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

5,349 篇 会议
129 册 图书
29 篇 期刊文献

馆藏范围

5,507 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,748 篇 工学
- 2,253 篇 计算机科学与技术...
- 926 篇 软件工程
- 478 篇 光学工程
- 399 篇 控制科学与工程
- 332 篇 机械工程
- 262 篇 仪器科学与技术
- 250 篇 信息与通信工程
- 128 篇 电气工程
- 122 篇 生物工程
- 90 篇 生物医学工程（可授...
- 70 篇 电子科学与技术（可...
- 39 篇 安全科学与工程
- 33 篇 化学工程与技术
- 31 篇 建筑学
- 27 篇 土木工程
- 25 篇 交通运输工程
- 24 篇 航空宇航科学与技...
859 篇 理学
- 526 篇 物理学
- 439 篇 数学
- 155 篇 统计学（可授理学、...
- 133 篇 生物学
- 28 篇 化学
- 22 篇 系统科学
242 篇 艺术学
- 242 篇 设计学（可授艺术学...
196 篇 管理学
- 101 篇 图书情报与档案管...
- 97 篇 管理科学与工程(可...
- 27 篇 工商管理
96 篇 医学
- 96 篇 临床医学
- 21 篇 基础医学(可授医学...
28 篇 法学
- 26 篇 社会学
8 篇 教育学
6 篇 经济学
5 篇 农学
2 篇 军事学

主题

2,165 篇 computer vision
915 篇 pattern recognit...
890 篇 conferences
640 篇 training
565 篇 cameras
410 篇 feature extracti...
373 篇 computational mo...
364 篇 image segmentati...
350 篇 visualization
338 篇 face recognition
321 篇 computer archite...
309 篇 robustness
290 篇 computer science
287 篇 shape
280 篇 humans
266 篇 object detection
234 篇 layout
196 篇 neural networks
191 篇 application soft...
191 篇 lighting

机构

20 篇 swiss fed inst t...
19 篇 institute for co...
18 篇 university of sc...
18 篇 microsoft resear...
18 篇 swiss fed inst t...
16 篇 carnegie mellon ...
16 篇 chinese acad sci...
14 篇 tsinghua univers...
14 篇 univ sci & techn...
14 篇 carnegie mellon ...
12 篇 harbin inst tech...
12 篇 tsinghua univ pe...
12 篇 department of co...
11 篇 megvii technol p...
11 篇 computer vision ...
11 篇 computer vision ...
10 篇 indian statistic...
10 篇 comp vis ctr bar...
10 篇 school of comput...
10 篇 univ modena & re...

作者

58 篇 timofte radu
17 篇 van gool luc
17 篇 luc van gool
17 篇 horst bischof
16 篇 rita cucchiara
16 篇 radu timofte
14 篇 escalera sergio
14 篇 bischof horst
14 篇 sergio escalera
13 篇 zhigang zhu
13 篇 hugo jair escala...
12 篇 murino vittorio
12 篇 li stan z.
12 篇 chen wei-ting
12 篇 qiang ji
11 篇 cucchiara rita
11 篇 fan haoqiang
11 篇 umapada pal
11 篇 marcos v. conde
11 篇 bowyer kevin w.

语言

5,493 篇 英文
10 篇 中文
5 篇 其他

检索条件"任意字段=2006 Conference on Computer Vision and Pattern Recognition Workshops"

共 5507 条记录，以下是471-480 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：

Goal-driven Self-Attentive Recurrent Networks for Trajectory Prediction

Goal-driven Self-Attentive Recurrent Networks for Trajectory...

引用

IEEE/CVF conference on computer vision and pattern recognition (CVPR)

作者： Chiara, Luigi Filippo Coscia, Pasquale Das, Sourav Calderara, Simone Cucchiara, Rita Ballan, Lamberto Univ Padua Padua Italy Univ Modena & Reggio Emilia Modena Italy

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Human trajectory forecasting is a key component of autonomous vehicles, social-aware robots and advanced video-surveillance applications. This challenging task typically requires knowledge about past motion, the environment and likely destination areas. In this context, multimodality is a fundamental aspect and its effective modeling can be beneficial to any architecture. Inferring accurate trajectories is nevertheless challenging, due to the inherently uncertain nature of the future. To overcome these difficulties, recent models use different inputs and propose to model human intentions using complex fusion mechanisms. In this respect, we propose a lightweight attention-based recurrent backbone that acts solely on past observed positions. Although this backbone already provides promising results, we demonstrate that its prediction accuracy can be improved considerably when combined with a scene-aware goal-estimation module. To this end, we employ a common goal module, based on a U-Net architecture, which additionally extracts semantic information to predict scene-compliant destinations. We conduct extensive experiments on publicly-available datasets (i.e. SDD, inD, ETH/UCY) and show that our approach performs on par with state-of-the-art techniques while reducing model complexity.

关键词： Measurement Semantics Stochastic processes computer architecture Trajectory Data mining Task analysis

来源：评论

学校读者我要写书评

暂无评论

Real-time Hyper-Dimensional Reconfiguration at the Edge using Hardware Accelerators

Real-time Hyper-Dimensional Reconfiguration at the Edge usin...

引用

IEEE/CVF conference on computer vision and pattern recognition (CVPR)

作者： Kandaswamy, Indhumathi Farkya, Saurabh Daniels, Zachary van der Wal, Gooitzen Raghavan, Aswin Zhang, Yuzheng Hu, Jun Lomnitz, Michael Isnardi, Michael Zhang, David Piacentino, Michael SRI Int Ctr Vis Technol Princeton NJ 08540 USA

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

In this paper we present Hyper-Dimensional Reconfigurable Analytics at the Tactical Edge (HyDRATE) using low-SWaP embedded hardware that can perform real-time reconfiguration at the edge leveraging non-MAC (free of floating-point Multiply-ACcumulate operations) deep neural nets (DNN) combined with hyperdimensional (HD) computing accelerators. We describe the algorithm, trained quantized model generation, and simulated performance of a feature extractor free of multiply-accumulates feeding a hyperdimensional logic-based classifier. Then we show how performance increases with the number of hyperdimensions. We describe the realized low-SWaP FPGA hardware and embedded software system compared to traditional DNNs and detail the implemented hardware accelerators. We discuss the measured system latency and power, noise robustness due to use of learnable quantization and HD computing, actual versus simulated system performance for a video activity classification task and demonstration of reconfiguration on this same dataset. We show that reconfigurability in the field is achieved by retraining only the feed-forward HD classifier without gradient descent backpropagation (gradient-free), using few-shot learning of new classes at the edge. Initial work performed used LRCN DNN and is currently extended to use Two-stream DNN with improved performance.

关键词： Quantization (signal) Power measurement System performance Software algorithms Feature extraction Real-time systems pattern recognition

来源：评论

学校读者我要写书评

暂无评论

MARRS: Modern Backbones Assisted Co-training for Rapid and Robust Semi-Supervised Domain Adaptation

MARRS: Modern Backbones Assisted Co-training for Rapid and R...

引用

2023 IEEE/CVF conference on computer vision and pattern recognition workshops, CVPRW 2023

作者： Jain, Saurabh Kumar Das, Sukhendu Indian Institute of Technology Visualization and Perception Lab Department of Computer Science Engineering Madras India

ISBN: (纸本)9798350302493

Semi-Supervised Domain Adaptation (SSDA) aims to develop domain invariant models from scarcely labeled target domain in addition to the fully labeled source domain. Current SSDA works are often applied in conjunction with ResNet34 backbone, which makes them overlook the advantages of utilizing other backbones. Hence, in this paper, we investigate the impact of employing different modern backbones in SSDA and propose a novel solution named Modern Backbones Assisted Co-training for Rapid and Robust Semi-Supervised Domain Adaptation (MARRS), that uses discriminative features of two modern backbones for training linear classifiers using the well established co-training framework. To induce diversity among classifiers for effective co-training, we propose a novel module that produces diversity at three levels, namely image, backbone, and feature distribution levels. Experiments reveal that MARRS not only achieves state-of-the-art performance across all popular SSDA datasets, but also drastically cuts the computation time compared to other SSDA approaches, making MARRS a rapid and robust solution for SSDA. We also provide extensive ablation experiments to verify our framework's vitality and primary design choices. © 2023 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

EFE: End-to-end Frame-to-Gaze Estimation

EFE: End-to-end Frame-to-Gaze Estimation

引用

2023 IEEE/CVF conference on computer vision and pattern recognition workshops, CVPRW 2023

作者： Balim, Haldun Park, Seonwook Wang, Xi Zhang, Xucong Hilliges, Otmar ETH Zürich Department of Computer Science Switzerland Lunit Inc. Delft University of Technology Computer Vision Lab Netherlands

ISBN: (纸本)9798350302493

Despite the recent development of learning-based gaze estimation methods, most methods require one or more eye or face region crops as inputs and produce a gaze direction vector as output. Cropping results in a higher resolution in the eye regions and having fewer confounding factors (such as clothing and hair) is believed to benefit the final model performance. However, this eye/face patch cropping process is expensive, erroneous, and implementation-specific for different methods. In this paper, we propose a frame-to-gaze network that directly predicts both 3D gaze origin and 3D gaze direction from the raw frame out of the camera without any face or eye cropping. Our method demonstrates that direct gaze regression from the raw downscaled frame, from FHD/HD to VGA/HVGA resolution, is possible despite the challenges of having very few pixels in the eye region. The proposed method achieves comparable results to state-of-the-art methods in Point-of-Gaze (PoG) estimation on three public gaze datasets: GazeCapture, MPIIFaceGaze, and EVE, and generalizes well to extreme camera view changes. © 2023 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

One-Stage Object Referring with Gaze Estimation

One-Stage Object Referring with Gaze Estimation

引用

IEEE/CVF conference on computer vision and pattern recognition (CVPR)

作者： Chen, Jianhang Zhang, Xu Wu, Yue Ghosh, Shalini Natarajan, Pradeep Chang, Shih-Fu Allebach, Jan Purdue Univ W Lafayette IN 47907 USA Amazon Seattle WA 98109 USA Columbia Univ New York NY 10027 USA

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

The classic object referring task aims at localizing the referred object in the image and requires a reference image and a natural language description as inputs. Given the facts that gaze signal can be easily obtained by a modern human-computer interaction system with a camera and that human tends to look at the object when referring to it, we propose a novel gaze-assisted object referring framework. The formulation not only simplifies the state-of-the-art gaze-assisted object referring system requiring many input signals besides gaze, but also incorporates the one-stage object detection idea to improve the inference efficiency. More importantly, it implicitly considers all object candidates and thus resolves the main pain point of existing two-stage object referring solutions for proposing an appropriate number of candidates - it cannot be too large, otherwise the computational cost can be prohibitive;it cannot be too small, otherwise the chance of missing a referred object can be significant. To utilize the gaze information, we propose to build a gaze heatmap by using the anchor position encoding map and the gaze prediction result. The gaze heatmap and the language feature are then merged into the feature pyramid in the object detection as the final one-stage referring system. In the CityScapes-OR dataset, the proposed method outperforms the state-of-the-art by 7.8% for Acc@1.

关键词： Heating systems computer vision Computational modeling Natural languages Object detection Feature extraction Encoding

来源：评论

学校读者我要写书评

暂无评论

Guided Deep Metric Learning

Guided Deep Metric Learning

引用

IEEE/CVF conference on computer vision and pattern recognition (CVPR)

作者： Gonzalez-Zapata, Jorge Reyes-Amezcua, Ivan Flores-Araiza, Daniel Mendez-Ruiz, Mauricio Ochoa-Ruiz, Gilberto Mendez-Vazquez, Andres CINVESTAV Unidad Guadalajara Zapopan Mexico Tecnol Monterrey Sch Engn & Sci Monterrey Mexico

ISBN: (纸本)9781665487399

Deep Metric Learning (DML) methods have been proven relevant for visual similarity learning. However, they sometimes lack generalization properties because they are trained often using an inappropriate sample selection strategy or due to the difficulty of the dataset caused by a distributional shift in the data. These represent a significant drawback when attempting to learn the underlying data manifold. Therefore, there is a pressing need to develop better ways of obtaining generalization and representation of the underlying manifold. In this paper, we propose a novel approach to DML that we call Guided Deep Metric Learning, a novel architecture oriented to learning more compact clusters, improving generalization under distributional shifts in DML. This novel architecture consists of two independent models: A multi-branch master model, inspired from a Few-Shot Learning (FSL) perspective, generates a reduced hypothesis space based on prior knowledge from labeled data, which guides or regularizes the decision boundary of a student model during training under an offline knowledge distillation scheme. Experiments have shown that the proposed method is capable of a better manifold generalization and representation to up to 40% improvement (Recall@1, CIFAR10), using guidelines suggested by Musgrave et al. to perform a more fair and realistic comparison, which is currently absent in the literature.

关键词： Measurement Manifolds Training Analytical models Adaptation models Visualization computer architecture

来源：评论

学校读者我要写书评

暂无评论

SoccerTrack: A Dataset and Tracking Algorithm for Soccer with Fish-eye and Drone Videos

SoccerTrack: A Dataset and Tracking Algorithm for Soccer wit...

引用

IEEE/CVF conference on computer vision and pattern recognition (CVPR)

作者： Scott, Atom Uchida, Ikuma Onishi, Masaki Kameda, Yoshinari Fukui, Kazuhiro Fujii, Keisuke Univ Tsukuba Tsukuba Ibaraki Japan Natl Inst Adv Ind Sci & Technol Tsukuba Japan Nagoya Univ Nagoya Aichi Japan RIKEN JST PRESTO Tokyo Japan

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Tracking devices that can track both players and balls are critical to the performance of sports teams. Recently, significant effort has been focused on building larger broadcast sports video datasets. However, broadcast videos do not show the entire pitch and only provides partial information about the game. On the other hand, other camera perspectives can capture the whole field in a single frame, such as fish-eye and bird-eye view (drone) cameras. Unfortunately, there has not been a dataset where such data has been publicly shared until now. This paper proposes SoccerTrack, a dataset set consisting of GNSS and bounding box tracking data annotated on video captured with a 8K-resolution fish-eye camera and a 4K-resolution drone camera. In addition to a benchmark tracking algorithm, we include code for camera calibration and other preprocessing. Finally, we evaluate the tracking accuracy among a GNSS, fish-eye camera and drone camera data. SoccerTrack is expected to provide a more robust foundation for designing MOT algorithms that are less reliant on visual cues and more reliant on motion analysis.

关键词： Performance evaluation Global navigation satellite system Visualization Codes Tracking Cameras pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Multi-Head Distillation for Continual Unsupervised Domain Adaptation in Semantic Segmentation

Multi-Head Distillation for Continual Unsupervised Domain Ad...

引用

IEEE/CVF conference on computer vision and pattern recognition (CVPR)

作者： Saporta, Antoine Douillard, Arthur Vu, Tuan-Hung Perez, Patrick Cord, Matthieu Sorbonne Univ Paris France valeo ai Paris France Heuritech Paris France

ISBN: (纸本)9781665487399

Unsupervised Domain Adaptation (UDA) is a transfer learning task which aims at training on an unlabeled target domain by leveraging a labeled source domain. Beyond the traditional scope of UDA with a single source domain and a single target domain, real-world perception systems face a variety of scenarios to handle, from varying lighting conditions to many cities around the world. In this context, UDAs with several domains increase the challenges with the addition of distribution shifts within the different target domains. This work focuses on a novel framework for learning UDA, continuous UDA, in which models operate on multiple target domains discovered sequentially, without access to previous target domains. We propose MuHDi, for Multi-Head Distillation, a method that solves the catastrophic forgetting problem, inherent in continual learning tasks. MuHDi performs distillation at multiple levels from the previous model as well as an auxiliary target-specialist segmentation head. We report both extensive ablation and experiments on challenging multi-target UDA semantic segmentation benchmarks to validate the proposed learning scheme and architecture.

关键词： Training Adaptation models Urban areas Semantics Transfer learning computer architecture Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Contrastive Learning-based Robust Object Detection under Smoky Conditions

Contrastive Learning-based Robust Object Detection under Smo...

引用

IEEE/CVF conference on computer vision and pattern recognition (CVPR)

作者： Wu, Wei Chang, Hao Zheng, Yonghua Li, Zhu Chen, Zhiwen Zhang, Ziheng Xidian Univ State Key Lab Integrated Serv Networks Xian Peoples R China Univ Missouri Dept Comp Sci & Elect Engn Kansas City MO 64110 USA

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Object detection is to effectively find out interested targets in images and then accurately determine their categories and positions. Recently many excellent methods have been developed to provide powerful detection capability. However, their performance may degrade significantly under severe weather such as smoky conditions. In this paper, we propose a contrastive learning-based robust object detection algorithm for smoke images. The proposed object detector consists of two modules: contrastive learning module and object bounding box prediction module. The first module learns representation vectors by maximizing agreement between different augmented views of the same smoke image. These representations are then sent to the second module to yield the bounding box for each object. In addition, we also propose a novel affine data augmentation method. Extensive experiments have been conducted on A2I2-Haze dataset which is the first real haze dataset with in-situ smoke measurement aligned to aerial and ground imagery. This dataset is also the only dataset used in the 5th UG(2)+ challenges of CVPR 2022 for both training and testing. Compared with state-of-the-art methods, evaluation results show the superiority of our proposed object detector.

关键词： Training computer vision conferences Object detection Detectors Transforms Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Remote Heart Rate Estimation by Signal Quality Attention Network

Remote Heart Rate Estimation by Signal Quality Attention Net...

引用

IEEE/CVF conference on computer vision and pattern recognition (CVPR)

作者： Gao, Haoyuan Wu, Xiaopei Geng, Jidong Lv, Yang Anhui Univ Sch Comp Sci & Technol Hefei Peoples R China

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Heart rate estimation is very important for heart health monitoring. As a non-invasive optical technology, remote photoplethysmography (rPPG) has the advantages of non-contact, portability and low-price. However, motion and noise artifacts bring additional uncertainty to the results of heart rate estimation. Based on the signal quality assessment method, we propose a new remote heart estimation algorithm by signal quality attention mechanism and long short-term memory (LSTM) networks. The model consists of three parts: firstly, an LSTM network is used to estimate the heart rate sampling point by sampling point;secondly, a similar LSTM network predicts the signal quality;finally, an attention-based model uses the heart rates and quality scores predicted above to calculate the average heart rate of a period of time. The model allocates higher weights to the reliable heart rates estimated from high-quality signals, meanwhile, ignores unreliable results estimated from low-quality signals. Experiments show that LSTM with attention mechanism accurately estimates heart rate from corruption rPPG signal and it performs well on cross-subject tasks and cross-dataset tasks. The results also demonstrate that the scores predicted by the signal quality model is valuable to extract reliable heart rate.

关键词： Heart rate Training Uncertainty computer network reliability Estimation Predictive models Prediction algorithms

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 << < 44 45 46 47 48 49 50 51 52 53 > >>

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：