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

13,623 篇 工学
- 11,107 篇 计算机科学与技术...
- 3,479 篇 软件工程
- 2,444 篇 机械工程
- 1,717 篇 光学工程
- 1,076 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
3,493 篇 医学
- 3,480 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

10,187 篇 computer vision
3,967 篇 pattern recognit...
3,010 篇 training
2,002 篇 computational mo...
1,816 篇 cameras
1,814 篇 visualization
1,515 篇 feature extracti...
1,482 篇 shape
1,459 篇 three-dimensiona...
1,439 篇 image segmentati...
1,289 篇 robustness
1,203 篇 computer archite...
1,158 篇 semantics
1,148 篇 conferences
1,106 篇 layout
1,093 篇 computer science
1,088 篇 object detection
1,024 篇 benchmark testin...
967 篇 codes
921 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...
97 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...
68 篇 microsoft res as...
66 篇 alibaba grp peop...
64 篇 adobe research
60 篇 peking univ peop...
59 篇 univ oxford oxfo...
59 篇 tsinghua univ pe...

作者

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

语言

23,023 篇 英文
166 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1221-1230 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：

DepGraph: Towards Any Structural Pruning

DepGraph: Towards Any Structural Pruning

引用

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

作者： Fang, Gongfan Ma, Xinyin Song, Mingli Mi, Michael Bi Wang, Xinchao Natl Univ Singapore Singapore Singapore Zhejiang Univ Hangzhou Peoples R China Huawei Technol Ltd Shenzhen Peoples R China

ISBN: (纸本)9798350301298

Structural pruning enables model acceleration by removing structurally-grouped parameters from neural networks. However, the parameter-grouping patterns vary widely across different models, making architecture-specific pruners, which rely on manually-designed grouping schemes, non-generalizable to new architectures. In this work, we study a highly-challenging yet barely-explored task, any structural pruning, to tackle general structural pruning of arbitrary architecture like CNNs, RNNs, GNNs and Transformers. The most prominent obstacle towards this goal lies in the structural coupling, which not only forces different layers to be pruned simultaneously, but also expects all removed parameters to be consistently unimportant, thereby avoiding structural issues and significant performance degradation after pruning. To address this problem, we propose a general and fully automatic method, Dependency Graph (DepGraph), to explicitly model the dependency between layers and comprehensively group coupled parameters for pruning. In this work, we extensively evaluate our method on several architectures and tasks, including ResNe(X)t, DenseNet, MobileNet and vision transformer for images, GAT for graph, DGCNN for 3D point cloud, alongside LSTM for language, and demonstrate that, even with a simple norm-based criterion, the proposed method consistently yields gratifying performances.

关键词： Efficient and scalable vision

来源：评论

学校读者我要写书评

暂无评论

Angelic Patches for Improving Third-Party Object Detector Performance

Angelic Patches for Improving Third-Party Object Detector Pe...

引用

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

作者： Si, Wenwen Li, Shuo Park, Sangdon Lee, Insup Bastani, Osbert Univ Penn Dept Comp & Info Sci Philadelphia PA 19104 USA Georgia Inst Technol Sch Cybersecur & Privacy Atlanta GA 30332 USA

ISBN: (纸本)9798350301298

Deep learning models have shown extreme vulnerability to distribution shifts such as synthetic perturbations and spatial transformations. In this work, we explore whether we can adopt the characteristics of adversarial attack methods to help improve robustness of object detection to distribution shifts such as synthetic perturbations and spatial transformations. We study a class of realistic object detection settings wherein the target objects have control over their appearance. To this end, we propose a reversed Fast Gradient Sign Method (FGSM) to obtain these angelic patches that significantly increase the detection probability, even without pre-knowledge of the perturbations. In detail, we apply the patch to each object instance simultaneously, strengthening not only classification, but also bounding box accuracy. Experiments demonstrate the efficacy of the partial-covering patch in solving the complex bounding box problem. More importantly, the performance is also transferable to different detection models even under severe affine transformations and deformable shapes. To the best of our knowledge, we are the first object detection patch that achieves both cross-model efficacy and multiple patches. We observed average accuracy improvements of 30% in the real-world experiments. Our code is available at: https: //***/averysi224/angelic_patches.

关键词： computer vision for social good

来源：评论

学校读者我要写书评

暂无评论

DeepLSD: Line Segment Detection and Refinement with Deep Image Gradients

DeepLSD: Line Segment Detection and Refinement with Deep Ima...

引用

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

作者： Pautrat, Remi Barath, Daniel Larsson, Viktor Oswald, Martin R. Pollefeys, Marc Swiss Fed Inst Technol Dept Comp Sci Zurich Switzerland Lund Univ Lund Sweden Univ Amsterdam Amsterdam Netherlands Microsoft Mixed Real & AI Zurich Lab Zurich Switzerland

ISBN: (纸本)9798350301298

Line segments are ubiquitous in our human-made world and are increasingly used in vision tasks. They are complementary to feature points thanks to their spatial extent and the structural information they provide. Traditional line detectors based on the image gradient are extremely fast and accurate, but lack robustness in noisy images and challenging conditions. Their learned counterparts are more repeatable and can handle challenging images, but at the cost of a lower accuracy and a bias towards wireframe lines. We propose to combine traditional and learned approaches to get the best of both worlds: an accurate and robust line detector that can be trained in the wild without ground truth lines. Our new line segment detector, DeepLSD, processes images with a deep network to generate a line attraction field, before converting it to a surrogate image gradient magnitude and angle, which is then fed to any existing handcrafted line detector. Additionally, we propose a new optimization tool to refine line segments based on the attraction field and vanishing points. This refinement improves the accuracy of current deep detectors by a large margin. We demonstrate the performance of our method on low-level line detection metrics, as well as on several downstream tasks using multiple challenging datasets. The source code and models are available at https://***/cvg/DeepLSD.

关键词： Low-level vision

来源：评论

学校读者我要写书评

暂无评论

FAME-ViL: Multi-Tasking vision-Language Model for Heterogeneous Fashion Tasks

FAME-ViL: Multi-Tasking Vision-Language Model for Heterogene...

引用

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

作者： Han, Xiao Zhu, Xiatian Yu, Licheng Zhang, Li Song, Yi-Zhe Xiang, Tao Univ Surrey CVSSP Guildford Surrey England IFlyTek Surrey Joint Res Ctr Artificial Intellige Guildford Surrey England Surrey Inst People Ctr Artificial Intelligenc Guildford Surrey England Fudan Univ Shanghai Peoples R China

ISBN: (纸本)9798350301298

In the fashion domain, there exists a variety of vision-and-language (V+L) tasks, including cross-modal retrieval, text-guided image retrieval, multi-modal classification, and image captioning. They differ drastically in each individual input/output format and dataset size. It has been common to design a task-specific model and fine-tune it independently from a pre-trained V+L model (e.g., CLIP). This results in parameter inefficiency and inability to exploit inter-task relatedness. To address such issues, we propose a novel FAshion-focused Multi-task Efficient learning method for vision-and-Language tasks (FAME-ViL) in this work. Compared with existing approaches, FAME-ViL applies a single model for multiple heterogeneous fashion tasks, therefore being much more parameter-efficient. It is enabled by two novel components: (1) a task-versatile architecture with cross-attention adapters and task-specific adapters integrated into a unified V+L model, and (2) a stable and effective multi-task training strategy that supports learning from heterogeneous data and prevents negative transfer. Extensive experiments on four fashion tasks show that our FAME-ViL can save 61.5% of parameters over alternatives, while significantly outperforming the conventional independently trained single-task models. Code is available at https://***/BrandonHanx/FAME-ViL.

关键词： and reasoning language vision

来源：评论

学校读者我要写书评

暂无评论

HiMODE: A Hybrid Monocular Omnidirectional Depth Estimation Model

HiMODE: A Hybrid Monocular Omnidirectional Depth Estimation ...

引用

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

作者： Junayed, Masum Shah Sadeghzadeh, Arezoo Islam, Md Baharul Wong, Lai-Kuan Aydin, Tarkan Bahcesehir Univ Istanbul Turkey Amer Univ Malta Cospicua Malta Multimedia Univ Cyberjaya Malaysia

ISBN: (纸本)9781665487399

Monocular omnidirectional depth estimation is receiving considerable research attention due to its broad applications for sensing 360 degrees surroundings. Existing approaches in this field suffer from limitations in recovering small object details and data lost during the ground-truth depth map acquisition. In this paper, a novel monocular omnidirectional depth estimation model, namely HiMODE is proposed based on a hybrid CNN+Transformer (encoder-decoder) architecture whose modules are efficiently designed to mitigate distortion and computational cost, without performance degradation. Firstly, we design a feature pyramid network based on the HNet block to extract high-resolution features near the edges. The performance is further improved, benefiting from a self and cross attention layer and spatial/temporal patches in the Transformer encoder and decoder, respectively. Besides, a spatial residual block is employed to reduce the number of parameters. By jointly passing the deep features extracted from an input image at each backbone block, along with the raw depth maps predicted by the transformer encoder-decoder, through a context adjustment layer, our model can produce resulting depth maps with better visual quality than the ground-truth. Comprehensive ablation studies demonstrate the significance of each individual module. Extensive experiments conducted on three datasets;Stanford3D, Matterport3D, and SunCG, demonstrate that HiMODE can achieve state-of-the-art performance for 360 degrees monocular depth estimation. Complete project code and supplementary materials are available at https://***/himode5008/HiMODE.

关键词： Visualization Three-dimensional displays Estimation Lighting computer architecture Feature extraction Transformers

来源：评论

学校读者我要写书评

暂无评论

Are Deep Neural Networks SMARTer than Second Graders?

Are Deep Neural Networks SMARTer than Second Graders?

引用

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

作者： Cherian, Anoop Peng, Kuan-Chuan Lohit, Suhas Smith, Kevin A. Tenenbaum, Joshua B. Mitsubishi Elect Res Labs Cambridge MA 02139 USA MIT Cambridge MA 02139 USA

ISBN: (纸本)9798350301298

Recent times have witnessed an increasing number of applications of deep neural networks towards solving tasks that require superior cognitive abilities, e.g., playing Go, generating art, question answering (e.g., ChatGPT), etc. Such a dramatic progress raises the question: how generalizable are neural networks in solving problems that demand broad skills? To answer this question, we propose SMART: a Simple Multimodal Algorithmic Reasoning Task and the associated SMART-101 dataset1, for evaluating the abstraction, deduction, and generalization abilities of neural networks in solving visuo-linguistic puzzles designed specifically for children in the 6-8 age group. Our dataset consists of 101 unique puzzles;each puzzle comprises a picture and a question, and their solution needs a mix of several elementary skills, including arithmetic, algebra, and spatial reasoning, among others. To scale our dataset towards training deep neural networks, we programmatically generate entirely new instances for each puzzle while retaining their solution algorithm. To benchmark the performance on the SMART-101 dataset, we propose a vision-and-language meta-learning model that can incorporate varied state-of-the-art neural backbones. Our experiments reveal that while powerful deep models offer reasonable performances on puzzles in a supervised setting, they are not better than random accuracy when analyzed for generalization - filling this gap may demand new multimodal learning approaches.

关键词： language reasoning vision

来源：评论

学校读者我要写书评

暂无评论

RIFormer: Keep Your vision Backbone Effective But Removing Token Mixer

RIFormer: Keep Your Vision Backbone Effective But Removing T...

引用

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

作者： Wang, Jiahao Zhang, Songyang Liu, Yong Wu, Taiqiang Yang, Yujiu Liu, Xihui Chen, Kai Luo, Ping Lin, Dahua Shanghai AI Lab Shanghai Peoples R China Univ HongKong Hong Kong Peoples R China Tsinghua Shenzhen Int Grad Sch Shenzhen Peoples R China

ISBN: (纸本)9798350301298

This paper studies how to keep a vision backbone effective while removing token mixers in its basic building blocks. Token mixers, as self-attention for vision transformers (ViTs), are intended to perform information communication between different spatial tokens but suffer from considerable computational cost and latency. However, directly removing them will lead to an incomplete model structure prior, and thus brings a significant accuracy drop. To this end, we first develop an RepIdentityFormer base on the re-parameterizing idea, to study the token mixer free model architecture. And we then explore the improved learning paradigm to break the limitation of simple token mixer free backbone, and summarize the empirical practice into 5 guidelines. Equipped with the proposed optimization strategy, we are able to build an extremely simple vision backbone with encouraging performance, while enjoying the high efficiency during inference. Extensive experiments and ablative analysis also demonstrate that the inductive bias of network architecture, can be incorporated into simple network structure with appropriate optimization strategy. We hope this work can serve as a starting point for the exploration of optimization-driven efficient network design.

关键词： Deep learning architectures and techniques

来源：评论

学校读者我要写书评

暂无评论

Tri-Perspective View for vision-Based 3D Semantic Occupancy Prediction

Tri-Perspective View for Vision-Based 3D Semantic Occupancy ...

引用

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

作者： Huang, Yuanhui Zheng, Wenzhao Zhang, Yunpeng Zhou, Jie Lu, Jiwen Beijing Natl Res Ctr Informat Sci & Technol Beijing Peoples R China Tsinghua Univ Dept Automat Beijing Peoples R China

ISBN: (纸本)9798350301298

Modern methods for vision-centric autonomous driving perception widely adopt the bird's-eye-view (BEV) representation to describe a 3D scene. Despite its better efficiency than voxel representation, it has difficulty describing the fine-grained 3D structure of a scene with a single plane. To address this, we propose a tri-perspective view (TPV) representation which accompanies BEV with two additional perpendicular planes. We model each point in the 3D space by summing its projected features on the three planes. To lift image features to the 3D TPV space, we further propose a transformer-based TPV encoder (TPVFormer) to obtain the TPV features effectively. We employ the attention mechanism to aggregate the image features corresponding to each query in each TPV plane. Experiments show that our model trained with sparse supervision effectively predicts the semantic occupancy for all voxels. We demonstrate for the first time that using only camera inputs can achieve comparable performance with LiDAR-based methods on the LiDAR segmentation task on nuScenes. Code: https://***/wzzheng/TPVFormer.

关键词： Autonomous driving

来源：评论

学校读者我要写书评

暂无评论

METransformer: Radiology Report Generation by Transformer with Multiple Learnable Expert Tokens

METransformer: Radiology Report Generation by Transformer wi...

引用

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

作者： Wang, Zhanyu Liu, Lingqiao Wang, Lei Zhou, Luping Univ Sydney Sydney NSW Australia Univ Adelaide Adelaide SA Australia Univ Wollongong Wollongong NSW Australia

ISBN: (纸本)9798350301298

In clinical scenarios, multi-specialist consultation could significantly benefit the diagnosis, especially for intricate cases. This inspires us to explore a "multi-expert joint diagnosis" mechanism to upgrade the existing "single expert" framework commonly seen in the current literature. To this end, we propose METransformer, a method to realize this idea with a transformer-based backbone. The key design of our method is the introduction of multiple learnable "expert" tokens into both the transformer encoder and decoder. In the encoder, each expert token interacts with both vision tokens and other expert tokens to learn to attend different image regions for image representation. These expert tokens are encouraged to capture complementary information by an orthogonal loss that minimizes their overlap. In the decoder, each attended expert token guides the cross-attention between input words and visual tokens, thus influencing the generated report. A metrics-based expert voting strategy is further developed to generate the final report. By the multi-experts concept, our model enjoys the merits of an ensemble-based approach but through a manner that is computationally more efficient and supports more sophisticated interactions among experts. Experimental results demonstrate the promising performance of our proposed model on two widely used benchmarks. Last but not least, the framework-level innovation makes our work ready to incorporate advances on existing "single-expert" models to further improve its performance.

关键词： and reasoning language vision

来源：评论

学校读者我要写书评

暂无评论

Seeing What You Miss: vision-Language Pre-training with Semantic Completion Learning

Seeing What You Miss: Vision-Language Pre-training with Sema...

引用

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

作者： Ji, Yatai Tu, Rongcheng Jiang, Jie Kong, Weijie Cai, Chengfei Zhao, Wenzhe Wang, Hongfa Yang, Yujiu Liu, Wei Tsinghua Univ Beijing Peoples R China Tencent Shenzhen Guangdong Peoples R China

ISBN: (纸本)9798350301298

Cross-modal alignment is essential for vision-language pre-training (VLP) models to learn the correct corresponding information across different modalities. For this purpose, inspired by the success of masked language modeling (MLM) tasks in the NLP pre-training area, numerous masked modeling tasks have been proposed for VLP to further promote cross-modal interactions. The core idea of previous masked modeling tasks is to focus on reconstructing the masked tokens based on visible context for learning local-to-local alignment. However, most of them pay little attention to the global semantic features generated for the masked data, resulting in a limited cross-modal alignment ability of global representations. Therefore, in this paper, we propose a novel Semantic Completion Learning (SCL) task, complementary to existing masked modeling tasks, to facilitate global-to-local alignment. Specifically, the SCL task complements the missing semantics of masked data by capturing the corresponding information from the other modality, promoting learning more representative global features which have a great impact on the performance of downstream tasks. Moreover, we present a flexible vision encoder, which enables our model to perform image-text and video-text multimodal tasks simultaneously. Experimental results show that our proposed method obtains state-of-the-art performance on various vision-language benchmarks, such as visual question answering, image-text retrieval, and video-text retrieval.

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 << < 119 120 121 122 123 124 125 126 127 128 > >>

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：