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

23,015 篇 会议
126 册 图书
93 篇 期刊文献

馆藏范围

23,233 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

13,637 篇 工学
- 11,122 篇 计算机科学与技术...
- 3,490 篇 软件工程
- 2,446 篇 机械工程
- 1,719 篇 光学工程
- 1,078 篇 电气工程
- 1,024 篇 控制科学与工程
- 791 篇 信息与通信工程
- 412 篇 仪器科学与技术
- 352 篇 生物工程
- 251 篇 生物医学工程（可授...
- 198 篇 电子科学与技术（可...
- 114 篇 化学工程与技术
- 110 篇 安全科学与工程
- 100 篇 测绘科学与技术
- 89 篇 交通运输工程
- 88 篇 建筑学
- 84 篇 土木工程
3,496 篇 医学
- 3,482 篇 临床医学
- 81 篇 基础医学(可授医学...
3,249 篇 理学
- 1,943 篇 物理学
- 1,645 篇 数学
- 564 篇 统计学（可授理学、...
- 500 篇 生物学
- 249 篇 系统科学
- 108 篇 化学
525 篇 管理学
- 313 篇 图书情报与档案管...
- 227 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...
67 篇 法学
- 64 篇 社会学
38 篇 农学
28 篇 教育学
22 篇 经济学
10 篇 军事学
4 篇 文学

主题

10,190 篇 computer vision
3,972 篇 pattern recognit...
3,005 篇 training
2,007 篇 computational mo...
1,818 篇 visualization
1,816 篇 cameras
1,516 篇 feature extracti...
1,481 篇 shape
1,455 篇 three-dimensiona...
1,438 篇 image segmentati...
1,287 篇 robustness
1,206 篇 computer archite...
1,155 篇 semantics
1,147 篇 conferences
1,107 篇 layout
1,093 篇 computer science
1,089 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...
106 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...
79 篇 university of ch...
77 篇 shanghai ai lab ...
74 篇 shanghai jiao to...
69 篇 national laborat...
67 篇 microsoft res as...
67 篇 alibaba grp peop...
64 篇 adobe research
60 篇 peking univ peop...
60 篇 tsinghua univ pe...
59 篇 univ oxford oxfo...

作者

81 篇 van gool luc
73 篇 timofte radu
65 篇 zhang lei
47 篇 luc van gool
40 篇 yang yi
40 篇 li stan z.
37 篇 loy chen change
35 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
29 篇 darrell trevor
29 篇 pascal fua
29 篇 li fei-fei
28 篇 ling haibin
28 篇 li xin
28 篇 ying shan

语言

22,989 篇 英文
216 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 23234 条记录，以下是1441-1450 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：

Meta-Explore: Exploratory Hierarchical vision-and-Language Navigation Using Scene Object Spectrum Grounding

Meta-Explore: Exploratory Hierarchical Vision-and-Language N...

引用

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

作者： Hwang, Minyoung Jeong, Jaeyeon Kim, Minsoo Oh, Yoonseon Oh, Songhwai Seoul Natl Univ Elect & Comp Engn Seoul South Korea Seoul Natl Univ ASRI Seoul South Korea Hanyang Univ Dept Elect Engn Seoul South Korea Seoul Natl Univ Interdisciplinary Major Artificial Intelligence Seoul South Korea

ISBN: (纸本)9798350301298

The main challenge in vision-and-language navigation (VLN) is how to understand natural-language instructions in an unseen environment. The main limitation of conventional VLN algorithms is that if an action is mistaken, the agent fails to follow the instructions or explores unnecessary regions, leading the agent to an irrecoverable path. To tackle this problem, we propose Meta-Explore, a hierarchical navigation method deploying an exploitation policy to correct misled recent actions. We show that an exploitation policy, which moves the agent toward a well-chosen local goal among unvisited but observable states, outperforms a method which moves the agent to a previously visited state. We also highlight the demand for imagining regretful explorations with semantically meaningful clues. The key to our approach is understanding the object placements around the agent in spectral-domain. Specifically, we present a novel visual representation, called scene object spectrum (SOS), which performs category-wise 2D Fourier transform of detected objects. Combining exploitation policy and SOS features, the agent can correct its path by choosing a promising local goal. We evaluate our method in three VLN benchmarks: R2R, SOON, and REVERIE. Meta-Explore outperforms other baselines and shows significant generalization performance. In addition, local goal search using the proposed spectral-domain SOS features significantly improves the success rateby17.1% andSPLby20.6% against the state-of-the-art method of the SOON benchmark. Project page: https://***/projects/Meta-Explore/***

关键词： Robotics

来源：评论

学校读者我要写书评

暂无评论

Towards Generalisable Video Moment Retrieval: Visual-Dynamic Injection to Image-Text Pre-Training

Towards Generalisable Video Moment Retrieval: Visual-Dynamic...

引用

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

作者： Luo, Dezhao Huang, Jiabo Gong, Shaogang Jin, Hailin Liu, Yang Queen Mary Univ London London England Adobe Res San Francisco CA USA Peking Univ WICT Beijing Peoples R China

ISBN: (纸本)9798350301298

The correlation between the vision and text is essential for video moment retrieval (VMR), however, existing methods heavily rely on separate pre-training feature extractors for visual and textual understanding. Without sufficient temporal boundary annotations, it is non-trivial to learn universal video-text alignments. In this work, we explore multi-modal correlations derived from large-scale image-text data to facilitate generalisable VMR. To address the limitations of image-text pre-training models on capturing the video changes, we propose a generic method, referred to as Visual-Dynamic Injection (VDI), to empower the model's understanding of video moments. Whilst existing VMR methods are focusing on building temporal-aware video features, being aware of the text descriptions about the temporal changes is also critical but originally overlooked in pre-training by matching static images with sentences. Therefore, we extract visual context and spatial dynamic information from video frames and explicitly enforce their alignments with the phrases describing video changes (e.g. verb). By doing so, the potentially relevant visual and motion patterns in videos are encoded in the corresponding text embeddings (injected) so to enable more accurate video-text alignments. We conduct extensive experiments on two VMR benchmark datasets (Charades-STA and ActivityNet-Captions) and achieve state-of-the-art performances. Especially, VDI yields notable advantages when being tested on the out-of-distribution splits where the testing samples involve novel scenes and vocabulary.

关键词： and reasoning language vision

来源：评论

学校读者我要写书评

暂无评论

The Dialog Must Go On: Improving Visual Dialog via Generative Self-Training

The Dialog Must Go On: Improving Visual Dialog via Generativ...

引用

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

作者： Kang, Gi-Cheon Kim, Sungdong Kim, Jin-Hwa Kwak, Donghyun Zhang, Byoung-Tak Seoul Natl Univ IPAI Seoul South Korea AIIS Seoul South Korea NAVER AI Lab Seongnam South Korea NAVER Cloud CLOVA Seongnam South Korea

ISBN: (纸本)9798350301298

Visual dialog (VisDial) is a task of answering a sequence of questions grounded in an image, using the dialog history as context. Prior work has trained the dialog agents solely on VisDial data via supervised learning or leveraged pre-training on related vision-and-language datasets. This paper presents a semi-supervised learning approach for visually-grounded dialog, called Generative Self-Training (GST), to leverage unlabeled images on the Web. Specifically, GST first retrieves in-domain images through out-of-distribution detection and generates synthetic dialogs regarding the images via multimodal conditional text generation. GST then trains a dialog agent on the synthetic and the original VisDial data. As a result, GST scales the amount of training data up to an order of magnitude that of VisDial (1.2M. 12.9M QA data). For robust training of the synthetic dialogs, we also propose perplexity-based data selection and multimodal consistency regularization. Evaluation on VisDial v1.0 and v0.9 datasets shows that GST achieves new state-of-the-art results on both datasets. We further observe the robustness of GST against both visual and textual adversarial attacks. Finally, GST yields strong performance gains in the low-data regime. Code is available at https: //***/gicheonkang/gst-visdial.

关键词： and reasoning language vision

来源：评论

学校读者我要写书评

暂无评论

Lost in Compression: the Impact of Lossy Image Compression on Variable Size Object Detection within Infrared Imagery

Lost in Compression: the Impact of Lossy Image Compression o...

引用

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

作者： Bhowmik, Neelanjan Barker, Jack W. Gaus, Yona Falinie A. Breckon, Toby P. Univ Durham Dept Comp Sci Durham England Univ Durham Dept Engn Durham England

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Lossy image compression strategies allow for more efficient storage and transmission of data by encoding data to a reduced form. This is essential enable training with larger datasets on less storage-equipped environments. However, such compression can cause severe decline in performance of deep Convolution Neural Network (CNN) architectures even when mild compression is applied and the resulting compressed imagery is visually identical. In this work, we apply the lossy JPEG compression method with six discrete levels of increasing compression {95, 75, 50, 15, 10, 5} to infrared band (thermal) imagery. Our study quantitatively evaluates the affect that increasing levels of lossy compression has upon the performance of characteristically diverse object detection architectures (Cascade-RCNN, FSAF and Deformable DETR) with respect to varying sizes of objects present in the dataset. When training and evaluating on uncompressed data as a baseline, we achieve maximal mean Average Precision (mAP) of 0.823 with Cascade R-CNN across the FLIR dataset, outperforming prior work. The impact of the lossy compression is more extreme at higher compression levels (15, 10, 5) across all three CNN architectures. However, re-training models on lossy compressed imagery notably ameliorated performances for all three CNN models with an average increment of similar to 76% (at higher compression level 5). Additionally, we demonstrate the relative sensitivity of differing object areas {tiny, small, medium, large} with respect to the compression level. We show that tiny and small objects are more sensitive to compression than medium and large objects. Overall, Cascade R-CNN attains the maximal mAP across most of the object area categories.

关键词： Training Image coding Sensitivity Transform coding Object detection computer architecture Transformers

来源：评论

学校读者我要写书评

暂无评论

Bit-shrinking: Limiting Instantaneous Sharpness for Improving Post-training Quantization

Bit-shrinking: Limiting Instantaneous Sharpness for Improvin...

引用

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

作者： Lin, Chen Peng, Bo Li, Zheyang Tan, Wenming Ren, Ye Xiao, Jun Pu, Shiliang Hikvis Res Inst Hangzhou Peoples R China Zhe Jiang Univ Hangzhou Peoples R China

ISBN: (纸本)9798350301298

Post-training quantization (PTQ) is an effective compression method to reduce the model size and computational cost. However, quantizing a model into a low-bit one, e.g., lower than 4, is difficult and often results in non-negligible performance degradation. To address this, we investigate the loss landscapes of quantized networks with various bit-widths. We show that the network with more ragged loss surface, is more easily trapped into bad local minima, which mostly appears in low-bit quantization. A deeper analysis indicates, the ragged surface is caused by the injection of excessive quantization noise. To this end, we detach a sharpness term from the loss which reflects the impact of quantization noise. To smooth the rugged loss surface, we propose to limit the sharpness term small and stable during optimization. Instead of directly optimizing the target bit network, we design a self-adapted shrinking scheduler for the bit-width in continuous domain from high bit-width to the target by limiting the increasing sharpness term within a proper range. It can be viewed as iteratively adding small "instant" quantization noise and adjusting the network to eliminate its impact. Widely experiments including classification and detection tasks demonstrate the effectiveness of the Bit-shrinking strategy in PTQ. On the vision Transformer models, our INT8 and INT6 models drop within 0.5% and 1.5% Top-1 accuracy, respectively. On the traditional CNN networks, our INT4 quantized models drop within 1.3% and 3.5% Top-1 accuracy on ResNet18 and MobileNetV2 without fine-tuning, which achieves the state-of-the-art performance.

关键词： Efficient and scalable vision

来源：评论

学校读者我要写书评

暂无评论

IFSeg: Image-free Semantic Segmentation via vision-Language Model

IFSeg: Image-free Semantic Segmentation via Vision-Language ...

引用

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

作者： Yun, Sukmin Park, Seong Hyeon Seo, Paul Hongsuck Shin, Jinwoo Korea Adv Inst Sci & Technol KAIST Daejeon South Korea Google Res Seoul South Korea Mohamed Bin Zayed Univ Artificial Intelligence MB Abu Dhabi U Arab Emirates

ISBN: (纸本)9798350301298

vision-language (VL) pre-training has recently gained much attention for its transferability and flexibility in novel concepts (e.g., cross-modality transfer) across various visual tasks. However, VL-driven segmentation has been underexplored, and the existing approaches still have the burden of acquiring additional training images or even segmentation annotations to adapt a VL model to downstream segmentation tasks. In this paper, we introduce a novel image-free segmentation task where the goal is to perform semantic segmentation given only a set of the target semantic categories, but without any task-specific images and annotations. To tackle this challenging task, our proposed method, coined IFSeg, generates VL-driven artificial image-segmentation pairs and updates a pre-trained VL model to a segmentation task. We construct this artificial training data by creating a 2D map of random semantic categories and another map of their corresponding word tokens. Given that a pre-trained VL model projects visual and text tokens into a common space where tokens that share the semantics are located closely, this artificially generated word map can replace the real image inputs for such a VL model. Through an extensive set of experiments, our model not only establishes an effective baseline for this novel task but also demonstrates strong performances compared to existing methods that rely on stronger supervision, such as task-specific images and segmentation masks. Code is available at https://***/alinlab/ifseg.

关键词： grouping and shape analysis Segmentation

来源：评论

学校读者我要写书评

暂无评论

Position-guided Text Prompt for vision-Language Pre-training

Position-guided Text Prompt for Vision-Language Pre-training

引用

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

作者： Wang, Jinpeng Zhou, Pan Shou, Mike Zheng Yan, Shuicheng Sea AI Lab Singapore Singapore Natl Univ Singapore Show Lab Singapore Singapore

ISBN: (纸本)9798350301298

vision-Language Pre-Training (VLP) has shown promising capabilities to align image and text pairs, facilitating a broad variety of cross-modal learning tasks. However, we observe that VLP models often lack the visual grounding/localization capability which is critical for many downstream tasks such as visual reasoning. In this work, we propose a novel Position-guided Text Prompt (PTP) paradigm to enhance the visual grounding ability of cross-modal models trained with VLP. Specifically, in the VLP phase, PTP divides the image into N x N blocks, and identifies the objects in each block through the widely used object detector in VLP. It then reformulates the visual grounding task into a fill-in-the-blank problem given a PTP by encouraging the model to predict the objects in the given blocks or regress the blocks of a given object, e.g. filling "[P]" or "[O]" in a PTP "The block [P] has a [O]". This mechanism improves the visual grounding capability of VLP models and thus helps them better handle various downstream tasks. By introducing PTP into several state-of-the-art VLP frameworks, we observe consistently significant improvements across representative cross-modal learning model architectures and several benchmarks, e.g. zero-shot Flickr30K Retrieval (+4.8 in average recall@1) for ViLT [16] baseline, and COCO Captioning (+5.3 in CIDEr) for SOTA BLIP [19] baseline. Moreover, PTP achieves comparable results with object-detector based methods [8, 23, 45], and much faster inference speed since PTP discards its object detector for inference while the later cannot.

关键词： Multi-modal learning

来源：评论

学校读者我要写书评

暂无评论

OpenFed: A Comprehensive and Versatile Open-Source Federated Learning Framework

OpenFed: A Comprehensive and Versatile Open-Source Federated...

引用

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

作者： Chen, Dengsheng Tan, Vince Junkai Lu, Zhilin Wu, Enhua Hu, Jie Meituan China Bytedance Inc. China Tsinghua University China University of Macau China State Key Lab of Computer Science Iscas China University of Chinese Academy of Sciences China

ISBN: (纸本)9798350302493

Recent developments in Artificial Intelligence techniques have enabled their successful application across a spectrum of commercial and industrial settings. However, these techniques require large volumes of data to be aggregated in a centralized manner, forestalling their applicability to scenarios wherein the data is sensitive or the cost of data transmission is prohibitive. Federated Learning alleviates these problems by decentralizing model training, thereby removing the need for data transfer and aggregation. To advance the adoption of Federated Learning, more research and development needs to be conducted to address some important open questions. In this work, we propose OpenFed, an open-source software framework for end-to-end Federated Learning. OpenFed reduces the barrier to entry for both researchers and downstream users of Federated Learning by the targeted removal of existing pain points. For researchers, OpenFed provides a framework wherein new methods can be easily implemented and fairly evaluated against an extensive suite of benchmarks. For downstream users, OpenFed allows Federated Learning to be plugged and play within different subject-matter contexts, removing the need for deep expertise in Federated Learning. The source code of OpenFed is publicly available online at https://***/FederalLab/OpenFed. © 2023 ieee.

关键词： Data transfer

来源：评论

学校读者我要写书评

暂无评论

t-RAIN: Robust generalization under weather-aliasing label shift attacks

t-RAIN: Robust generalization under weather-aliasing label s...

引用

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

作者： Marathe, Aboli Prabhu, Sanjana Carnegie Mellon University Machine Learning Department PittsburghPA15213 United States Carnegie Mellon University Department of Electrical and Computer Engineering PittsburghPA15213 United States

ISBN: (纸本)9798350302493

In the classical supervised learning settings, classifiers are fit with the assumption of balanced label distributions and produce remarkable results on the same. In the real world, however, these assumptions often bend and in turn adversely impact model performance. Identifying bad learners in skewed target distributions is even more challenging. Thus achieving model robustness under these "label shift"settings is an important task in autonomous perception. In this paper, we analyze the impact of label shift on the task of multi-weather classification for autonomous vehicles. We use this information as a prior to better assess pedestrian detection in adverse weather. We model the classification performance as an indicator of robustness under 4 label shift scenarios and study the behavior of multiple classes of models. We propose t-RAIN a similarity mapping technique for synthetic data augmentation using large scale generative models and evaluate the performance on DAWN dataset. This mapping boosts model test accuracy by 2.1, 4.4, 1.9, 2.7 % in no-shift, fog, snow, dust shifts respectively. We present state-of-the-art pedestrian detection results on real and synthetic weather domains with best performing 82.69 AP (snow) and 62.31 AP (fog) respectively. © 2023 ieee.

关键词： Snow

来源：评论

学校读者我要写书评

暂无评论

Scalable and Accurate Self-supervised Multimodal Representation Learning without Aligned Video and Text Data

Scalable and Accurate Self-supervised Multimodal Representat...

引用

23rd ieee/CVF Winter conference on Applications of computer vision (WACV)

作者： Lialin, Vladislav Rawls, Stephen Chan, David Ghosh, Shalini Rumshisky, Anna Hamza, Wael UMass Lowell Lowell MA 01854 USA Amazon Seattle WA USA Univ Calif Berkeley Berkeley CA USA

ISBN: (纸本)9798350320565

Scaling up weakly-supervised datasets has shown to be highly effective in the image-text domain and has contributed to most of the recent state-of-the-art computer vision and multimodal neural networks. However, existing large-scale video-text datasets and mining techniques suffer from several limitations, such as the scarcity of aligned data, the lack of diversity in the data, and the difficulty of collecting aligned data. Currently popular video-text data mining approach via automatic speech recognition (ASR) used in HowTo100M provides low-quality captions that often do not refer to the video content. Other mining approaches do not provide proper language descriptions (video tags) and are biased toward short clips (alt text). In this work, we show how recent advances in image captioning allow us to pre-train high-quality video models without any parallel video-text data. We pre-train several video captioning models that are based on an OPT language model and a TimeSformer visual backbone. We fine-tune these networks on several video captioning datasets. First, we demonstrate that image captioning pseudolabels work better for pre-training than the existing HowTo100M ASR captions. Second, we show that pre-training on both images and videos produces a significantly better network (+4 CIDER on MSR-VTT) than pre-training on a single modality. Our methods are complementary to the existing pre-training or data mining approaches and can be used in a variety of settings. Given the efficacy of the pseudolabeling method, we are planning to publicly release the generated captions.

关键词： Training Representation learning Adaptation models computer vision Visualization Neural networks Optimized production technology

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 << < 141 142 143 144 145 146 147 148 149 150 > >>

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：