检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Liang, Baoyu Su, Qile Zhu, Shoutai Liang, Yuchen Tong, Chao School of Computer Science and Engineering Beihang University China State Key Laboratory of Virtual Reality Technology and Systems Beihang University China

ISBN: (纸本)157735897X

Despite the significant impact of visual events on human cognition, understanding events in videos remains a challenging task for AI due to their complex structures, semantic hierarchies, and dynamic evolution. To address this, we propose the task of video event understanding that extracts event scripts and makes predictions with these scripts from videos. To support this task, we introduce VidEvent, a large-scale dataset containing over 23,000 well-labeled events, featuring detailed event structures, broad hierarchies, and logical relations extracted from movie recap videos. The dataset was created through a meticulous annotation process, ensuring high-quality and reliable event data. We also provide comprehensive baseline models offering detailed descriptions of their architecture and performance metrics. These models serve as benchmarks for future research, facilitating comparisons and improvements. Our analysis of VidEvent and the baseline models highlights the dataset’s potential to advance video event understanding and encourages the exploration of innovative algorithms and models. © 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 Doctors Behavior Aware and Domain Knowledge Driven Model for Medical Report Generation

A Doctors Behavior Aware and Domain Knowledge Driven Model f...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Wang, Han Niu, Jianwei Liu, Xuefeng Wang, Yong Beihang University School of Computer Science Beijing China State Key Laboratory of Virtual Reality Technology and Systems Beijing China Zhongguancun Laboratory Beijing China Peking Union Medical College Chinese Academy of Medical Sciences Beijing China

ISBN: (纸本)9798350337488

When doctors write a medical report, they first focus on key regions in the image, which usually contain abnormal information. Then, they write the report based on their experience and professional knowledge. Some existing medical report generation methods design corresponding schemes to model this process, but they still have some drawbacks. Some of them adopt the attention map to model the doctors' image-reading behavior, which requires additional cropping and feature extraction operations, bringing many extra computations. Other methods manually construct knowledge graphs to model the doctors' domain knowledge, which requires manual construction for different disease domains and has less generalization. Therefore, We propose DEKG, a doctors behavior aware and domain knowledge driven model, to improve the quality of generated reports by modeling the fixed pattern of doctors when writing reports. Specifically, feature clustering is utilized to model the doctors' image-reading behavior that only brings fewer computations, and then we capture key regions with possible abnormalities. We also design a method to automatically construct domain knowledge graphs, which can quickly accomplish the construction process for different disease domains without human intervention. Extensive experiments on datasets from different disease domains demonstrate that DEKG achieves competitive results with state-of-the-art methods and can generate high-quality reports. © 2023 IEEE.

关键词： Feature Clustering Knowledge Graph Medical Report Generation Transformer

来源：评论

学校读者我要写书评

暂无评论

Exploring Regional Clues in CLIP for Zero-Shot Semantic Segmentation

Exploring Regional Clues in CLIP for Zero-Shot Semantic Segm...

引用

Conference on computer vision and Pattern Recognition (CVPR)

作者： Yi Zhang Meng-Hao Guo Miao Wang Shi-Min Hu State Key Laboratory of Virtual Reality Technology and Systems SCSE Beihang University Department of Computer Science and Technology BNRist Tsinghua University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

CLIP has demonstrated marked progress in visual recognition due to its powerful pre-training on large-scale image-text pairs. However, it still remains a critical challenge: how to transfer image-level knowledge into pixel-level understanding tasks such as semantic segmentation. In this paper, to solve the mentioned challenge, we analyze the gap between the capability of the CLIP model and the requirement of the zero-shot semantic segmentation task. Based on our analysis and observations, we propose a novel method for zero-shot semantic segmentation, dubbed CLIP-RC (CLIP with Regional Clues), bringing two main insights. On the one hand, a region-level bridge is necessary to provide fine-grained semantics. On the other hand, over-fitting should be mitigated during the training stage. Benefiting from the above discoveries, CLIP-RC achieves state-of-the-art performance on various zero-shot semantic segmentation benchmarks, including PASCAL VOC, PASCAL Context, and COCO-Stuff 164K. Code will be available at https://***/Jittor/JSeg.

关键词： Training Bridges Visualization computer vision Image recognition Codes Semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

SSCCPC-Net: Simultaneously Learning 2D and 3D Features with CLIP for Semantic Scene Completion on Point Cloud 1

引用

41st computer Graphics International Conference, CGI 2024

作者： Duan, Wantong Bao, Yongtang Qi, Yue State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China Shandong University of Science and Technology Qingdao266590 China Jingdezhen Research Institute of Beihang University Jingdezhen333000 China Qingdao Research Institute of Beihang University Qingdao266000 China

ISBN: (数字)9783031820243

ISBN: (纸本)9783031820236

Compare to traditional Scene Completion (SC), Semantic Scene Completion (SSC) is a challenging task that aims to generate complete and semantically consistent 3D scene from partial and sparse input data, which is fundamental to fully understanding the scene and being able to interact with it. Consequently, the SSC task has received much attention in recent years. Most of the methods are voxel-based approaches, but they have high computational and memory requirements. A few works based on point cloud do not sufficiently exploit the correlation between semantic segmentation and geometric completion subtasks, while focusing too much on point cloud shape features and ignoring the rich texture information that RGB images can provide. In this paper, we present SSCCPC-Net (Semantic Scene Completion with CLIP on Point Cloud-Net), a novel network architecture for point cloud semantic scene completion using a combination of 2D and 3D features. Inspired by recent works of large pretrained vision-language models in semantic segmentation, we explore to accomplish SSC task with the help of Contrastive Language-Image Pre-Training (CLIP) model. Specifically, we use the CLIP features for guidance to fuse the 2D features extracted from the RGB image and the 3D features extracted from the point cloud. The fused features are then fed into our designed Semantic-Completion Decoder for per-point semantic prediction and semantic labeling-assisted point cloud completion. Finally, we obtain the complete semantically point cloud. Numerous experiments have demonstrated that our method has higher effectiveness and generalizability compared to state-of-the-art methods. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Super-resolution of Solar Magnetograms Using Deep Learning

引用

Research in Astronomy and Astrophysics 2022年第8期22卷 218-229页

作者： Fengping Dou Long Xu Zhixiang Ren Dong Zhao Xinze Zhang State Key Laboratory of Space Weather National Space Science CenterChinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China Peng Cheng National Laboratory Shenzhen 518000China State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100191China

Currently,data-driven models of solar activity forecast are investigated extensively by using machine *** model training,it is highly demanded to establish a large database which may contain observations coming from different instruments with different spatio-temporal *** this paper,we employ deep learning models for super-resolution(SR)of magnetogram of Michelson Doppler Imager(MDI)in order to achieve the same spatial resolution of Helioseismic and Magnetic Imager(HMI).First,a generative adversarial network(GAN)is designed to transfer characteristics of MDI onto downscaled HMI,getting low-resolution HMI magnetogram in the same domain as ***,with the paired low-resolution and high-resolution HMI magnetograms,another GAN is trained in a supervised learning way,which consists of two streams,one is for generating high-fidelity image content,the other is explicitly optimized for generating elaborate image ***,these two streams work together to guarantee both high-fidelity and photorealistic super-resolved *** results demonstrate that the proposed method can generate super-resolved magnetograms with perceptual-pleasant visual ***,the best PSNR,LPIPS,RMSE,comparable SSIM and CC are obtained by the proposed *** source code and data set can be accessed via https://***/filterbank/SPSR.

关键词： techniques:image processing Sun:magnetic fields Sun:atmosphere

来源：评论

学校读者我要写书评

暂无评论

PMM: A Smart Shopping Guider Based on Mobile AR 23

PMM: A Smart Shopping Guider Based on Mobile AR

引用

16th International Symposium on Visual Information Communication and Interaction, VINCI 2023

作者： Han, Jiahao Ding, Zhifei Chen, Yuxuan Yu, Lingxin Chen, Siru Liu, Richen School of Computer and Electronic Information/School of Artificial Intelligence Nanjing Normal University China School of Computer and Electronic Information/School of Artificial Intelligence Nanjing Normal University China and State Key Laboratory of Virtual Reality Technology and Systems Beihang University China

ISBN: (纸本)9798400707513

Augmented reality (AR) is a burgeoning interaction technology with the ability to provide users with immersive everyday experiences. Shopping is among the most common experiences. When consumers purchase products, they often encounter difficulties in obtaining detailed information relevant to their interests, such as ingredients, origin, and product comparisons, leading to frustration. This situation can be undeniably frustrating. We can use visualization technology [18] to organize it more orderly and friendly. This paper proposes a mobile augmented reality-based application framework, Product Magic Mirror (PMM), which helps to integrate basic visualization design into the application. The augmented information can be rich, e.g. they can be some visualizations and vivid data videos. In the evaluation, we simulated a goods purchase scene, and applied information to the real world by using AR. The real environment and virtual objects were superimposed on the same screen in real time, so as to achieve an experience beyond reality [24]. In our user survey, users rated our tools as a way to make better shopping choices, giving them a positive score for an immersive shopping experience. We predict that displaying information such as instructions, ingredients, and/or user review information next to products could allow consumers to make better consumption choices while reducing decision time and making shopping more immersive. © 2023 ACM.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Transforming vision Transformer: Towards Efficient Multi-Task Asynchronous Learning

arXiv

引用

arXiv 2025年

作者： Zhong, Hanwen Chen, Jiaxin Zhang, Yutong Huang, Di Wang, Yunhong State Key Laboratory of Virtual Reality Technology and Systems Beihang University China School of Computer Science and Engineering Beihang University Beijing China

Multi-Task Learning (MTL) for vision Transformer aims at enhancing the model capability by tackling multiple tasks simultaneously. Most recent works have predominantly focused on designing Mixture-of-Experts (MoE) structures and integrating Low-Rank Adaptation (LoRA) to efficiently perform multi-task learning. However, their rigid combination hampers both the optimization of MoE and the effectiveness of reparameterization of LoRA, leading to sub-optimal performance and low inference speed. In this work, we propose a novel approach dubbed Efficient Multi-Task Learning (EMTAL) by transforming a pre-trained vision Transformer into an efficient multi-task learner during training, and reparameterizing the learned structure for efficient inference. Specifically, we firstly develop the MoEfied LoRA structure, which decomposes the pre-trained Transformer into a low-rank MoE structure and employ LoRA to fine-tune the parameters. Subsequently, we take into account the intrinsic asynchronous nature of multi-task learning and devise a learning Quality Retaining (QR) optimization mechanism, by leveraging the historical high-quality class logits to prevent a well-trained task from performance degradation. Finally, we design a router fading strategy to integrate the learned parameters into the original Transformer, archiving efficient inference. Extensive experiments on public benchmarks demonstrate the superiority of our method, compared to the state-of-the-art multi-task learning approaches. The project page is available at https://***/Yewen1486/EMTAL. Copyright © 2025, The Authors. All rights reserved.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Flow-aware synthesis: A generic motion model for video frame interpolation

引用

Computational Visual Media 2021年第3期7卷 393-405页

作者： Jinbo Xing Wenbo Hu Yuechen Zhang Tien-Tsin Wong Department of Computer Science and Engineering the Chinese University of Hong KongHong Kong SARChina Shenzhen Key Laboratory of Virtual Reality and Human Interaction Technology Shenzhen Institutes of Advanced TechnologyChinese Academy of SciencesChina

A popular and challenging task in video research,frame interpolation aims to increase the frame rate of *** existing methods employ a fixed motion model,e.g.,linear,quadratic,or cubic,to estimate the intermediate warping ***,such fixed motion models cannot well represent the complicated non-linear motions in the real world or rendered ***,we present an adaptive flow prediction module to better approximate the complex motions in ***,interpolating just one intermediate frame between consecutive input frames may be insufficient for complicated non-linear *** enable multi-frame interpolation,we introduce the time as a control variable when interpolating frames between original ones in our generic adaptive flow prediction *** and quantitative experimental results show that our method can produce high-quality results and outperforms the existing stateof-the-art methods on popular public datasets.

关键词： flow-aware generic motion model video frame interpolation

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-Estimation with Normalized Logits for Out-of-Distribution Detection

arXiv

引用

arXiv 2023年

作者： Huang, Mouxiao Qiao, Yu The Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China

Out-of-distribution (OOD) detection is critical for preventing deep learning models from making incorrect predictions to ensure the safety of artificial intelligence systems. Especially in safety-critical applications such as medical diagnosis and autonomous driving, the cost of incorrect decisions is usually unbearable. However, neural networks often suffer from the overconfidence issue, making high confidence for OOD data which are never seen during training process and may be irrelevant to training data, namely in-distribution (ID) data. Determining the reliability of the prediction is still a difficult and challenging task. In this work, we propose Uncertainty-Estimation with Normalized Logits (UE-NL), a robust learning method for OOD detection, which has three main benefits. (1) Neural networks with UE-NL treat every ID sample equally by predicting the uncertainty score of input data and the uncertainty is added into softmax function to adjust the learning strength of easy and hard samples during training phase, making the model learn robustly and accurately. (2) UE-NL enforces a constant vector norm on the logits to decouple the effect of the increasing output’s norm from optimization process, which causes the overconfidence issue to some extent. (3) UE-NL provides a new metric, the magnitude of uncertainty score, to detect OOD data. Experiments demonstrate that UE-NL achieves top performance on common OOD benchmarks and is more robust to noisy ID data that may be misjudged as OOD data by other methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Cumulus cloud modeling from images based on VAE-GAN

引用

virtual reality & Intelligent Hardware 2021年第2期3卷 171-181页

作者： Zili ZHANG Yunchi CEN Fan ZHANG Xiaohui LIANG State Key Laboratory of Virtual Reality Technology and Systems Beihang UniversityBeijing 100191China Department of Computer Science and Engineering Shijiazhuang UniversityShijiazhuang 050035China

Background Cumulus clouds are important elements in creating virtual outdoor *** cumulus clouds that have a specific shape is difficult owing to the fluid nature of the ***-based modeling is an efficient method to solve this *** of the complexity of cloud shapes,the task of modeling the cloud from a single image remains in the development *** In this study,a deep learning-based method was developed to address the problem of modeling 3D cumulus clouds from a single *** method employs a three-dimensional autoencoder network that combines the variational autoencoder and the generative adversarial ***,a 3D cloud shape is mapped into a unique hidden space using the proposed ***,the parameters of the decoder are fixed.A shape reconstruction network is proposed for use instead of the encoder part,and it is trained with rendered *** train the presented models,we constructed a 3D cumulus dataset that included 2003D cumulus *** cumulus clouds were rendered under different lighting *** The qualitative experiments showed that the proposed autoencoder method can learn more structural details of 3D cumulus shapes than existing ***,some modeling experiments on rendering images demonstrated the effectiveness of the reconstruction *** The proposed autoencoder network learns the latent space of 3D cumulus cloud *** presented reconstruction architecture models a cloud from a single *** demonstrated the effectiveness of the two models.

关键词： 3D cloud model 3D autoencoder network Generative adversarial network

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：