orders of magnitude of computational *** The proposed homogenization method for nonlinear inhomogeneous elastic materials is capable of capturing the nonlinear dynamics of the

关键词： Physical-based simulation Homogenization theory Heterogeneous material Modal basis

来源：评论

学校读者我要写书评

暂无评论

SCARF: Scalable Continual Learning Framework for Memory-efficient Multiple Neural Radiance Fields

arXiv

引用

arXiv 2024年

作者： Wang, Yuze Wang, Junyi Wang, Chen Duan, Wantong Bao, Yongtang Qi, Yue State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University China School of Computer Science and Technology Shandong University China School of Computer and Artificial Intelligence Beijing Technology and Business University China Jingdezhen Research Institute Beihang University China Shandong University of Science and Technology China

This paper introduces a novel continual learning framework for synthesising novel views of multiple scenes, learning multiple 3D scenes incrementally, and updating the network parameters only with the training data of the upcoming new scene. We build on Neural Radiance Fields (NeRF), which uses multi-layer perceptron to model the density and radiance field of a scene as the implicit function. While NeRF and its extensions have shown a powerful capability of rendering photo-realistic novel views in a single 3D scene, managing these growing 3D NeRF assets efficiently is a new scientific problem. Very few works focus on the efficient representation or continuous learning capability of multiple scenes, which is crucial for the practical applications of NeRF. To achieve these goals, our key idea is to represent multiple scenes as the linear combination of a cross-scene weight matrix and a set of scene-specific weight matrices generated from a global parameter generator. Furthermore, we propose an uncertain surface knowledge distillation strategy to transfer the radiance field knowledge of previous scenes to the new model. Representing multiple 3D scenes with such weight matrices significantly reduces memory requirements. At the same time, the uncertain surface distillation strategy greatly overcomes the catastrophic forgetting problem and maintains the photo-realistic rendering quality of previous scenes. Experiments show that the proposed approach achieves state-of-the-art rendering quality of continual learning NeRF on NeRF-Synthetic, LLFF, and TanksAndTemples datasets while preserving extra low storage cost. Copyright © 2024, The Authors. All rights reserved.

关键词： Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

Fault Localization for Novice Programs Combining Static Analysis and Dynamic Detection

Fault Localization for Novice Programs Combining Static Anal...

引用

IEEE Annual International computer Software and Applications Conference (COMPSAC)

作者： Han Wan Wenhao Nie Shiyang Yue Xiaoyan Luo State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Image processing Center School of Astronautics Beihang University Beijing China

ISBN: (数字)9798350376968

ISBN: (纸本)9798350376975

In programming teaching, teachers or teaching assistants often need to spend a lot of energy helping students solve the problems they face when doing programming. It will be helpful to provide students with valuable programming feedback, such as information on faulty lines. However, most existing algorithms do not perform well on novice programs. Therefore, considering the background in programming teaching, we proposed a novel approach combining static analysis with dynamic detection by using the correct programs submitted by previous students and coverage information for the incorrect program. In particular, the core of the static analysis module is to locate specific faulty lines through syntax tree difference comparison, which includes matching similar programs, variable mapping and replacement, and fault localization based on abstract syntax tree differences. The core of the module on dynamic detection is to perform traditional Spectrum-based Fault Localization. To evaluate the effectiveness of our proposed approach, we conducted some empirical studies on 223 student-failure programs in the real world. The experimental results indicate that our approach outperforms other baselines regarding TOP-l and TOP-3. Furthermore, we analyzed the performance of our method on different categories of programming problems as well as the effectiveness of the combination of static analysis and dynamic detection.

关键词： Location awareness Heuristic algorithms Education Static analysis Syntactics Software Performance analysis

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

Pixel-Level Domain Adaptation: A New Perspective for Enhancing Weakly Supervised Semantic Segmentation

arXiv

引用

arXiv 2024年

作者： Du, Ye Fu, Zehua Liu, Qingjie The State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China The Hangzhou Innovation Institute Beihang University Hangzhou310051 China

Recent attention has been devoted to the pursuit of learning semantic segmentation models exclusively from image tags, a paradigm known as image-level Weakly Supervised Semantic Segmentation (WSSS). Existing attempts adopt the Class Activation Maps (CAMs) as priors to mine object regions yet observe the imbalanced activation issue, where only the most discriminative object parts are located. In this paper, we argue that the distribution discrepancy between the discriminative and the non-discriminative parts of objects prevents the model from producing complete and precise pseudo masks as ground truths. For this purpose, we propose a Pixel-Level Domain Adaptation (PLDA) method to encourage the model in learning pixel-wise domain-invariant features. Specifically, a multi-head domain classifier trained adversarially with the feature extraction is introduced to promote the emergence of pixel features that are invariant with respect to the shift between the source (i.e., the discriminative object parts) and the target (i.e., the non-discriminative object parts) domains. In addition, we come up with a Confident Pseudo-Supervision strategy to guarantee the discriminative ability of each pixel for the segmentation task, which serves as a complement to the intra-image domain adversarial training. Our method is conceptually simple, intuitive and can be easily integrated into existing WSSS methods. Taking several strong baseline models as instances, we experimentally demonstrate the effectiveness of our approach under a wide range of settings. © 2024, CC BY.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

G-MAP: General Memory-Augmented Pre-trained Language Model for Domain Tasks

G-MAP: General Memory-Augmented Pre-trained Language Model f...

引用

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

作者： Wan, Zhongwei Yin, Yichun Zhang, Wei Shi, Jiaxin Shang, Lifeng Chen, Guangyong Jiang, Xin Liu, Qun Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Science China University of Chinese Academy of Sciences China Huawei Noah's Ark Lab Huawei Cloud Computing Zhejiang Lab China

Recently, domain-specific PLMs have been proposed to boost the task performance of specific domains (e.g., biomedical and computer science) by continuing to pre-train general PLMs with domain-specific corpora. However, this Domain-Adaptive Pre-Training (DAPT;Gururangan et al. (2020)) tends to forget the previous general knowledge acquired by general PLMs, which leads to a catastrophic forgetting phenomenon and sub-optimal performance. To alleviate this problem, we propose a new framework of General Memory-Augmented Pre-trained Language Model (G-MAP), which augments the domain-specific PLM by a memory representation built from the frozen general PLM without losing any general knowledge. Specifically, we propose a new memory-augmented layer, and based on it, different augmented strategies are explored to build the memory representation and then adaptively fuse it into the domain-specific PLM. We demonstrate the effectiveness of G-MAP on various domains (biomedical and computer science publications, news, and reviews) and different kinds (text classification, QA, NER) of tasks, and the extensive results show that the proposed G-MAP can achieve SOTA results on all tasks. © 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

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：