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

3,317 篇 会议
3 篇 期刊文献

馆藏范围

3,320 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,915 篇 工学
- 1,820 篇 计算机科学与技术...
- 376 篇 软件工程
- 142 篇 机械工程
- 136 篇 光学工程
- 42 篇 生物工程
- 28 篇 信息与通信工程
- 11 篇 控制科学与工程
- 9 篇 电气工程
- 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
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
29 篇 医学
- 28 篇 临床医学
- 3 篇 基础医学(可授医学...
15 篇 管理学
- 8 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

1,179 篇 computer vision
801 篇 conferences
570 篇 training
484 篇 pattern recognit...
330 篇 computational mo...
279 篇 computer archite...
255 篇 visualization
180 篇 feature extracti...
160 篇 neural networks
153 篇 semantics
152 篇 task analysis
145 篇 cameras
143 篇 deep learning
140 篇 three-dimensiona...
139 篇 benchmark testin...
126 篇 low-level vision
117 篇 vision
115 篇 language
113 篇 image segmentati...
112 篇 estimation

机构

35 篇 tsinghua univ pe...
34 篇 univ sci & techn...
28 篇 shanghai ai lab ...
26 篇 chinese univ hon...
25 篇 university of sc...
25 篇 tsinghua univers...
24 篇 peng cheng labor...
23 篇 swiss fed inst t...
23 篇 swiss fed inst t...
23 篇 peng cheng lab p...
22 篇 zhejiang univ pe...
22 篇 carnegie mellon ...
20 篇 univ chinese aca...
20 篇 university of ch...
18 篇 harbin inst tech...
18 篇 shanghai jiao to...
18 篇 sensetime res pe...
16 篇 hong kong univ s...
15 篇 fudan univ peopl...
14 篇 national key lab...

作者

60 篇 timofte radu
26 篇 radu timofte
19 篇 van gool luc
16 篇 lei lei
15 篇 loy chen change
15 篇 qiao yu
14 篇 fan haoqiang
13 篇 zhang yulun
13 篇 liu shuaicheng
13 篇 luc van gool
12 篇 chen chen
12 篇 chen wei-ting
12 篇 li chongyi
11 篇 wangmeng zuo
11 篇 pan jinshan
11 篇 marcos v. conde
10 篇 wei dong
10 篇 zhou shangchen
10 篇 suiyi zhao
10 篇 yu lei

语言

3,319 篇 英文
1 篇 其他

检索条件"任意字段=2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023"

共 3320 条记录，以下是2581-2590 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：

Dynamic Attention-based Visual Odometry

Dynamic Attention-based Visual Odometry

引用

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

作者： Kuo, Xin-Yu Liu, Chien Lin, Kai-Chen Lee, Chun-Yi Natl Tsing Hua Univ Dept Comp Sci Elsa Lab Hsinchu Taiwan

ISBN: (纸本)9781728193601

This paper proposes a dynamic attention-based visual odometry framework (DAVO), a learning-based VO method, for estimating the ego-motion of a monocular camera. DAVO dynamically adjusts the attention weights on different semantic categories for different motion scenarios based on optical flow maps. These weighted semantic categories can then be used to generate attention maps that highlight the relative importance of different semantic regions in input frames for pose estimation. In order to examine the proposed DAVO, we perform a number of experiments on the KITTI Visual Odometry and SLAM benchmark suite to quantitatively and qualitatively inspect the impacts of the dynamically adjusted weights on the accuracy of the evaluated trajectories. Moreover, we design a set of ablation analyses to justify each of our design choices, and validate the effectiveness as well as the advantages of DAVO. Our experiments on the KITTI dataset shows that the proposed DAVO framework does provide satisfactory performance in ego-motion estimation, and is able deliver competitive performance when compared to the contemporary VO methods.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Task Residual for Tuning vision-Language Models

Task Residual for Tuning Vision-Language Models

引用

conference on computer vision and pattern recognition (CVPR)

作者： Tao Yu Zhihe Lu Xin Jin Zhibo Chen Xinchao Wang National University of Singapore University of Science and Technology of China

Large-scale vision-language models (VLMs) pre-trained on billion-level data have learned general visual representations and broad visual concepts. In principle, the welllearned knowledge structure of the VLMs should be inherited appropriately when being transferred to downstream tasks with limited data. However, most existing efficient transfer learning (ETL) approaches for VLMs either damage or are excessively biased towards the prior knowledge, e.g., prompt tuning (PT) discards the pre-trained text-based classifier and builds a new one while adapter-style tuning (AT) fully relies on the pre-trained features. To address this, we propose a new efficient tuning approach for VLMs named Task Residual Tuning (TaskRes), which performs directly on the text-based classifier and explicitly decouples the prior knowledge of the pre-trained models and new knowledge regarding a target task. Specifically, TaskRes keeps the original classifier weights from the VLMs frozen and obtains a new classifier for the target task by tuning a set of prior-independent parameters as a residual to the original one, which enables reliable prior knowledge preservation and flexible task-specific knowledge exploration. The proposed TaskRes is simple yet effective, which significantly outperforms previous ETL methods (e.g., PT and AT) on 11 benchmark datasets while requiring minimal effort for the implementation. Our code is available at https://***/geekyutao/TaskRes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Blind Image Quality Assessment via vision-Language Correspondence: A Multitask Learning Perspective

Blind Image Quality Assessment via Vision-Language Correspon...

引用

conference on computer vision and pattern recognition (CVPR)

作者： Weixia Zhang Guangtao Zhai Ying Wei Xiaokang Yang Kede Ma MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Department of Computer Science City University of Hong Kong Shenzhen Research Institute City University of Hong Kong

We aim at advancing blind image quality assessment (BIQA), which predicts the human perception of image quality without any reference information. We develop a general and automated multitask learning scheme for BIQA to exploit auxiliary knowledge from other tasks, in a way that the model parameter sharing and the loss weighting are determined automatically. Specifically, we first describe all candidate label combinations (from multiple tasks) using a textual template, and compute the joint probability from the cosine similarities of the visual-textual embeddings. Predictions of each task can be inferred from the joint distribution, and optimized by carefully designed loss functions. Through comprehensive experiments on learning three tasks - BIQA, scene classification, and distortion type identification, we verify that the proposed BIQA method 1) benefits from the scene classification and distortion type identification tasks and outperforms the state-of-the-art on multiple IQA datasets, 2) is more robust in the group maximum differentiation competition, and 3) realigns the quality annotations from different IQA datasets more effectively. The source code is available at https://***/zwx8981/LIQE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic Inference with Grounding Based vision and Language Models

Dynamic Inference with Grounding Based Vision and Language M...

引用

conference on computer vision and pattern recognition (CVPR)

作者： Burak Uzkent Amanmeet Garg Wentao Zhu Keval Doshi Jingru Yi Xiaolong Wang Mohamed Omar Amazon Prime Video

Transformers have been recently utilized for vision and language tasks successfully. For example, recent image and language models with more than 200M parameters have been proposed to learn visual grounding in the pre-training step and show impressive results on downstream vision and language tasks. On the other hand, there exists a large amount of computational redundancy in these large models which skips their run-time efficiency. To address this problem, we propose dynamic inference for grounding based vision and language models conditioned on the input image-text pair. We first design an approach to dynamically skip multihead self-attention and feed forward network layers across two backbones and multimodal network. Additionally, we propose dynamic token pruning and fusion for two backbones. In particular, we remove redundant tokens at different levels of the backbones and fuse the image tokens with the language tokens in an adaptive manner. To learn policies for dynamic inference, we train agents using reinforcement learning. In this direction, we replace the CNN backbone in a recent grounding-based vision and language model, MDETR, with a vision transformer and call it ViTMDETR. Then, we apply our dynamic inference method to ViTMDETR, called D-ViTDMETR, and perform experiments on image-language tasks. Our results show that we can improve the run-time efficiency of the state-of-the-art models MDETR and GLIP by up to ~ 50% on Referring Expression Comprehension and Segmentation, and VQA with only maximum ~ 0.3% accuracy drop.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Q: How to Specialize Large vision-Language Models to Data-Scarce VQA Tasks? A: Self-Train on Unlabeled Images!

Q: How to Specialize Large Vision-Language Models to Data-Sc...

引用

conference on computer vision and pattern recognition (CVPR)

作者： Zaid Khan BG Vijay Kumar Samuel Schulter Xiang Yu Yun Fu Manmohan Chandraker Northeastern University NEC Labs America Amazon UC San Diego

Finetuning a large vision language model (VLM) on a target dataset after large scale pretraining is a dominant paradigm in visual question answering (VQA). Datasets for specialized tasks such as knowledge-based VQA or VQA in non natural-image domains are orders of magnitude smaller than those for general-purpose VQA. While collecting additional labels for specialized tasks or domains can be challenging, unlabeled images are often available. We introduce SelTDA (Self-Taught Data Augmentation), a strategy for finetuning large VLMs on small-scale VQA datasets. SelTDA uses the VLM and target dataset to build a teacher model that can generate question-answer pseudolabels directly conditioned on an image alone, allowing us to pseudolabel unlabeled images. SelTDA then finetunes the initial VLM on the original dataset augmented with freshly pseudolabeled images. We describe a series of experiments showing that our self-taught data augmentation increases robustness to adversarially searched questions, counterfactual examples and rephrasings, improves domain generalization, and results in greater retention of numerical reasoning skills. The proposed strategy requires no additional annotations or architectural modifications, and is compatible with any modern encoder-decoder multimodal transformer. Code available at https://***/codezakh/SelTDA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unifying vision, Text, and Layout for Universal Document Processing

Unifying Vision, Text, and Layout for Universal Document Pro...

引用

conference on computer vision and pattern recognition (CVPR)

作者： Zineng Tang Ziyi Yang Guoxin Wang Yuwei Fang Yang Liu Chenguang Zhu Michael Zeng Cha Zhang Mohit Bansal University of North Carolina at Chapel Hill Microsoft Azure Cognitive Services Research Microsoft Azure Visual Document Intelligence

We propose Universal Document Processing (UDOP), a foundation Document AI model which unifies text, image, and layout modalities together with varied task formats, including document understanding and generation. UDOP leverages the spatial correlation between textual content and document image to model image, text, and layout modalities with one uniform representation. With a novel vision-Text-Layout Transformer, UDOP unifies pretraining and multi-domain downstream tasks into a prompt-based sequence generation scheme. UDOP is pretrained on both large-scale unlabeled document corpora using innovative self-supervised objectives and diverse labeled data. UDOP also learns to generate document images from text and layout modalities via masked image reconstruction. To the best of our knowledge, this is the first time in the field of document AI that one model simultaneously achieves high-quality neural document editing and content customization. Our method sets the state-of-the-art on 8 Document AI tasks, e.g., document understanding and QA, across diverse data domains like finance reports, academic papers, and web-sites. UDOP ranks first on the leaderboard of the Document Understanding Benchmark. 1 1 Code and models: https://***/microsoft/i-Code/tree/main/i-Code-Doc

关键词：

来源：评论

学校读者我要写书评

暂无评论

Masked Image Training for Generalizable Deep Image Denoising

Masked Image Training for Generalizable Deep Image Denoising

引用

conference on computer vision and pattern recognition (CVPR)

作者： Haoyu Chen Jinjin Gu Yihao Liu Salma Abdel Magid Chao Dong Qiong Wang Hanspeter Pfister Lei Zhu The Hong Kong University of Science and Technology (Guangzhou) Shanghai AI Lab The University of Sydney ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Harvard University Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences The Hong Kong University of Science and Technology

When capturing and storing images, devices inevitably introduce noise. Reducing this noise is a critical task called image denoising. Deep learning has become the de facto method for image denoising, especially with the emergence of Transformer-based models that have achieved notable state-of-the-art results on various image tasks. However, deep learning-based methods often suffer from a lack of generalization ability. For example, deep models trained on Gaussian noise may perform poorly when tested on other noise distributions. To address this issue, we present a novel approach to enhance the generalization performance of denoising networks, known as masked training. Our method involves masking random pixels of the input image and reconstructing the missing information during training. We also mask out the features in the self-attention layers to avoid the impact of training-testing inconsistency. Our approach exhibits better generalization ability than other deep learning models and is directly applicable to real-world scenarios. Additionally, our interpretability analysis demonstrates the superiority of our method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fusing Personal and Environmental Cues for Identification and Segmentation of First-Person Camera Wearers in Third-Person Views

Fusing Personal and Environmental Cues for Identification an...

引用

conference on computer vision and pattern recognition (CVPR)

作者： Ziwei Zhao Yuchen Wang Chuhua Wang Indiana University Bloomington

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

As wearable cameras become more popular, an important question emerges: how to identify camera wearers within the perspective of conventional static cameras. The drastic difference between first-person (egocentric) and third-person (exocentric) camera views makes this a challenging task. We present PersonEnvironmentNet (PEN), a framework designed to integrate information from both the individuals in the two views and geometric cues inferred from the background environment. To facilitate research in this direction, we also present TF2023, a novel dataset comprising synchronized first-person and third-person views, along with masks of camera wearers and labels associating these masks with the respective first-person views. In addition, we propose a novel quantitative metric designed to measure a model's ability to comprehend the relationship between the two views. Our experiments re- veal that PEN outperforms existing methods. The code and dataset are available at https://***/ziweizhao1993/PEN.

关键词： Measurement computer vision Codes Focusing Cameras pattern recognition Synchronization

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

conference on computer vision and pattern recognition (CVPR)

作者： Rémi Pautrat Daniel Barath Viktor Larsson Martin R. Oswald Marc Pollefeys Department of Computer Science ETH Zurich Lund University University of Amsterdam Microsoft Mixed Reality and AI Zurich Lab

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：

来源：评论

学校读者我要写书评

暂无评论

3DQ-Nets: Visual Concepts Emerge in Pose Equivariant 3D Quantized Neural Scene Representations

3DQ-Nets: Visual Concepts Emerge in Pose Equivariant 3D Quan...

引用

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

作者： Prabhudesai, Mihir Lal, Shamit Tung, Hsiao-Yu Fish Harley, Adam W. Potdar, Shubhankar Fragkiadaki, Katerina Carnegie Mellon Univ Pittsburgh PA 15213 USA

ISBN: (纸本)9781728193601

Concept learning lies at the very heart of intelligence, providing organizing principles with which to comprehend the world (6). Most computer vision models learn concept classifiers or detectors using labelled examples of object boxes, poses and categories. Self-supervised or unsupervised approaches mostly focus on (pre)training CNNs on auxiliary pretext tasks to lessen the need for human labels for a downstream recognition task. The visual "concepts" learnt from pretext tasks are implicit and represented as distributed neural CNN activations (7). We see the following limitations with representing concepts (solely) as neural activations across multiple layers of a deep network: i) visual memory and computation are not separated (3), which means that computation increases exponentially with the number of visual concepts learnt, ii) concepts are not stored somewhere and cannot be referred to or retrieved on demand, iii) the number of concepts cannot increase automatically based on new visual experiences, rather it is determined by the processing architecture;this misaligns with the idea that animals are capable of spontaneous concept instantiation in novel scenes (2), iv) concepts cannot be mentally manipulated by imagining variations, transformations or mental simulations (8), v) concepts do not have any spatial dimension and are hard to use for spatial reasoning. © 2020 ieee.

关键词： computer vision

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332页 << < 255 256 257 258 259 260 261 262 263 264 > >>

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：