检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

8,283 篇 会议
385 篇 期刊文献
19 篇 学位论文
11 册 图书
3 篇 资讯

馆藏范围

8,701 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

5,388 篇 工学
- 3,227 篇 计算机科学与技术...
- 1,802 篇 电气工程
- 1,721 篇 软件工程
- 1,345 篇 信息与通信工程
- 590 篇 机械工程
- 535 篇 控制科学与工程
- 465 篇 电子科学与技术（可...
- 451 篇 光学工程
- 351 篇 仪器科学与技术
- 208 篇 安全科学与工程
- 200 篇 生物医学工程（可授...
- 162 篇 交通运输工程
- 148 篇 材料科学与工程（可...
- 132 篇 生物工程
- 94 篇 航空宇航科学与技...
- 82 篇 测绘科学与技术
- 69 篇 化学工程与技术
- 64 篇 土木工程
1,970 篇 理学
- 1,384 篇 物理学
- 466 篇 数学
- 159 篇 系统科学
- 141 篇 生物学
- 111 篇 统计学（可授理学、...
- 76 篇 化学
1,373 篇 医学
- 1,299 篇 临床医学
- 114 篇 特种医学
379 篇 管理学
- 275 篇 管理科学与工程(可...
- 108 篇 图书情报与档案管...
- 78 篇 工商管理
54 篇 法学
- 49 篇 社会学
29 篇 农学
28 篇 经济学
23 篇 教育学
20 篇 艺术学
15 篇 文学
15 篇 军事学

主题

1,027 篇 image processing
708 篇 cameras
613 篇 streaming media
503 篇 real time system...
499 篇 real-time system...
443 篇 image segmentati...
380 篇 image coding
299 篇 image edge detec...
296 篇 object detection
277 篇 image color anal...
253 篇 video coding
253 篇 feature extracti...
251 篇 motion estimatio...
239 篇 hardware
217 篇 pixel
193 篇 computer archite...
182 篇 graphics process...
175 篇 field programmab...
166 篇 video compressio...
160 篇 visualization

机构

14 篇 school of commun...
12 篇 beijing key labo...
10 篇 institute of inf...
8 篇 univ chinese aca...
8 篇 center for signa...
7 篇 heinrich hertz i...
7 篇 tsinghua univ de...
7 篇 chinese acad sci...
7 篇 microsoft res as...
7 篇 department of co...
6 篇 univ pisa dept i...
6 篇 microsoft resear...
6 篇 eindhovan univer...
6 篇 imec leuven
6 篇 school of inform...
6 篇 hewlett packard ...
6 篇 electrical and c...
5 篇 tsinghua univers...
5 篇 beijing inst tec...
5 篇 tampere univ ult...

作者

18 篇 wang qi
14 篇 grecos christos
12 篇 li li
11 篇 saponara sergio
10 篇 nightingale jame...
9 篇 gohshi seiichi
9 篇 cheung gene
8 篇 li ying
8 篇 zhang hong
8 篇 satoshi goto
8 篇 takaki takeshi
8 篇 ponomaryov volod...
7 篇 amer aishy
7 篇 luciano agostini
7 篇 agostini luciano
7 篇 wang chunping
7 篇 chien shao-yi
7 篇 sarmiento r
7 篇 radha h
7 篇 liang-gee chen

语言

8,427 篇 英文
168 篇 中文
84 篇 其他
19 篇 土耳其文
3 篇 葡萄牙文
1 篇 西班牙文
1 篇 俄文

检索条件"任意字段=Conference on Real-Time Image and Video Processing 2011"

共 8701 条记录，以下是261-270 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Exploring Motion Cues for video Test-time Adaptation 23

Exploring Motion Cues for Video Test-Time Adaptation

引用

31st ACM International conference on Multimedia (MM)

作者： Zeng, Runhao Deng, Qi Xu, Huixuan Niu, Shuaicheng Chen, Jian Shenzhen Univ Guangdong Key Lab Elect Control & Intelligent Rob Coll Mech & Control Engn Shenzhen Peoples R China Shenzhen Univ Ind Res Ctr Intelligent Mfg Shenzhen Peoples R China South China Univ Technol Guangzhou Peoples R China Nanyang Technol Univ Singapore Singapore

ISBN: (纸本)9798400701085

Test-time adaptation (TTA) aims at boosting the generalization capability of a trained model by conducting self-/un-supervised learning during testing in real-world applications. Though TTA on image-based tasks has seen significant progress, TTA techniques for video remain scarce. Naively introducing image-based TTA methods into video tasks may achieve limited performance, since these methods do not consider the special nature of video tasks, e.g., the motion information. In this paper, we propose leveraging motion cues in videos to design a new test-time learning scheme for video classification. We extract spatial appearance and dynamic motion clip features using two sampling rates (i.e., slow and fast) and propose a fast-to-slow unidirectional alignment scheme to align fast motion and slow appearance features, thereby enhancing the motion encoding ability. Additionally, we propose a slow-fast dual contrastive learning strategy to learn a joint feature space for fastly and slowly sampled clips, guiding the model to extract discriminative video features. Lastly, we introduce a stochastic pseudo-negative sampling scheme to provide better adaptation supervision by selecting a more reliable pseudo-negative label compared to the pseudo-positive label used in prior TTA methods. This technique reduces the adaptation difficulty often caused by poor performance on out-of-distribution test data before adaptation. Our approach significantly improves performance on various video classification backbones, as demonstrated through extensive experiments on two benchmark datasets.

关键词： test-time adaptation video classification motion encoding

来源：评论

学校读者我要写书评

暂无评论

video Stabilization based on Sub-pixel Keypoints 4

Video Stabilization based on Sub-pixel Keypoints

引用

4th International conference on Defence Technology, ICDT 2024

作者： Zhong, Bihua Wang, Fangyi Liu, Tao Liu, Chengyi Bai, Hongyang Wan, Gang National Key Laboratory of Transient Physics Nanjing University of Science and Technology Nanjing210094 China School of Energy and Power Engineering Nanjing University of Science and Technology Nanjing210094 China Key Laboratory of Maritime Intelligent Cyberspace Technology Nanjing University of Science and Technology Ministry of Education Nanjing210094 China School of Electronic and Optical Engineering Nanjing University of Science and Technology Nanjing210094 China

With the continuous advancement of seeker technology and image processing techniques, the precision of guided weapons has increasingly improved. However, due to the rigidly fixed structure between the seeker and the guided weapon, the weapon is prone to experiencing disturbances and vibrations during flight, which can deteriorate the real-time video quality monitored by the seeker and, consequently reduce the precision of the guided weapon. To enhance the precision of guided weapons, it is necessary to mitigate the adverse effects of vibrations through video stabilization techniques. This paper proposes a video stabilization framework based on sub-pixel keypoints detection. It utilizes a lightweight network to detect keypoints, employs the Lucas-Kanade (LK) optical flow method for motion estimation, and smooths the camera's motion path with an adaptive filter. Experimental results show that the proposed algorithm has an average processing time of approximately 0.2s per frame, achieving a stability index of 0.9262, a PSNR index of 22.3074, and an SSIM index of 0.7188. This demonstrates a balanced performance in terms of computational efficiency and stabilization, exhibiting excellent comprehensive performance. © 2024 Institute of Physics Publishing. 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

FAST video OBJECT SEGMENTATION VIA DYNAMIC YOLACT 47

FAST VIDEO OBJECT SEGMENTATION VIA DYNAMIC YOLACT

引用

47th IEEE International conference on Acoustics, Speech and Signal processing (ICASSP)

作者： Meng, Tianfang Zhang, Wenqiang Fudan Univ Sch Comp Sci Shanghai Key Lab Intelligent Informat Proc Shanghai Peoples R China

ISBN: (纸本)9781665405409

video Object Segmentation (VOS) is a fundamental task in video recognition with many practical applications. It aims at predicting segmentation masks of multiple objects in an entire video. Recent video object segmentation(VOS) researches have achieved remarkable performance. However, as a video processing task, the inference speed of the VOS method is also essential. VOS can be considered an extension of semantic segmentation from a static image to a dynamic image sequence. Following this idea, we propose a fast VOS framework based on YOLACT, a real-time static image segmentation framework. We employ a fast online training technique to make YOLACT grow wings to handle dynamic video sequences and achieve competitive performance(77.2 J&F and 30.9 FPS on DAVIS17) among fast VOS methods. Moreover, by linearly combining mask bases to generate masks for arbitrary objects, our method can process multi-object videos with minimal extra computations.

关键词： video Object Segmentation Conjugate Gradient Optimization Online Training

来源：评论

学校读者我要写书评

暂无评论

Optimized image Mosaicing Using ORB with Histogram Equalization for real-time Applications 2

Optimized Image Mosaicing Using ORB with Histogram Equalizat...

引用

2nd International conference on Advanced Computing and Communication Technologies, ICACCTech 2024

作者： Shridhar, H. Harakannanavar, Sunil S. Chetan, R. Kanabur, Vidyashree Jayalaxmi, H. Prashanth, R.C. Government Engineering College Department of Electronics and Communication Engineering Karnataka Haveri581110 India Nitte Meenakshi Institute of Technology Yelahanka Department of Electronics and Communication Engineering Karnataka Bangalore India Shri Madhwa Vadiraja Institute of Technology & Management Banakal Department of Electronics and Communication Engineering Karnataka Udupi India National Institute of Technology Surathkal Department of Electronics and Communication Engineering Mangalore575025 India Acharya Institute of Technology Department of Electronics and Communication Engineering Karnataka Bangalore560090 India S J B Institute of Technology Department of Electronics and Communication Engineering Karnataka Bangalore560060 India

ISBN: (纸本)9798331519056

image mosaicing combines overlapping images of the same scene into a larger, seamless image. This work aims to develop a model that efficiently merges images while evaluating its performance in terms of runtime and the number of key features used. Histogram Equalization (HE) is applied to handle intensity variability, while key features are extracted using SIFT, ORB, and BRISK descriptors. K-Nearest Neighbor (KNN) matches the features, and homography is estimated using the RANSAC algorithm to align the images. A smoothing filter is applied to create the final panorama. Experimental results show that ORB with HE is the most efficient technique, using 500 key features and achieving a runtime of 0.0836 seconds. The average runtime of the entire image mosaicing process, from feature extraction to panorama generation, was significantly lower for ORB than for SIFT (0.45 seconds) and BRISK (0.30 seconds). The minimal runtime and reduced computational cost of ORB make it ideal for applications requiring real-time image stitching, such as video processing or live panoramic imaging. The proposed model addresses limitations in feature matching and offers improved performance in image mosaicing. © 2024 IEEE.

关键词： Equalizers

来源：评论

学校读者我要写书评

暂无评论

TOWARDS ZERO-LATENCY video TRANSMISSION THROUGH FRAME EXTRAPOLATION 29

TOWARDS ZERO-LATENCY VIDEO TRANSMISSION THROUGH FRAME EXTRAP...

引用

IEEE International conference on image processing (ICIP)

作者： Vijayaratnam, Melan Cagnazzo, Marco Valenzise, Giuseppe Trioux, Anthony Kieffer, Michel Inst Polytech Paris LTCI Telecom ParisTech Paris France Univ Padua Dept Informat Engn Padua Italy Univ Paris Saclay CNRS Cent Supelec Lab Signaux & Syst Gif Sur Yvette France Univ Polytech Hauts de France CNRS UMR 8520 DOAEIEMN Valenciennes France

ISBN: (数字)9781665496209

ISBN: (纸本)9781665496209

In the past few years, several efforts have been devoted to reduce individual sources of latency in video delivery, including acquisition, coding and network transmission. The goal is to improve the quality of experience in applications requiring real-time interaction. Nevertheless, these efforts are fundamentally constrained by technological and physical limits. In this paper, we investigate a radically different approach that can arbitrarily reduce the overall latency by means of video extrapolation. We propose two latency compensation schemes where video extrapolation is performed either at the encoder or at the decoder side. Since a loss of fidelity is the price to pay for compensating latency arbitrarily, we study the latency-fidelity compromise using three recent video prediction schemes. Our preliminary results show that by accepting a quality loss, we can compensate a typical latency of 100 ms with a loss of 8 dB in PSNR with the best extrapolator. This approach is promising but also suggests that further work should be done in video prediction to pursue zero-latency video transmission.

关键词： Extrapolation low-latency video delivery video deep learning

来源：评论

学校读者我要写书评

暂无评论

A Temporal Consistency Enhancement Algorithm Based on Pixel Flicker Correction 29th

A Temporal Consistency Enhancement Algorithm Based on Pixel ...

引用

29th International conference on Neural Information processing

作者： Meng, Junfeng Shen, Qiwei He, Yangliu Liao, Jianxin Beijing Univ Posts & Telecommun Beijing Peoples R China

ISBN: (纸本)9789819916382;9789819916399

When the image algorithm is directly applied to the video scene and the video is processed frame by frame, an obvious pixel flickering phenomenon is happened, that is the problem of temporal inconsistency. In this paper, a temporal consistency enhancement algorithm based on pixel flicker correction is proposed to enhance video temporal consistency. The algorithm consists of temporal stabilization module TSM-Net, optical flow constraint module and loss calculation module. The innovation of TSM-Net is that the ConvGRU network is embedded layer by layer with dual-channel parallel structure in the decoder, which effectively enhances the information extraction ability of the neural network in the time domain space through feature fusion. This paper also proposes a hybrid loss based on optical flow, which sums the temporal loss and the spatial loss to better balance the dominant role of the two during training. It improves temporal consistency while ensuring better perceptual similarity. Since the algorithm does not require optical flow during testing, it achieves real-time performance. This paper conducts experiments based on public datasets to verify the effectiveness of the pixel flicker correction algorithm.

关键词： short video creation deep learning temporal consistency optical flow

来源：评论

学校读者我要写书评

暂无评论

Experimental Evaluation of LED-based Wearable Transmitter for Optical Camera Communications Systems 17

Experimental Evaluation of LED-based Wearable Transmitter fo...

引用

17th International conference on Telecommunications (ConTEL)

作者： Niarchou, Eleni Matus, Vicente Rabadan, Jose Guerra, Victor Perez-Jimenez, Rafael IDeTIC ULPGC Las Palmas Gran Canaria Spain Pi Lighting Valais Switzerland

ISBN: (纸本)9798350302233

In this paper, we experimentally demonstrate an optical camera communications (OCC) system for wearable light-emitting diode (LED) as the transmitter. Wearable devices are powerful tools for supporting Internet of Things (IoT) systems because of their sensing, processing, and communication capability. The term "wearable devices" refers to a wide range of products that can be integrated into clothing and accessories, thus allowing real-time data detection, storage, and exchange without human intervention. This paper presents the practical evaluation of an LED-based wearable transmitter for an OCC system to demonstrate its feasibility. In particular, an LED array attached to the body is modulated using on-off keying to transmit data via visible light, and a smartphone camera captures video of the user wearing the device while slightly moving in a static position in the room. Finally, the data is decoded from the video frames using an image processing algorithm that tracks the source and demodulates the signal.

关键词： Optical camera communications (OCC) visible light communications (VLC) Internet of Things (IoT) wearable devices image processing

来源：评论

学校读者我要写书评

暂无评论

CLUSTERING-BASED PSYCHOMETRIC NO-REFERENCE QUALITY MODEL FOR POINT CLOUD video 29

CLUSTERING-BASED PSYCHOMETRIC NO-REFERENCE QUALITY MODEL FOR...

引用

IEEE International conference on image processing (ICIP)

作者： Van Damme, Sam Vega, Maria Torres van der Hooft, Jeroen De Turck, Filip Univ Ghent Dept Informat Technol INTEC IDLab Imec Ghent Belgium

ISBN: (数字)9781665496209

ISBN: (纸本)9781665496209

Point cloud video streaming is a fundamental application of immersive multimedia. In it, objects represented as sets of points are streamed and displayed to remote users. Given the high bandwidth requirements of this content, small changes in the network and/or encoding can affect the users' perceived quality in unexpected manners. To tackle the degradation of the service as fast as possible, real-time Quality of Experience (QoE) assessment is needed. As subjective evaluations are not feasible in real time due to their inherent costs and duration, low-complexity objective quality assessment is a must. Traditional No-Reference (NR) objective metrics at client side are best suited to fulfill the task. However, they lack on accuracy to human perception. In this paper, we present a cluster-based objective NR QoE assessment model for point cloud video. By means of Machine Learning (ML)-based clustering and prediction techniques combined with NR pixel-based features (e.g., blur and noise), the model shows high correlations (up to a 0.977 Pearson Linear Correlation Coefficient (PLCC)) and low Root Mean Squared Error (RMSE) (down to 0.077 on a zero-to-one scale) towards objective benchmarks after evaluation on an adaptive streaming point cloud dataset consisting of sixteen source videos and 453 sequences in total.

关键词： Point clouds Quality of Experience objective quality metrics psychometric curve-fitting quality modelling

来源：评论

学校读者我要写书评

暂无评论

RVSRT: real-time video Super Resolution Transformer 14

RVSRT: Real-time Video Super Resolution Transformer

引用

14th International conference on Graphics and image processing (ICGIP)

作者： Ou, Linlin Chen, Yuanping Chinese Acad Sci Comp Network Informat Ctr Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China

ISBN: (纸本)9781510666313;9781510666320

video super-resolution is the task of converting low-resolution video to high-resolution video. Existing methods with better intuitive effects are mainly based on convolutional neural networks (CNNs), but the architecture is heavy, resulting in a slow inference structure. Aiming at this problem, this paper proposes a real-time video super-resolution Transformer (RVSRT) can quickly complete the super-resolution task while considering the visual fluency of video frame switching. Unlike traditional methods based on CNNs, this paper does not process video frames separately with different network modules in the temporal domain, but batches adjacent frames through a single UNet-style structure end-to-end Transformer network architecture. Moreover, this paper creatively sets up two-stage interpolation sampling before and after the end-to-end network to maximize the performance of the traditional CV algorithm. The experimental results show that compared with SOTA TMNet [1], RVSRT has only 20% of the network size (2.3M vs 12.3M, parameters) while ensuring comparable performance, and the speed is increased by 80% (26.2 fps vs 14.3 fps, frame size is 720*576).

关键词： video super resolution vision transformer deep learning

来源：评论

学校读者我要写书评

暂无评论

SHAPE DETECTION IN AN image USING PARALLELIZED TRADITIONAL image ANALYSIS TECHNIQUES 58

SHAPE DETECTION IN AN IMAGE USING PARALLELIZED TRADITIONAL I...

引用

58th Annual International Telemetering conference, ITC 2023

作者： Loreto Cornídez, Alan Manuel Fuentes Gutiérrez, Rubén Diego College of Electrical and Computer Engineering The University of Arizona TucsonAZ85721 United States

Modern day computer vision applications are frequently implemented using machine learning approaches. While these implementations can perform very well, the performance is heavily dependent on sufficient and accurate training data. Due to a lack of adequate training data, the Arizona Autonomous Vehicles Club (AZA) decided to implement the generalized hough transform to detect shapes in a live video feed from an unmanned aerial system (UAS). The hough transform is computationally intensive and since real-time performance is required, a serial approach may not have the execution speed necessary for the application. image processing techniques include matrix multiplication and convolution operations which are highly parallelizable. Therefore, the algorithm was parallelized and implemented on a graphics processing unit (GPU). Performance profiling was done on both machine learning and traditional approaches where execution time and accuracy were compared. © 2023 International Foundation for Telemetering. All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共500页 << < 23 24 25 26 27 28 29 30 31 32 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：