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

23,000 篇 会议
126 册 图书
92 篇 期刊文献

馆藏范围

23,217 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

13,622 篇 工学
- 11,107 篇 计算机科学与技术...
- 3,479 篇 软件工程
- 2,445 篇 机械工程
- 1,716 篇 光学工程
- 1,075 篇 电气工程
- 1,014 篇 控制科学与工程
- 784 篇 信息与通信工程
- 411 篇 仪器科学与技术
- 352 篇 生物工程
- 251 篇 生物医学工程（可授...
- 196 篇 电子科学与技术（可...
- 114 篇 化学工程与技术
- 107 篇 安全科学与工程
- 100 篇 测绘科学与技术
- 88 篇 建筑学
- 86 篇 交通运输工程
- 84 篇 土木工程
3,494 篇 医学
- 3,481 篇 临床医学
- 81 篇 基础医学(可授医学...
3,241 篇 理学
- 1,939 篇 物理学
- 1,640 篇 数学
- 563 篇 统计学（可授理学、...
- 500 篇 生物学
- 249 篇 系统科学
- 106 篇 化学
521 篇 管理学
- 311 篇 图书情报与档案管...
- 223 篇 管理科学与工程(可...
- 76 篇 工商管理
276 篇 艺术学
- 276 篇 设计学（可授艺术学...
66 篇 法学
- 63 篇 社会学
38 篇 农学
28 篇 教育学
22 篇 经济学
10 篇 军事学
3 篇 文学

主题

10,186 篇 computer vision
3,966 篇 pattern recognit...
3,005 篇 training
2,007 篇 computational mo...
1,818 篇 visualization
1,815 篇 cameras
1,515 篇 feature extracti...
1,481 篇 shape
1,455 篇 three-dimensiona...
1,438 篇 image segmentati...
1,287 篇 robustness
1,205 篇 computer archite...
1,155 篇 semantics
1,147 篇 conferences
1,107 篇 layout
1,092 篇 computer science
1,087 篇 object detection
1,025 篇 benchmark testin...
970 篇 codes
922 篇 face recognition

机构

136 篇 univ sci & techn...
121 篇 univ chinese aca...
118 篇 chinese univ hon...
107 篇 carnegie mellon ...
101 篇 tsinghua univers...
101 篇 microsoft resear...
95 篇 swiss fed inst t...
93 篇 zhejiang univ pe...
82 篇 university of sc...
81 篇 zhejiang univers...
80 篇 university of ch...
77 篇 shanghai ai lab ...
72 篇 shanghai jiao to...
69 篇 national laborat...
67 篇 microsoft res as...
67 篇 alibaba grp peop...
64 篇 adobe research
61 篇 tsinghua univ pe...
60 篇 peking univ peop...
59 篇 univ oxford oxfo...

作者

81 篇 van gool luc
72 篇 timofte radu
64 篇 zhang lei
47 篇 luc van gool
40 篇 yang yi
40 篇 li stan z.
37 篇 loy chen change
34 篇 chen chen
33 篇 xiaoou tang
32 篇 liu yang
32 篇 qi tian
31 篇 tian qi
31 篇 sun jian
30 篇 murino vittorio
30 篇 pascal fua
29 篇 darrell trevor
29 篇 li fei-fei
28 篇 li xin
28 篇 ying shan
27 篇 vasconcelos nuno

语言

23,137 篇 英文
52 篇 其他
22 篇 中文
5 篇 土耳其文
2 篇 日文

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

共 23218 条记录，以下是971-980 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：

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

Generalizable Implicit Neural Representations via Instance pattern Composers

Generalizable Implicit Neural Representations via Instance P...

引用

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

作者： Kim, Chiheon Lee, Doyup Kim, Saehoon Cho, Minsu Han, Wook-Shin Kakao Brain Seongnam South Korea POSTECH Pohang South Korea

ISBN: (纸本)9798350301298

Despite recent advances in implicit neural representations (INRs), it remains challenging for a coordinate-based multi-layer perceptron (MLP) of INRs to learn a common representation across data instances and generalize it for unseen instances. In this work, we introduce a simple yet effective framework for generalizable INRs that enables a coordinate-based MLP to represent complex data instances by modulating only a small set of weights in an early MLP layer as an instance pattern composer;the remaining MLP weights learn pattern composition rules for common representations across instances. Our generalizable INR framework is fully compatible with existing meta-learning and hypernetworks in learning to predict the modulated weight for unseen instances. Extensive experiments demonstrate that our method achieves high performance on a wide range of domains such as an audio, image, and 3D object, while the ablation study validates our weight modulation.

关键词： Self-supervised or unsupervised representation learning

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

Auxiliary Learning for Self-Supervised Video Representation via Similarity-based Knowledge Distillation

Auxiliary Learning for Self-Supervised Video Representation ...

引用

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

作者： Dadashzadeh, Amirhossein Whone, Alan Mirmehdi, Majid Univ Bristol Bristol Avon England

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Despite the outstanding success of self-supervised pretraining methods for video representation learning, they generalise poorly when the unlabeled dataset for pretraining is small or the domain difference between unlabelled data in source task (pretraining) and labeled data in target task (finetuning) is significant. To mitigate these issues, we propose a novel approach to complement self-supervised pretraining via an auxiliary pretraining phase, based on knowledge similarity distillation, auxSKD, for better generalisation with a significantly smaller amount of video data, e.g. Kinetics-100 rather than Kinetics-400. Our method deploys a teacher network that iteratively distils its knowledge to the student model by capturing the similarity information between segments of unlabelled video data. The student model meanwhile solves a pretext task by exploiting this prior knowledge. We also introduce a novel pretext task, Video Segment Pace Prediction or VSPP, which requires our model to predict the playback speed of a randomly selected segment of the input video to provide more reliable self-supervised representations. Our experimental results show superior results to the state of the art on both UCF101 and HMDB51 datasets when pretraining on K100 in apple-to-apple comparisons. Additionally, we show that our auxiliary pretraining, auxSKD, when added as an extra pretraining phase to recent state of the art self-supervised methods (i.e. VCOP, VideoPace, and RSPNet), improves their results on UCF101 and HMDB51.

关键词： Representation learning Knowledge engineering Training Predictive models Data models pattern recognition Reliability

来源：评论

学校读者我要写书评

暂无评论

LAVENDER: Unifying Video-Language Understanding as Masked Language Modeling

LAVENDER: Unifying Video-Language Understanding as Masked La...

引用

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

作者： Li, Linjie Can, Zhe Lin, Kevin Lin, Chung-Ching Liu, Zicheng Liu, Ce Wang, Lijuan Microsoft Albuquerque NM 87108 USA

ISBN: (纸本)9798350301298

Unified vision-language frameworks have greatly advanced in recent years, most of which adopt an encoder-decoder architecture to unify image-text tasks as sequence-to-sequence generation. However, existing video-language (VidL) models still require task-specific designs in model architecture and training objectives for each task. In this work, we explore a unified VidL framework LAVENDER, where Masked Language Modeling [13] (MLM) is used as the common interface for all pre-training and downstream tasks. Such unification leads to a simplified model architecture, where only a lightweight MLM head, instead of a decoder with much more parameters, is needed on top of the multimodal encoder. Surprisingly, experimental results show that this unified framework achieves competitive performance on 14 VidL benchmarks, covering video question answering, text-to-video retrieval and video captioning. Extensive analyses further demonstrate LAVENDER can (i) seamlessly support all downstream tasks with just a single set of parameter values when multi-task fine-tuned;(ii) generalize to various downstream tasks with limited training samples;and (iii) enable zero-shot evaluation on video question answering tasks. Code is available at https://***/microsoft/LAVENDER.

关键词： and reasoning language vision

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

Learning Debiased Representations via Conditional Attribute Interpolation

Learning Debiased Representations via Conditional Attribute ...

引用

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

作者： Zhang, Yi-Kai Wang, Qi-Wei Zhan, De-Chuan Ye, Han-Jia Nanjing Univ State Key Lab Novel Software Technol Nanjing Peoples R China

ISBN: (纸本)9798350301298

An image is usually described by more than one attribute like "shape" and "color". When a dataset is biased, i.e., most samples have attributes spuriously correlated with the target label, a Deep Neural Network (DNN) is prone to make predictions by the "unintended" attribute, especially if it is easier to learn. To improve the generalization ability when training on such a biased dataset, we propose a chi(2)-model to learn debiased representations. First, we design a.-shape pattern to match the training dynamics of a DNN and find Intermediate Attribute Samples (IASs) samples near the attribute decision boundaries, which indicate how the value of an attribute changes from one extreme to another. Then we rectify the representation with a chi-structured metric learning objective. Conditional interpolation among IASs eliminates the negative effect of peripheral attributes and facilitates retaining the intra-class compactness. Experiments show that chi(2)-model learns debiased representation effectively and achieves remarkable improvements on various datasets. Code is available at: https: //***/ZhangYikaii/chi-square

关键词： accountability ethics in vision fairness privacy Transparency

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

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

An Once-for-All Budgeted Pruning Framework for ConvNets Considering Input Resolution

An Once-for-All Budgeted Pruning Framework for ConvNets Cons...

引用

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

作者： Sun, Wenyu Cao, Jian Xu, Pengtao Liu, Xiangcheng Zhang, Yuan Wang, Yuan Peking Univ Sch Software & Microelect Beijing Peoples R China Peking Univ Sch Integrated Circuits Beijing Peoples R China

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

We propose an efficient once-for-all budgeted pruning framework (OFARPruning) to find many compact network architectures close to winner tickets in the early training stage considering the effect of input resolution during the pruning process. In architecture searching stage, we measure the similarity of the pruning mask to get high-quality network architecture with low energy and time consumption. After searching stage, our proposed method randomly sample the compact architectures with different pruning rates and input resolution to achieve joint optimization. Ultimately, we can obtain a cohort of compact networks adaptive to various resolution to meet dynamic FLOPs constraints on different edge devices with only once training. The experiments based on image classification and object detection show that OFARPruning has a higher accuracy than the once-for-all compression methods such as US-Net and MutualNet (1-2% better with less FLOPs), and achieve competitive performance as the conventional pruning methods (72.6% vs. 70.5% on MobileNetv2 under 170 MFLOPs) with much higher efficiency.

关键词： Training Image resolution Adaptive systems Image edge detection Energy resolution Object detection computer architecture

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 << < 94 95 96 97 98 99 100 101 102 103 > >>

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：