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

6,639 篇 会议
34 篇 期刊文献
5 册 图书

馆藏范围

6,677 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

3,950 篇 工学
- 3,725 篇 计算机科学与技术...
- 1,476 篇 软件工程
- 807 篇 光学工程
- 323 篇 信息与通信工程
- 240 篇 控制科学与工程
- 206 篇 机械工程
- 169 篇 电气工程
- 85 篇 生物医学工程（可授...
- 73 篇 电子科学与技术（可...
- 70 篇 生物工程
- 65 篇 仪器科学与技术
- 38 篇 建筑学
- 36 篇 土木工程
- 34 篇 力学（可授工学、理...
- 32 篇 航空宇航科学与技...
- 29 篇 安全科学与工程
- 23 篇 化学工程与技术
- 21 篇 材料科学与工程（可...
1,498 篇 理学
- 969 篇 物理学
- 929 篇 数学
- 369 篇 统计学（可授理学、...
- 136 篇 生物学
- 40 篇 系统科学
- 26 篇 化学
210 篇 医学
- 210 篇 临床医学
- 23 篇 基础医学(可授医学...
165 篇 管理学
- 123 篇 图书情报与档案管...
- 44 篇 管理科学与工程(可...
- 29 篇 工商管理
21 篇 法学
- 21 篇 社会学
10 篇 农学
9 篇 教育学
6 篇 经济学
2 篇 军事学
1 篇 艺术学

主题

2,364 篇 computer vision
848 篇 pattern recognit...
663 篇 cameras
634 篇 computer science
592 篇 face recognition
558 篇 layout
541 篇 conferences
527 篇 image segmentati...
514 篇 shape
454 篇 object recogniti...
453 篇 robustness
394 篇 humans
339 篇 feature extracti...
324 篇 training
305 篇 object detection
263 篇 image recognitio...
260 篇 application soft...
249 篇 lighting
248 篇 computational mo...
238 篇 image reconstruc...

机构

44 篇 microsoft resear...
27 篇 department of co...
21 篇 swiss fed inst t...
21 篇 school of comput...
21 篇 carnegie mellon ...
20 篇 department of co...
19 篇 swiss fed inst t...
18 篇 department of co...
17 篇 department of in...
17 篇 the robotics ins...
17 篇 institute of com...
16 篇 univ sci & techn...
16 篇 robotics institu...
15 篇 tsinghua univ pe...
14 篇 department of el...
14 篇 center for autom...
14 篇 school of comput...
14 篇 school of comput...
13 篇 univ maryland co...
13 篇 microsoft resear...

作者

39 篇 timofte radu
28 篇 s.k. nayar
25 篇 huang thomas s.
24 篇 xiaoou tang
22 篇 t. kanade
20 篇 chellappa rama
20 篇 t.s. huang
19 篇 van gool luc
19 篇 nayar shree k.
19 篇 t. darrell
17 篇 a.k. jain
17 篇 a. zisserman
17 篇 heung-yeung shum
17 篇 jain anil k.
17 篇 zisserman andrew
16 篇 g. healey
16 篇 torralba antonio
16 篇 l. van gool
15 篇 ying wu
15 篇 m. shah

语言

6,668 篇 英文
8 篇 中文
2 篇 其他

检索条件"任意字段=2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2003"

共 6678 条记录，以下是501-510 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：

Identity Preserving Loss for Learned Image Compression

Identity Preserving Loss for Learned Image Compression

引用

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

作者： Xiao, Jiuhong Aggarwal, Lavisha Banerjee, Prithviraj Aggarwal, Manoj Medioni, Gerard NYU 550 1St Ave New York NY 10012 USA Amazon Seattle WA 98109 USA

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Deep learning model inference on embedded devices is challenging due to the limited availability of computation resources. A popular alternative is to perform model inference on the cloud, which requires transmitting images from the embedded device to the cloud. Image compression techniques are commonly employed in such cloud-based architectures to reduce transmission latency over low bandwidth networks. This work proposes an end-to-end image compression framework that learns domain-specific features to achieve higher compression ratios than standard HEVC/JPEG compression techniques while maintaining accuracy on downstream tasks (e.g., recognition). Our framework does not require fine-tuning of the downstream task, which allows us to drop-in any off-the-shelf downstream task model without retraining. We choose faces as an application domain due to the ready availability of datasets and off-the-shelf recognition models as representative downstream tasks. We present a novel Identity Preserving Reconstruction (IPR) loss function which achieves Bits-Per-Pixel (BPP) values that are similar to 38% and similar to 42% of CRF-23 HEVC compression for LFW (low-resolution) and CelebA-HQ (high-resolution) datasets, respectively, while maintaining parity in recognition accuracy. The superior compression ratio is achieved as the model learns to retain the domain-specific features (e.g., facial features) while sacrificing details in the background. Furthermore, images reconstructed by our proposed compression model are robust to changes in downstream model architectures. We show at-par recognition performance on the LFW dataset with an unseen recognition model while retaining a lower BPP value of similar to 38% of CRF-23 HEVC compression.

关键词： Image coding Image recognition Face recognition Computational modeling Intellectual property computer architecture Robustness

来源：评论

学校读者我要写书评

暂无评论

DRT: A Lightweight Single Image Deraining Recursive Transformer

DRT: A Lightweight Single Image Deraining Recursive Transfor...

引用

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

作者： Liang, Yuanchu Anwar, Saeed Liu, Yang Australian Natl Univ Canberra Australia CSIRO Data61 Sydney Australia

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Over parameterization is a common technique in deep learning to help models learn and generalize sufficiently to the given task;nonetheless, this often leads to enormous network structures and consumes considerable computing resources during training. Recent powerful transformer-based deep learning models on vision tasks usually have heavy parameters and bear training difficulty. However, many dense-prediction low-level computer vision tasks, such as rain streak removing, often need to be executed on devices with limited computing power and memory in practice. Hence, we introduce a recursive local window-based self-attention structure with residual connections and propose deraining a recursive transformer (DRT), which enjoys the superiority of the transformer but requires a small amount of computing resources. In particular, through recursive architecture, our proposed model uses only similar to 1.3% of the number of parameters of the current best performing model in deraining while exceeding the state-of-the-art methods on the Rain100L benchmark by at least 0.33 dB. Ablation studies also investigate the impact of recursions on derain outcomes. Moreover, since the model contains no deliberate design for deraining, it can also be applied to other image restoration tasks. Our experiment shows that it can achieve competitive results on desnowing. The source code and pretrained model can be found at https://***/YC-Liang/DRT.

关键词： Training Deep learning computer vision Rain Computational modeling computer architecture Transformers

来源：评论

学校读者我要写书评

暂无评论

Transformer Decoders with MultiModal Regularization for Cross-Modal Food Retrieval

Transformer Decoders with MultiModal Regularization for Cros...

引用

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

作者： Shukor, Mustafa Couairon, Guillaume Grechka, Asya Cord, Matthieu Sorbonne Univ Paris France Meta AI New York NY USA Meero Paris France Valeoai Paris France

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Cross-modal image-recipe retrieval has gained significant attention in recent years. Most work focuses on improving cross-modal embeddings using unimodal encoders, that allow for efficient retrieval in large-scale databases, leaving aside cross-attention between modalities which is more computationally expensive. We propose a new retrieval framework, T-Food (Transformer Decoders with MultiModal Regularization for Cross-Modal Food Retrieval) that exploits the interaction between modalities in a novel regularization scheme, while using only unimodal encoders at test time for efficient retrieval. We also capture the intra-dependencies between recipe entities with a dedicated recipe encoder, and propose new variants of triplet losses with dynamic margins that adapt to the difficulty of the task. Finally, we leverage the power of the recent vision and Language Pretraining (VLP) models such as CLIP for the image encoder. Our approach outperforms existing approaches by a large margin on the Recipe1M dataset. Specifically, we achieve absolute improvements of 8.1 % (72.6 R@1) and +10.9 % (44.6 R@1) on the 1k and 10k test sets respectively. The code is available here:https://***/mshukor/TFood.

关键词： computer vision Databases conferences Computational modeling Transfer learning Transformers Decoding

来源：评论

学校读者我要写书评

暂无评论

From Less to More: Spectral Splitting and Aggregation Network for Hyperspectral Face Super-Resolution

From Less to More: Spectral Splitting and Aggregation Networ...

引用

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

作者： Jiang, Junjun Wang, Chenyang Liu, Xianming Jiang, Kui Ma, Jiayi Harbin Inst Technol Harbin Peoples R China Wuhan Univ Wuhan Peoples R China

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

High-resolution (HR) hyperspectral face image plays an important role in face related computer vision tasks under uncontrolled conditions, such as low-light environment and spoofing attacks. However, the dense spectral bands of hyperspectral face images come at the cost of limited amount of photons reached a narrow spectral window on average, which greatly reduces the spatial resolution of hyperspectral face images. In this paper, we investigate how to adapt the deep learning techniques to hyperspectral face image super-resolution (HFSR), especially when the training samples are very limited. Benefiting from the amount of spectral bands, in which each band can be seen as an image, we present a spectral splitting and aggregation network (SSANet) for HFSR with limited training samples. In the shallow layers, we split the hyperspectral image into different spectral groups. Then, we gradually aggregate the neighbor bands at deeper layers to exploit spectral correlations. By this spectral splitting and aggregation strategy (SSAS), we can divide the original hyperspectral image into multiple samples (from less to more) to support the efficient training of the network and effectively exploit the spectral correlations among spectrum. To cope with the challenge of small training sample size (S3) problem, we propose to expand the training samples by a self-representation model and symmetry-induced augmentation. Experiments show that SSANet can well model the joint correlations of spatial and spectral information. By expanding the training samples, SSANet can effectively alleviate the S3 problem.

关键词： Training computer vision Correlation Face recognition Superresolution Task analysis Spatial resolution

来源：评论

学校读者我要写书评

暂无评论

ActAR: Actor-Driven Pose Embeddings for Video Action recognition

ActAR: Actor-Driven Pose Embeddings for Video Action Recogni...

引用

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

作者： Lamghari, Soufiane Bilodeau, Guillaume-Alexandre Saunier, Nicolas Polytech Montreal Dept Comp & Software Engn LITIV Lab Montreal PQ Canada Polytech Montreal Dept Civil Geol & Min Engn Montreal PQ Canada

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Human action recognition (HAR) in videos is one of the core tasks of video understanding. Based on video sequences, the goal is to recognize actions performed by humans. While HAR has received much attention in the visible spectrum, action recognition in infrared videos is little studied. Accurate recognition of human actions in the infrared domain is a highly challenging task because of the redundant and indistinguishable texture features present in the sequence. Furthermore, in some cases, challenges arise from the irrelevant information induced by the presence of multiple active persons not contributing to the actual action of interest. Therefore, most existing methods consider a standard paradigm that does not take into account these challenges, which is in some part due to the ambiguous definition of the recognition task in some cases. In this paper, we propose a new method that simultaneously learns to recognize efficiently human actions in the infrared spectrum, while automatically identifying the key-actors performing the action without using any prior knowledge or explicit annotations. Our method is composed of three stages. In the first stage, optical flow-based key-actor identification is performed. Then for each key-actor, we estimate key-poses that will guide the frame selection process. A scale-invariant encoding process along with embedded pose filtering are performed in order to enhance the quality of action representations. Experimental results on InfAR dataset show that our proposed model achieves promising recognition performance and learns useful action representations.

关键词： Training Optical filters Filtering Annotations Computational modeling Video sequences pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Event Transformer. A sparse-aware solution for efficient event data processing

Event Transformer. A sparse-aware solution for efficient eve...

引用

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

作者： Sabater, Alberto Montesano, Luis Murillo, Ana C. Univ Zaragoza DIIS I3A Zaragoza Spain Bitbrain Technol Zaragoza Spain

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Event cameras are sensors of great interest for many applications that run in low-resource and challenging environments. They log sparse illumination changes with high temporal resolution and high dynamic range, while they present minimal power consumption. However, top-performing methods often ignore specific event-data properties, leading to the development of generic but computationally expensive algorithms. Efforts toward efficient solutions usually do not achieve top-accuracy results for complex tasks. This work proposes a novel framework, Event Transformer (EvT)(1), that effectively takes advantage of event-data properties to be highly efficient and accurate. We introduce a new patch-based event representation and a compact transformer-like architecture to process it. EvT is evaluated on different event-based benchmarks for action and gesture recognition. Evaluation results show better or comparable accuracy to the state-of-the-art while requiring significantly less computation resources, which makes EvT able to work with minimal latency both on GPU and CPU.

关键词： Power demand Graphics processing units Gesture recognition computer architecture Benchmark testing Transformers Data processing

来源：评论

学校读者我要写书评

暂无评论

Is Neuron Coverage Needed to Make Person Detection More Robust?

Is Neuron Coverage Needed to Make Person Detection More Robu...

引用

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

作者： Pavlitskaya, Svetlana Yikmis, Siyar Zoellner, J. Marius FZI Res Ctr Informat Technol D-76131 Karlsruhe Germany

ISBN: (纸本)9781665487399

The growing use of deep neural networks (DNNs) in safety- and security-critical areas like autonomous driving raises the need for their systematic testing. Coverage-guided testing (CGT) is an approach that applies mutation or fuzzing according to a predefined coverage metric to find inputs that cause misbehavior. With the introduction of a neuron coverage metric, CGT has also recently been applied to DNNs. In this work, we apply CGT to the task of person detection in crowded scenes. The proposed pipeline uses YOLOv3 for person detection and includes finding DNN bugs via sampling and mutation, and subsequent DNN retraining on the updated training set. To be a bug, we require a mutated image to cause a significant performance drop compared to a clean input. In accordance with the CGT, we also consider an additional requirement of increased coverage in the bug definition. In order to explore several types of robustness, our approach includes natural image transformations, corruptions, and adversarial examples generated with the Daedalus attack. The proposed framework has uncovered several thousand cases of incorrect DNN behavior. The relative change in mAP performance of the retrained models reached on average between 26.21% and 64.24% for different robustness types. However, we have found no evidence that the investigated coverage metrics can be advantageously used to improve robustness.

关键词： Measurement Deep learning computer vision computer bugs Neurons Neural networks Training data

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

Emphasizing Complementary Samples for Non-literal Cross-modal Retrieval

Emphasizing Complementary Samples for Non-literal Cross-moda...

引用

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

作者： Thomas, Christopher Kovashka, Adriana Columbia Univ New York NY 10027 USA Univ Pittsburgh Pittsburgh PA 15260 USA

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Existing cross-modal retrieval methods assume a straightforward relationship where images and text contain portrayals or mentions of the same objects. In contrast, real-world image-text pairs (e.g. an image and its caption in a news article) often feature more complex relations. Importantly, not all image-text pairs have the same relationship: in some pairs, image and text may be more closely aligned, while others are more loosely aligned hence complementary. In order to ensure the model learns a semantically robust space which captures nuanced relationships, care must be taken that loosely-aligned image-text pairs have a strong enough impact on learning. In this paper, we propose a novel approach to prioritize loosely-aligned samples. Unlike prior sample weighting methods, ours relies on estimating to what extent semantic similarity is preserved in the separate channels (images/text) in the learned multimodal space. In particular, the image-text pair weights in the retrieval loss focus learning towards samples from diverse or discrepant neighborhoods: samples where images or text that were close in a semantic space, are distant in the cross-modal space (diversity), or where neighbor relations are asymmetric (discrepancy). Experiments on three challenging datasets exhibiting abstract image-text relations, as well as COCO, demonstrate significant performance gains compared to recent state-of-the-art models and sample weighting approaches.

关键词： computer vision Spatial diversity conferences Semantics Channel estimation Performance gain Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Estimating Multiple Emotion Descriptors by Separating Description and Inference

Estimating Multiple Emotion Descriptors by Separating Descri...

引用

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

作者： Deng, Didan Shi, Bertram E. Hong Kong Univ Sci & Technol Dept Elect & Comp Engn Kowloon Hong Kong Peoples R China

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

To describe complex emotional states, psychologists have proposed multiple emotion descriptors: sparse descriptors like facial action units, continuous descriptors like valence and arousal, and discrete class descriptors like the expressions of happiness and anger. According to Cohn et al. [1], facial action units are sign vehicles that convey the emotion message, while discrete or continuous emotion descriptors are the messages perceived by observers. They differ in their focuses. Sign vehicles focus on describing facial behavior. Emotion messages focus on an observer's inference about the underlying state of the subject from facial behavior. We describe a novel architecture for multiple emotion descriptor estimation that incorporates this prior knowledge about the differences between descriptive labels (sign vehicles, like facial action units) and inferential labels (emotion messages like discrete emotion expressions, valence, and arousal). In our multi-level architecture, a common set of low-level features of facial regions are fed into two separate branches: one for descriptive labels and the other for inferential labels. The differences between these two branches reflects the differences between the two types of labels. Sign vehicles are typically more specific and spatially localized. Emotion messages are reflected across the entire face. Our experiments on the ABAW3 challenge [9] dataset demonstrate this approach outperforms all other submitted approaches to multi-task learning.

关键词： Space vehicles Representation learning Visualization Emotion recognition Gold Face recognition Psychology

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 << < 47 48 49 50 51 52 53 54 55 56 > >>

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：