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

11,886 篇 会议
5 篇 期刊文献

馆藏范围

11,891 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

8,060 篇 工学
- 7,618 篇 计算机科学与技术...
- 796 篇 机械工程
- 688 篇 电气工程
- 361 篇 软件工程
- 228 篇 控制科学与工程
- 41 篇 光学工程
- 19 篇 生物工程
- 17 篇 信息与通信工程
- 12 篇 生物医学工程（可授...
- 7 篇 交通运输工程
- 6 篇 电子科学与技术（可...
- 6 篇 建筑学
- 5 篇 仪器科学与技术
- 5 篇 化学工程与技术
- 5 篇 安全科学与工程
- 4 篇 土木工程
3,347 篇 医学
- 3,346 篇 临床医学
- 4 篇 基础医学(可授医学...
- 4 篇 公共卫生与预防医...
254 篇 理学
- 198 篇 系统科学
- 32 篇 物理学
- 21 篇 生物学
- 19 篇 数学
- 9 篇 统计学（可授理学、...
- 7 篇 化学
17 篇 管理学
- 12 篇 管理科学与工程(可...
- 7 篇 图书情报与档案管...
- 5 篇 工商管理
3 篇 法学
- 3 篇 社会学
3 篇 教育学
- 3 篇 教育学
2 篇 农学
1 篇 经济学
1 篇 军事学

主题

5,633 篇 computer vision
2,668 篇 training
2,203 篇 pattern recognit...
1,745 篇 computational mo...
1,504 篇 visualization
1,360 篇 three-dimensiona...
1,082 篇 semantics
1,001 篇 benchmark testin...
990 篇 codes
959 篇 computer archite...
892 篇 deep learning
777 篇 conferences
754 篇 task analysis
716 篇 feature extracti...
560 篇 transformers
536 篇 face recognition
526 篇 neural networks
495 篇 object detection
490 篇 image segmentati...
472 篇 cameras

机构

174 篇 univ sci & techn...
145 篇 carnegie mellon ...
144 篇 univ chinese aca...
143 篇 tsinghua univ pe...
134 篇 chinese univ hon...
110 篇 zhejiang univ pe...
100 篇 peng cheng lab p...
99 篇 swiss fed inst t...
91 篇 tsinghua univers...
90 篇 shanghai ai lab ...
84 篇 shanghai jiao to...
83 篇 zhejiang univers...
82 篇 sensetime res pe...
81 篇 stanford univ st...
79 篇 university of sc...
79 篇 univ hong kong p...
79 篇 tech univ munich...
76 篇 alibaba grp peop...
76 篇 australian natl ...
75 篇 peng cheng labor...

作者

74 篇 timofte radu
64 篇 van gool luc
50 篇 zhang lei
43 篇 yang yi
37 篇 loy chen change
36 篇 tao dacheng
32 篇 zhou jie
31 篇 chen chen
30 篇 liu yang
30 篇 tian qi
30 篇 zha zheng-jun
29 篇 sun jian
28 篇 li xin
27 篇 qi tian
27 篇 luc van gool
26 篇 vasconcelos nuno
25 篇 liu xiaoming
25 篇 darrell trevor
24 篇 zheng wei-shi
24 篇 luo ping

语言

11,850 篇 英文
40 篇 其他
1 篇 中文

检索条件"任意字段=2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024"

共 11891 条记录，以下是1251-1260 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：

Unsupervised Contour Tracking of Live Cells by Mechanical and Cycle Consistency Losses

Unsupervised Contour Tracking of Live Cells by Mechanical an...

引用

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

作者： Jang, Junbong Lee, Kwonmoo Kim, Tae-Kyun Korea Adv Inst Sci & Technol Seoul South Korea Harvard Med Sch Boston Childrens Hosp Boston MA 02115 USA Imperial Coll London London England

ISBN: (纸本)9798350301298

Analyzing the dynamic changes of cellular morphology is important for understanding the various functions and characteristics of live cells, including stem cells and metastatic cancer cells. To this end, we need to track all points on the highly deformable cellular contour in every frame of live cell video. Local shapes and textures on the contour are not evident, and their motions are complex, often with expansion and contraction of local contour features. The prior arts for optical flow or deep point set tracking are unsuited due to the fluidity of cells, and previous deep contour tracking does not consider point correspondence. We propose the first deep learning-based tracking of cellular (or more generally viscoelastic materials) contours with point correspondence by fusing dense representation between two contours with cross attention. Since it is impractical to manually label dense tracking points on the contour, unsupervised learning comprised of the mechanical and cyclical consistency losses is proposed to train our contour tracker. The mechanical loss forcing the points to move perpendicular to the contour effectively helps out. For quantitative evaluation, we labeled sparse tracking points along the contour of live cells from two live cell datasets taken with phase contrast and confocal fluorescence microscopes. Our contour tracker quantitatively outperforms compared methods and produces qualitatively more favorable results. Our code and data are publicly available at https://***/JunbongJang/ contour-tracking/

关键词： cell microscopy Medical and biological vision

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Semantic Correspondence Networks for Video Paragraph Grounding

Hierarchical Semantic Correspondence Networks for Video Para...

引用

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

作者： Tan, Chaolei Lin, Zihang Hu, Jian-Fang Zheng, Wei-Shi Lai, Jianhuang Sun Yat Sen Univ Sch Comp Sci & Engn Guangzhou Peoples R China Guangdong Prov Key Lab Informat Secur Technol Guangzhou Peoples R China Minist Educ Key Lab Machine Intelligence & Adv Comp Beijing Peoples R China

ISBN: (纸本)9798350301298

Video Paragraph Grounding (VPG) is an essential yet challenging task in vision-language understanding, which aims to jointly localize multiple events from an untrimmed video with a paragraph query description. One of the critical challenges in addressing this problem is to comprehend the complex semantic relations between visual and textual modalities. Previous methods focus on modeling the contextual information between the video and text from a single-level perspective (i.e., the sentence level), ignoring rich visual-textual correspondence relations at different semantic levels, e.g., the video-word and video-paragraph correspondence. To this end, we propose a novel Hierarchical Semantic Correspondence Network (HSCNet), which explores multi-level visual-textual correspondence by learning hierarchical semantic alignment and utilizes dense supervision by grounding diverse levels of queries. Specifically, we develop a hierarchical encoder that encodes the multi-modal inputs into semantics-aligned representations at different levels. To exploit the hierarchical semantic correspondence learned in the encoder for multi-level supervision, we further design a hierarchical decoder that progressively performs finer grounding for lower-level queries conditioned on higher-level semantics. Extensive experiments demonstrate the effectiveness of HSCNet and our method significantly outstrips the state-of-the-arts on two challenging benchmarks, i.e., ActivityNet-Captions and TACoS.

关键词： and reasoning language vision

来源：评论

学校读者我要写书评

暂无评论

FCC: Feature Clusters Compression for Long-Tailed Visual recognition

FCC: Feature Clusters Compression for Long-Tailed Visual Rec...

引用

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

作者： Li, Jian Meng, Ziyao Shi, Daqian Song, Rui Diao, Xiaolei Wang, Jingwen Xu, Hao Jilin Univ Changchun Peoples R China Univ Minho Braga Portugal Univ Toronto Toronto ON Canada

ISBN: (纸本)9798350301298

Deep Neural Networks (DNNs) are rather restrictive in long-tailed data, since they commonly exhibit an under-representation for minority classes. Various remedies have been proposed to tackle this problem from different perspectives, but they ignore the impact of the density of Backbone Features (BFs) on this issue. Through representation learning, DNNs can map BFs into dense clusters in feature space, while the features of minority classes often show sparse clusters. In practical applications, these features are discretely mapped or even cross the decision boundary resulting in misclassification. Inspired by this observation, we propose a simple and generic method, namely Feature Clusters Compression (FCC), to increase the density of BFs by compressing backbone feature clusters. The proposed FCC can be easily achieved by only multiplying original BFs by a scaling factor in training phase, which establishes a linear compression relationship between the original and multiplied features, and forces DNNs to map the former into denser clusters. In test phase, we directly feed original features without multiplying the factor to the classifier, such that BFs of test samples are mapped closer together and do not easily cross the decision boundary. Meanwhile, FCC can be friendly combined with existing long-tailed methods and further boost them. We apply FCC to numerous state-of-the-art methods and evaluate them on widely used longtailed benchmark datasets. Extensive experiments fully verify the effectiveness and generality of our method. Code is available at https://***/lijian16/FCC.

关键词： detection recognition: Categorization retrieval

来源：评论

学校读者我要写书评

暂无评论

PHA: Patch-wise High-frequency Augmentation for Transformer-based Person Re-identification

PHA: Patch-wise High-frequency Augmentation for Transformer-...

引用

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

作者： Zhang, Guiwei Zhang, Yongfei Zhang, Tianyu Li, Bo Pu, Shiliang Beihang Univ Beijing Key Lab Digital Media Sch Comp Sci & Engn Beijing Peoples R China Beihang Univ State Key Lab Virtual Real Technol & Syst Beijing Peoples R China Pengcheng Lab Shenzhen Peoples R China Hikvis Res Inst Hangzhou Peoples R China

ISBN: (纸本)9798350301298

Although recent studies empirically show that injecting Convolutional Neural Networks (CNNs) into vision Transformers (ViTs) can improve the performance of person re-identification, the rationale behind it remains elusive. From a frequency perspective, we reveal that ViTs perform worse than CNNs in preserving key high-frequency components (e.g, clothes texture details) since high-frequency components are inevitably diluted by low-frequency ones due to the intrinsic Self-Attention within ViTs. To remedy such inadequacy of the ViT, we propose a Patch-wise High-frequency Augmentation (PHA) method with two core designs. First, to enhance the feature representation ability of high-frequency components, we split patches with high-frequency components by the Discrete Haar Wavelet Transform, then empower the ViT to take the split patches as auxiliary input. Second, to prevent high-frequency components from being diluted by low-frequency ones when taking the entire sequence as input during network optimization, we propose a novel patch-wise contrastive loss. From the view of gradient optimization, it acts as an implicit augmentation to improve the representation ability of key high-frequency components. This benefits the ViT to capture key high-frequency components to extract discriminative person representations. PHA is necessary during training and can be removed during inference, without bringing extra complexity. Extensive experiments on widely-used ReID datasets validate the effectiveness of our method.

关键词： detection recognition: Categorization retrieval

来源：评论

学校读者我要写书评

暂无评论

Holistic Representation Learning for Multitask Trajectory Anomaly Detection

Holistic Representation Learning for Multitask Trajectory An...

引用

ieee/cvf Winter conference on Applications of computer vision (WACV)

作者： Stergiou, Alexandros De Weerdt, Brent Deligiannis, Nikos Vrije Univ Brussel Brussels Belgium IMEC Leuven Belgium

ISBN: (纸本)9798350318920;9798350318937

Video anomaly detection deals with the recognition of abnormal events in videos. Apart from the visual signal, video anomaly detection has also been addressed with the use of skeleton sequences. We propose a holistic representation of skeleton trajectories to learn expected motions across segments at different times. Our approach uses multitask learning to reconstruct any continuous unobserved temporal segment of the trajectory allowing the extrapolation of past or future segments and the interpolation of inbetween segments. We use an end-to-end attention-based encoder-decoder. We encode temporally occluded trajectories, jointly learn latent representations of the occluded segments, and reconstruct trajectories based on expected motions across different temporal segments. Extensive experiments on three trajectory-based video anomaly detection datasets show the advantages and effectiveness of our approach with state-of-the-art results on anomaly detection in skeleton trajectories(dagger).

关键词： Algorithms Video recognition and understanding

来源：评论

学校读者我要写书评

暂无评论

Improving vision-and-Language Navigation by Generating Future-View Image Semantics

Improving Vision-and-Language Navigation by Generating Futur...

引用

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

作者： Li, Jialu Bansal, Mohit UNC Chapel Hill Chapel Hill NC 27599 USA

ISBN: (纸本)9798350301298

vision-and-Language Navigation (VLN) is the task that requires an agent to navigate through the environment based on natural language instructions. At each step, the agent takes the next action by selecting from a set of navigable locations. In this paper, we aim to take one step further and explore whether the agent can benefit from generating the potential future view during navigation. Intuitively, humans will have an expectation of how the future environment will look like, based on the natural language instructions and surrounding views, which will aid correct navigation. Hence, to equip the agent with this ability to generate the semantics of future navigation views, we first propose three proxy tasks during the agent's in-domain pre-training: Masked Panorama Modeling (MPM), Masked Trajectory Modeling (MTM), and Action Prediction with Image Generation (APIG). These three objectives teach the model to predict missing views in a panorama (MPM), predict missing steps in the full trajectory (MTM), and generate the next view based on the full instruction and navigation history (APIG), respectively. We then fine-tune the agent on the VLN task with an auxiliary loss that minimizes the difference between the view semantics generated by the agent and the ground truth view semantics of the next step. Empirically, our VLN-SIG achieves the new state-of-the-art on both Room-to-Room dataset and CVDN dataset. We further show that our agent learns to fill in missing patches in future views qualitatively, which brings more interpretability over agents' predicted actions. Lastly, we demonstrate that learning to predict future view semantics also enables the agent to have better performance on longer paths.

关键词： language reasoning vision

来源：评论

学校读者我要写书评

暂无评论

Re-thinking Model Inversion Attacks Against Deep Neural Networks

Re-thinking Model Inversion Attacks Against Deep Neural Netw...

引用

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

作者： Nguyen, Ngoc-Bao Chandrasegaran, Keshigeyan Abdollahzadeh, Milad Cheung, Ngai-Man SUTD Singapore Singapore

ISBN: (纸本)9798350301298

Model inversion (MI) attacks aim to infer and reconstruct private training data by abusing access to a model. MI attacks have raised concerns about the leaking of sensitive information (e.g. private face images used in training a face recognition system). Recently, several algorithms for MI have been proposed to improve the attack performance. In this work, we revisit MI, study two fundamental issues pertaining to all state-of-the-art (SOTA) MI algorithms, and propose solutions to these issues which lead to a significant boost in attack performance for all SOTA MI. In particular, our contributions are two-fold: 1) We analyze the optimization objective of SOTA MI algorithms, argue that the objective is sub-optimal for achieving MI, and propose an improved optimization objective that boosts attack performance significantly. 2) We analyze "MI overfitting", show that it would prevent reconstructed images from learning semantics of training data, and propose a novel "model augmentation" idea to overcome this issue. Our proposed solutions are simple and improve all SOTA MI attack accuracy significantly. E.g., in the standard CelebA benchmark, our solutions improve accuracy by 11.8% and achieve for the first time over 90% attack accuracy. Our findings demonstrate that there is a clear risk of leaking sensitive information from deep learning models. We urge serious consideration to be given to the privacy implications. Our code, demo, and models are available at https:// ***/rethinking_model_inversion_attacks/.

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

A New Path: Scaling vision-and-Language Navigation with Synthetic Instructions and Imitation Learning

A New Path: Scaling Vision-and-Language Navigation with Synt...

引用

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

作者： Kamath, Aishwarya Anderson, Peter Wang, Su Koh, Jing Yu Ku, Alexander Waters, Austin Yang, Yinfei Baldridge, Jason Parekh, Zarana NYU New York NY 10003 USA Google Res Mountain View CA 94043 USA Carnegie Mellon Univ Pittsburgh PA 15213 USA Apple Cupertino CA USA

ISBN: (纸本)9798350301298

Recent studies in vision-and-Language Navigation (VLN) train RL agents to execute natural-language navigation instructions in photorealistic environments, as a step towards robots that can follow human instructions. However, given the scarcity of human instruction data and limited diversity in the training environments, these agents still struggle with complex language grounding and spatial language understanding. Pretraining on large text and image-text datasets from the web has been extensively explored but the improvements are limited. We investigate large-scale augmentation with synthetic instructions. We take 500+ indoor environments captured in densely-sampled 360. panoramas, construct navigation trajectories through these panoramas, and generate a visually-grounded instruction for each trajectory using Marky [63], a high-quality multilingual navigation instruction generator. We also synthesize image observations from novel viewpoints using an image-to-image GAN [27]. The resulting dataset of 4.2M instruction-trajectory pairs is two orders of magnitude larger than existing human-annotated datasets, and contains a wider variety of environments and viewpoints. To efficiently leverage data at this scale, we train a simple transformer agent with imitation learning. On the challenging RxR dataset, our approach outperforms all existing RL agents, improving the state-of-the-art NDTW from 71.1 to 79.1 in seen environments, and from 64.6 to 66.8 in unseen test environments. Our work points to a new path to improving instruction-following agents, emphasizing large-scale training on near-human quality synthetic instructions.

关键词： language reasoning vision

来源：评论

学校读者我要写书评

暂无评论

Contrastive Learning for Multi-Object Tracking with Transformers

Contrastive Learning for Multi-Object Tracking with Transfor...

引用

ieee/cvf Winter conference on Applications of computer vision (WACV)

作者： De Plaen, Pierre-Francois Marinello, Nicola Proesmans, Marc Tuytelaars, Tinne Van Gool, Luc Katholieke Univ Leuven ESAT PSI Leuven Belgium Swiss Fed Inst Technol CVL Zurich Switzerland TRACE Vzw Leuven Belgium

ISBN: (纸本)9798350318920;9798350318937

The DEtection TRansformer (DETR) opened new possibilities for object detection by modeling it as a translation task: converting image features into object-level representations. Previous works typically add expensive modules to DETR to perform Multi-Object Tracking (MOT), resulting in more complicated architectures. We instead show how DETR can be turned into a MOT model by employing an instance-level contrastive loss, a revised sampling strategy and a lightweight assignment method. Our training scheme learns object appearances while preserving detection capabilities and with little overhead. Its performance surpasses the previous state-of-the-art by +2.6 mMOTA on the challenging BDD100K dataset and is comparable to existing transformer-based methods on the MOT17 dataset.

关键词： Algorithms Algorithms Applications Autonomous Driving Image recognition and understanding Video recognition and understanding

来源：评论

学校读者我要写书评

暂无评论

MAGVLT: Masked Generative vision-and-Language Transformer

MAGVLT: Masked Generative Vision-and-Language Transformer

引用

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

作者： Kim, Sungwoong Jo, Daejin Lee, Donghoon Kim, Jongmin Korea Univ Dept Artificial Intelligence Seoul South Korea Kakao Brain Seongnam South Korea

ISBN: (纸本)9798350301298

While generative modeling on multimodal image-text data has been actively developed with large-scale paired datasets, there have been limited attempts to generate both image and text data by a single model rather than a generation of one fixed modality conditioned on the other modality. In this paper, we explore a unified generative vision-and-language (VL) model that can produce both images and text sequences. Especially, we propose a generative VL transformer based on the non-autoregressive mask prediction, named MAGVLT, and compare it with an autoregressive generative VL transformer (ARGVLT). In comparison to ARGVLT, the proposed MAGVLT enables bidirectional context encoding, fast decoding by parallel token predictions in an iterative refinement, and extended editing capabilities such as image and text infilling. For rigorous training of our MAGVLT with image-text pairs from scratch, we combine the image-to-text, text-to-image, and joint image-and-text mask prediction tasks. Moreover, we devise two additional tasks based on the step-unrolled mask prediction and the selective prediction on the mixture of two image-text pairs. Experimental results on various downstream generation tasks of VL benchmarks show that our MAGVLT outperforms ARGVLT by a large margin even with significant inference speedup. Particularly, MAGVLT achieves competitive results on both zero-shot image-to-text and text-to-image generation tasks from MS-COCO by one moderatesized model (fewer than 500M parameters) even without the use of monomodal data and networks.

关键词： Multi-modal learning

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 << < 122 123 124 125 126 127 128 129 130 131 > >>

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：