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

3,915 篇 会议
2 篇 期刊文献

馆藏范围

3,917 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

3,011 篇 工学
- 2,919 篇 计算机科学与技术...
- 216 篇 软件工程
- 141 篇 机械工程
- 133 篇 光学工程
- 42 篇 生物工程
- 28 篇 信息与通信工程
- 25 篇 电气工程
- 17 篇 控制科学与工程
- 9 篇 电子科学与技术（可...
- 9 篇 化学工程与技术
- 9 篇 交通运输工程
- 8 篇 生物医学工程（可授...
- 7 篇 安全科学与工程
- 4 篇 材料科学与工程（可...
- 4 篇 建筑学
- 3 篇 土木工程
- 3 篇 农业工程
1,559 篇 医学
- 1,558 篇 临床医学
- 3 篇 基础医学(可授医学...
174 篇 理学
- 136 篇 物理学
- 43 篇 生物学
- 29 篇 数学
- 16 篇 统计学（可授理学、...
- 10 篇 化学
14 篇 管理学
- 7 篇 管理科学与工程(可...
- 7 篇 图书情报与档案管...
- 3 篇 工商管理
5 篇 法学
- 3 篇 社会学
- 2 篇 法学
2 篇 教育学
- 2 篇 教育学
2 篇 农学
1 篇 经济学

主题

2,408 篇 computer vision
1,085 篇 training
1,043 篇 pattern recognit...
805 篇 conferences
709 篇 computational mo...
543 篇 visualization
491 篇 computer archite...
446 篇 three-dimensiona...
410 篇 semantics
409 篇 benchmark testin...
383 篇 codes
331 篇 transformers
290 篇 deep learning
277 篇 feature extracti...
260 篇 neural networks
256 篇 task analysis
238 篇 shape
216 篇 image segmentati...
204 篇 measurement
202 篇 object detection

机构

72 篇 tsinghua univ pe...
59 篇 univ sci & techn...
55 篇 zhejiang univ pe...
55 篇 chinese univ hon...
51 篇 carnegie mellon ...
51 篇 peng cheng lab p...
49 篇 swiss fed inst t...
47 篇 sensetime res pe...
46 篇 shanghai ai lab ...
42 篇 univ hong kong p...
38 篇 huawei noahs ark...
35 篇 univ chinese aca...
35 篇 shanghai jiao to...
33 篇 alibaba grp peop...
32 篇 tech univ munich...
31 篇 stanford univ st...
30 篇 peking univ peop...
30 篇 swiss fed inst t...
29 篇 adobe res san jo...
29 篇 google res mount...

作者

63 篇 timofte radu
30 篇 van gool luc
19 篇 yang yi
19 篇 qiao yu
18 篇 loy chen change
16 篇 zhang lei
16 篇 radu timofte
15 篇 sun jian
14 篇 liu yang
14 篇 liu shuaicheng
14 篇 tao dacheng
13 篇 li xin
13 篇 fan haoqiang
13 篇 chen wei-ting
12 篇 luo ping
12 篇 chen dongdong
12 篇 wang kai
12 篇 wang xinchao
12 篇 torralba antonio
12 篇 ghanem bernard

语言

3,916 篇 英文
1 篇 其他

检索条件"任意字段=2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022"

共 3917 条记录，以下是3661-3670 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：

iEdit: Localised Text-guided Image Editing with Weak Supervision

iEdit: Localised Text-guided Image Editing with Weak Supervi...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Rumeysa Bodur Erhan Gundogdu Binod Bhattarai Tae-Kyun Kim Michael Donoser Loris Bazzani Imperial College London UK Amazon University of Aberdeen UK KAIST South Korea

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Diffusion models (DMs) can generate realistic images with text guidance using large-scale datasets. However, they demonstrate limited controllability on the generated images. We introduce iEdit, a novel method for text-guided image editing conditioned on a source image and textual prompt. As a fully-annotated dataset with target images does not exist, previous approaches perform subject-specific fine-tuning at test time or adopt contrastive learning without a target image, leading to issues on preserving source image fidelity. We propose to automatically construct a dataset derived from LAION-5B, containing pseudo-target images and descriptive edit prompts. The dataset allows us to incorporate a weakly-supervised loss function, generating the pseudo-target image from the source image’s latent noise conditioned on the edit prompt. To encourage localised editing we propose a loss function that uses segmentation masks to guide the editing during training and optionally at inference. Trained with limited GPU resources on the constructed dataset, our model outperforms counterparts in image fidelity, CLIP alignment score, and qualitatively for both generated and real images.

关键词： Training Image segmentation computer vision conferences Noise Graphics processing units Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Efficient local correlation volume for unsupervised optical flow estimation on small moving objects in large satellite images

Efficient local correlation volume for unsupervised optical ...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Sarra Khairi Etienne Meunier Renaud Fraisse Patrick Bouthemy Inria Rennes France Airbus Defence & Space Toulouse France

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

With the advent of deep learning methods, performance and efficiency of optical flow estimation has significantly increased, especially for supervised models. However, they do not generalize well to more specific data involving small moving objects in large images, such as high-resolution aerial or satellite sequences. In addition, annotation and realistic simulation are difficult for these contents, which calls for unsupervised alternatives. Yet, the latter are still less accurate than their supervised counterparts. In this paper, we introduce an unsupervised local optical flow estimation method adapted to small moving objects in large-size images by involving no downsampling of the feature maps. We adopt a local correlation search and implement it in an original way with a per-shift computation, which minimizes memory consumption and speed up inference computation for large-scale images. We also design a loss function combining similarity, smoothness and sparsity constraints. We demonstrate the performance of our SMOFlow method on real stabilized aerial videos fully representative of future satellite conditions. SMOFlow favorably compares to other methods. Our SMOFlow method is able to accurately capture the motion of small objects in large images, while efficiently reducing memory consumption.

关键词： computer vision Solid modeling Correlation Satellites Memory management Estimation Satellite images

来源：评论

学校读者我要写书评

暂无评论

3D Human Pose Estimation with Occlusions: Introducing BlendMimic3D Dataset and GCN Refinement

3D Human Pose Estimation with Occlusions: Introducing BlendM...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Filipa Lino Carlos Santiago Manuel Marques LARSyS Instituto Superior Técnico Institute for Systems and Robotics Portugal

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

In the field of 3D Human Pose Estimation (HPE), accurately estimating human pose, especially in scenarios with occlusions, is a significant challenge. This work identifies and addresses a gap in the current state of the art in 3D HPE concerning the scarcity of data and strategies for handling occlusions. We introduce our novel BlendMimic3D dataset, designed to mimic real-world situations where occlusions occur for seamless integration in 3D HPE algorithms. Additionally, we propose a 3D pose refinement block, employing a Graph Convolutional Network (GCN) to enhance pose representation through a graph model. This GCN block acts as a plug-and-play solution, adaptable to various 3D HPE frameworks without requiring retraining them. By training the GCN with occluded data from Blend-Mimic3D, we demonstrate significant improvements in resolving occluded poses, with comparable results for non-occluded ones. Project web page is available at https://***/BlendMimic3D/.

关键词： Training Solid modeling computer vision Three-dimensional displays Graph convolutional networks conferences Pose estimation

来源：评论

学校读者我要写书评

暂无评论

De-noised vision-language Fusion Guided by Visual Cues for E-commerce Product Search

De-noised Vision-language Fusion Guided by Visual Cues for E...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Zhizhang Hu Shasha Li Ming Du Arnab Dhua Douglas Gray University of California Merced Amazon Visual Search & AR

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

In e-commerce applications, vision-language multimodal transformer models play a pivotal role in product search. The key to successfully training a multimodal model lies in the alignment quality of image-text pairs in the dataset. However, the data in practice is often automatically collected with minimal manual intervention. Hence the alignment of image-text pairs is far from ideal. In e-commerce, this misalignment can stem from noisy and redundant non-visual-descriptive text attributes in the product description. To address this, we introduce the MultiModal alignment-guided Learned Token Pruning (MM-LTP) method. MM-LTP employs token pruning, conventionally used for computational efficiency, to perform online text cleaning during multimodal model training. By enabling the model to discern and discard unimportant tokens, it is able to train with implicitly cleaned image-text pairs. We evaluate MM-LTP using a benchmark multimodal e-commerce dataset comprising over 710,000 unique Amazon products. Our evaluation hinges on visual search, a prevalent e-commerce feature. Through MM-LTP, we demonstrate that refining text tokens enhances the paired image branch's training, which leads to significantly improved visual search performance.

关键词： Training Visualization Computational modeling Refining Manuals Fasteners Transformers

来源：评论

学校读者我要写书评

暂无评论

Condensation-Net: Memory-Efficient Network Architecture With Cross-Channel Pooling Layers and Virtual Feature Maps

Condensation-Net: Memory-Efficient Network Architecture With...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Tse-Wei Chen Motoki Yoshinaga Hongxing Gao Wei Tao Dongchao Wen Junjie Liu Kinya Osa Masami Kato Device Technology Development Headquarters Canon Inc. Tokyo Japan Canon Information Technology (Beijing) Co. Ltd. Haidian Beijing China

ISBN: (数字)9781728125060

ISBN: (纸本)9781728125077

Lightweight convolutional neural networks is an important research topic in the field of embedded vision. To implement image recognition tasks on a resource-limited hardware platform, it is necessary to reduce the memory size and the computational cost. The contribution of this paper is stated as follows. First, we propose an algorithm to process a specific network architecture (Condensation-Net) without increasing the maximum memory storage for feature maps. The architecture for virtual feature maps saves 26.5% of memory bandwidth by calculating the results of cross-channel pooling before storing the feature map into the memory. Second, we show that cross-channel pooling can improve the accuracy of object detection tasks, such as face detection, because it increases the number of filter weights. Compared with Tiny-YOLOv2, the improvement of accuracy is 2.0% for quantized networks and 1.5% for full-precision networks when the false-positive rate is 0.1. Last but not the least, the analysis results show that the overhead to support the cross-channel pooling with the proposed hardware architecture is negligible small. The extra memory cost to support Condensation-Net is 0.2% of the total size, and the extra gate count is only 2.1% of the total size.

关键词： Hardware computer architecture Network architecture Training Microsoft Windows Feature extraction Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Improving Object Detection to Fisheye Cameras with Open-Vocabulary Pseudo-Label Approach

Improving Object Detection to Fisheye Cameras with Open-Voca...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Long Hoang Pham Quoc Pham-Nam Ho Duong Nguyen-Ngoc Tran Tai Huu-Phuong Tran Huy-Hung Nguyen Duong Khac Vu Chi Dai Tran Ngoc Doan-Minh Huynh Hyung-Min Jeon Hyung-Joon Jeon Jae Wook Jeon Department of Electrical and Computer Engineering Sungkyunkwan University

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Fish-eye cameras have long been employed in traffic surveillance systems to allow for wider observation of the roads. Despite their widespread use, limited computer vision research is tailored explicitly to images captured by fish-eye cameras. The AI City Challenge 2024 - Track 4 introduces a novel fish-eye camera dataset for the 2D road object detection task. This paper proposes a framework designed to detect objects in fish-eye camera images. Our approach involves several key steps: first, we generate image data to bridge the representation gap between day and night images. Next, we leverage zero-shot open vocabulary detection to produce pseudo-labels, aiding in training supervised object detection models. Additionally, we optimize the model’s hyper-parameters and inference configuration for better performance. Finally, we apply various post-processing techniques to enhance detection performance. Our solution achieves a final F1 score of 0.6194 in the AI City Challenge 2024 - Track 4, ranking third among competing teams. The source code is available at GitHub Repo.

关键词： Training computer vision Adaptation models Vocabulary Roads Urban areas Object detection

来源：评论

学校读者我要写书评

暂无评论

Event detection in coarsely annotated sports videos via parallel multi receptive field 1D convolutions

Event detection in coarsely annotated sports videos via para...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Kanav Vats Mehrnaz Fani Pascale Walters David A. Clausi John Zelek University of Waterloo Waterloo Ontario Canada

ISBN: (数字)9781728193601

ISBN: (纸本)9781728193618

In problems such as sports video analytics, it is difficult to obtain accurate frame level annotations and exact event duration because of the lengthy videos and sheer volume of video data. This issue is even more pronounced in fast-paced sports such as ice hockey. Obtaining annotations on a coarse scale can be much more practical and time efficient. We propose the task of event detection in coarsely annotated videos. We introduce a multi-tower temporal convolutional network architecture for the proposed task. The network, with the help of multiple receptive fields, processes information at various temporal scales to account for the uncertainty with regard to the exact event location and duration. We demonstrate the effectiveness of the multi-receptive field architecture through appropriate ablation studies. The method is evaluated on two tasks - event detection in coarsely annotated hockey videos in the NHL dataset and event spotting in soccer on the SoccerNet dataset. The two datasets lack frame-level annotations and have very distinct event frequencies. Experimental results demonstrate the effectiveness of the network by obtaining a 55% average F1 score on the NHL dataset and by achieving competitive performance compared to the state of the art on the SoccerNet dataset. We believe our approach will help develop more practical pipelines for event detection in sports video.

关键词： Videos Poles and towers Event detection Games Task analysis computer vision

来源：评论

学校读者我要写书评

暂无评论

Block Selective Reprogramming for On-device Training of vision Transformers

Block Selective Reprogramming for On-device Training of Visi...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Sreetama Sarkar Souvik Kundu Kai Zheng Peter A. Beerel Universiy of Southern California Los Angeles USA Intel Labs San Diego USA

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

The ubiquity of vision transformers (ViTs) for various edge applications, including personalized learning, has created the demand for on-device fine-tuning. However, training with the limited memory and computation power of edge devices remains a significant challenge. In particular, the memory required for training is much higher than that needed for inference, primarily due to the need to store activations across all layers in order to compute the gradients needed for weight updates. Previous works have explored reducing this memory requirement via frozen-weight training as well storing the activations in a compressed format. However, these methods are deemed inefficient due to their inability to provide training or inference speedup. In this paper, we first investigate the limitations of existing on-device training methods aimed at reducing memory and compute requirements. We then present block selective reprogramming (BSR) in which we fine-tune only a fraction of total blocks of a pre-trained model and selectively drop tokens based on self-attention scores of the frozen layers. To show the efficacy of BSR, we present extensive evaluations on ViT-B and DeiT-S with five different datasets. Compared to the existing alternatives, our approach simultaneously reduces training memory by up to 1.4× and compute cost by up to 2× while maintaining similar accuracy. We also showcase results for Mixture-of-Expert (MoE) models, demonstrating the effectiveness of our approach in multitask learning scenarios. Code will be available at: https://***/sreetamasarkar/BSR.

关键词： Training computer vision Costs Quantization (signal) Codes Computational modeling conferences

来源：评论

学校读者我要写书评

暂无评论

Two Stage Dehazing Framework for Dense and Non-Homogeneous Dehazing

Two Stage Dehazing Framework for Dense and Non-Homogeneous D...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Wei Song Yichang Gao Jiahao Xiong Hualiang Lin Dong Li Yun Zhang Guangdong University of Technology Guangzhou China

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

In real-world environments, haze often causes a decrease in visibility, leading to potentially severe consequences. Although current methods based on the assumption of homogeneous haze density have achieved commendable results, dehazing techniques for non-homogeneous density haze still fall short in terms of visibility restoration and color accuracy. We observe that although single-stage methods have made significant strides, a multi-stage enhancement can further improve dehazing in terms of both visibility and color restoration. In this paper, we propose a two-stage dehaze framework, named Two Stage Dehazing Framework. Our approach consists of a DehazeNet, which does not require specifying a particular model for dehazing and can accept a hazy image as input, producing an clear image of the same dimensions as the original. Two such DehazeNet are sequentially connected to form the final serial DehazeNet. Moreover, to better approximate the output image to real-world scenes, we propose the Multi-Scale Attention Head. Our method achieved third place in NTIRE 2024 Dense and NonHomogeneous Dehazing Challenge, demonstrating outstanding performance metrics in the Peak Signal to Noise Ratio (PSNR), the Structral Similarity Index (SSIM), and the Mean Opinion Score (MOS). Related code will be acailable on code.

关键词： Training Measurement computer vision PSNR Head Codes Image color analysis

来源：评论

学校读者我要写书评

暂无评论

AAPL: Adding Attributes to Prompt Learning for vision-Language Models

AAPL: Adding Attributes to Prompt Learning for Vision-Langua...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Gahyeon Kim Sohee Kim Seokju Lee Korea Institute of Energy Technology (KENTECH)

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Recent advances in large pre-trained vision-language models have demonstrated remarkable performance on zeroshot downstream tasks. Building upon this, recent studies, such as CoOp and CoCoOp, have proposed the use of prompt learning, where context within a prompt is replaced with learnable vectors, leading to significant improvements over manually crafted prompts. However, the performance improvement for unseen classes is still marginal, and to tackle this problem, data augmentation has been frequently used in traditional zero-shot learning techniques. Through our experiments, we have identified important issues in CoOp and CoCoOp: the context learned through traditional image augmentation is biased toward seen classes, negatively impacting generalization to unseen classes. To address this problem, we propose adversarial token embedding to disentangle low-level visual augmentation features from high-level class information when inducing bias in learnable prompts. Through our novel mechanism called "Adding Attributes to Prompt Learning", AAPL, we guide the learnable context to effectively extract text features by focusing on high-level features for unseen classes. We have conducted experiments across 11 datasets, and overall, AAPL shows favorable performances compared to the existing methods in few-shot learning, zero-shot learning, cross-dataset, and domain generalization tasks.

关键词： Visualization Zero-shot learning Semantics Focusing Feature extraction Data augmentation Vectors

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392页 << < 363 364 365 366 367 368 369 370 371 372 > >>

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：