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

50,636 篇 会议
1,423 册 图书
1,044 篇 期刊文献
1 篇 学位论文

馆藏范围

53,101 篇 电子文献
3 种 纸本馆藏

日期分布

学科分类号

31,927 篇 工学
- 24,897 篇 计算机科学与技术...
- 12,629 篇 软件工程
- 5,176 篇 光学工程
- 4,760 篇 电气工程
- 4,463 篇 信息与通信工程
- 4,261 篇 机械工程
- 3,980 篇 控制科学与工程
- 2,477 篇 生物工程
- 1,736 篇 生物医学工程（可授...
- 1,583 篇 仪器科学与技术
- 1,314 篇 电子科学与技术（可...
- 795 篇 化学工程与技术
- 715 篇 安全科学与工程
- 560 篇 交通运输工程
- 383 篇 建筑学
- 335 篇 土木工程
11,899 篇 理学
- 6,481 篇 物理学
- 5,426 篇 数学
- 2,765 篇 生物学
- 1,915 篇 统计学（可授理学、...
- 804 篇 化学
- 669 篇 系统科学
5,313 篇 医学
- 5,103 篇 临床医学
- 731 篇 基础医学(可授医学...
- 459 篇 药学(可授医学、理...
3,369 篇 管理学
- 1,964 篇 图书情报与档案管...
- 1,554 篇 管理科学与工程(可...
- 485 篇 工商管理
720 篇 艺术学
- 718 篇 设计学（可授艺术学...
434 篇 法学
- 406 篇 社会学
302 篇 农学
198 篇 教育学
166 篇 经济学
63 篇 文学
48 篇 军事学

主题

17,404 篇 computer vision
9,026 篇 pattern recognit...
4,196 篇 training
3,830 篇 feature extracti...
3,134 篇 cameras
2,876 篇 computational mo...
2,794 篇 image segmentati...
2,622 篇 visualization
2,574 篇 shape
2,535 篇 face recognition
2,176 篇 robustness
2,124 篇 computer science
1,975 篇 object detection
1,960 篇 computer archite...
1,882 篇 layout
1,853 篇 object recogniti...
1,801 篇 three-dimensiona...
1,725 篇 neural networks
1,705 篇 humans
1,697 篇 image recognitio...

机构

165 篇 univ chinese aca...
144 篇 tsinghua univers...
135 篇 national laborat...
106 篇 univ sci & techn...
104 篇 zhejiang univers...
101 篇 shanghai jiao to...
95 篇 university of sc...
95 篇 microsoft resear...
85 篇 zhejiang univ pe...
84 篇 shanghai ai lab ...
74 篇 school of comput...
69 篇 computer vision ...
68 篇 peking univ peop...
68 篇 chinese acad sci...
66 篇 chinese univ hon...
63 篇 institute of inf...
62 篇 google res mount...
61 篇 univ oxford oxfo...
59 篇 univ toronto on
57 篇 swiss fed inst t...

作者

92 篇 van gool luc
87 篇 umapada pal
78 篇 zhang lei
64 篇 lee seong-whan
50 篇 vittorio murino
42 篇 yang yi
34 篇 nassir navab
34 篇 ling haibin
33 篇 li xin
33 篇 jie yang
32 篇 liu yang
31 篇 loy chen change
30 篇 escalera sergio
30 篇 h. bischof
29 篇 zhou jie
29 篇 vasconcelos nuno
29 篇 jan-michael frah...
28 篇 blumenstein mich...
27 篇 jia yunde
27 篇 luo ping

语言

50,122 篇 英文
2,746 篇 其他
252 篇 中文
22 篇 土耳其文
4 篇 西班牙文
2 篇 日文
2 篇 葡萄牙文
2 篇 俄文

检索条件"任意字段=IEEE Conference on Computer Vision and Pattern Recognition"

共 53104 条记录，以下是271-280 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：

Generalized Single-Image-Based Morphing Attack Detection Using Deep Representations from vision Transformer

Generalized Single-Image-Based Morphing Attack Detection Usi...

引用

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

作者： Zhang, Haoyu Ramachandra, Raghavendra Raja, Kiran Busch, Christoph Norwegian Univ Sci & Technol Trondheim Norway Darmstadt Univ Appl Sci Darmstadt Germany

ISBN: (纸本)9798350365474

Face morphing attacks have posed severe threats to Face recognition Systems (FRS), which are operated in border control and passport issuance use cases. Correspondingly, morphing attack detection algorithms (MAD) are needed to defend against such attacks. MAD approaches must be robust enough to handle unknown attacks in an open-set scenario where attacks can originate from various morphing generation algorithms, post-processing and the diversity of printers/scanners. The problem of generalization is further pronounced when the detection has to be made on a single suspected image. In this paper, we propose a generalized single-image-based MAD (S-MAD) algorithm by learning the encoding from vision Transformer (ViT) architecture. Compared to CNN-based architectures, ViT model has the advantage on integrating local and global information and hence can be suitable to detect the morphing traces widely distributed among the face region. Extensive experiments are carried out on face morphing datasets generated using publicly available FRGC face datasets. Several state-of-the-art (SOTA) MAD algorithms, including representative ones that have been publicly evaluated, have been selected and benchmarked with our ViT-based approach. Obtained results demonstrate the improved detection performance of the proposed S-MAD method on inter-dataset testing (when different data is used for training and testing) and comparable performance on intra-dataset testing (when the same data is used for training and testing) experimental protocol.

关键词： Face recognition Morphing Attack Detection

来源：评论

学校读者我要写书评

暂无评论

Finding Lottery Tickets in vision Models via Data-driven Spectral Foresight Pruning

Finding Lottery Tickets in Vision Models via Data-driven Spe...

引用

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

作者： Iurada, Leonardo Ciccone, Marco Tommasi, Tatiana Politecn Torino Turin Italy

ISBN: (纸本)9798350353006

Recent advances in neural network pruning have shown how it is possible to reduce the computational costs and memory demands of deep learning models before training. We focus on this framework and propose a new pruning at initialization algorithm that leverages the Neural Tangent Kernel (NTK) theory to align the training dynamics of the sparse network with that of the dense one. Specifically, we show how the usually neglected data-dependent component in the NTK's spectrum can be taken into account by providing an analytical upper bound to the NTK's trace obtained by decomposing neural networks into individual paths. This leads to our Path eXclusion (PX), a foresight pruning method designed to preserve the parameters that mostly influence the NTK's trace. PX is able to find lottery tickets (i.e. good paths) even at high sparsity levels and largely reduces the need for additional training. When applied to pre-trained models it extracts subnetworks directly usable for several downstream tasks, resulting in performance comparable to those of the dense counterpart but with substantial cost and computational savings. Code available at: https://***/iurada/px-ntk-pruning

关键词： Efficient computer vision Neural Network Pruning Neural Tangent Kernel Pruning-at-Initialization

来源：评论

学校读者我要写书评

暂无评论

Back to 3D: Few-Shot 3D Keypoint Detection with Back-Projected 2D Features

Back to 3D: Few-Shot 3D Keypoint Detection with Back-Project...

引用

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

作者： Wimmer, Thomas Wonka, Peter Ovsjanikov, Maks Ecole Polytech LIX Palaiseau France Tech Univ Munich Munich Germany KAUST Thuwal Saudi Arabia

ISBN: (纸本)9798350353013;9798350353006

With the immense growth of dataset sizes and computing resources in recent years, so-called foundation models have become popular in NLP and vision tasks. In this work, we propose to explore foundation models for the task of keypoint detection on 3D shapes. A unique characteristic of keypoint detection is that it requires semantic and geometric awareness while demanding high localization accuracy. To address this problem, we propose, first, to back-project features from large pre-trained 2D vision models onto 3D shapes and employ them for this task. We show that we obtain robust 3D features that contain rich semantic information and analyze multiple candidate features stemming from different 2D foundation models. Second, we employ a keypoint candidate optimization module which aims to match the average observed distribution of keypoints on the shape and is guided by the back-projected features. The resulting approach achieves a new state of the art for few-shot keypoint detection on the KeyPointNet dataset, almost doubling the performance of the previous best methods.

关键词： 3D vision Foundation Models Keypoint Detection Shape Analysis

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

作者： Sarkar, Sreetama Kundu, Souvik Zheng, Kai Beerel, Peter A. Univ Southern Calif Los Angeles CA 90007 USA Intel Labs San Diego CA USA

ISBN: (纸本)9798350365474

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 1.4x and compute cost by up to 2x 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： on-device training token pruning vision transformer

来源：评论

学校读者我要写书评

暂无评论

Stronger, Fewer, & Superior: Harnessing vision Foundation Models for Domain Generalized Semantic Segmentation

Stronger, Fewer, & Superior: Harnessing Vision Foundation Mo...

引用

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

作者： Wei, Zhixiang Chen, Lin Jin, Yi Ma, Xiaoxiao Liu, Tianle Ling, Pengyang Wang, Ben Chen, Huaian Zheng, Jinjin Univ Sci & Technol China Hefei Peoples R China Shanghai Ai Lab Shanghai Peoples R China

ISBN: (纸本)9798350353006

In this paper, we first assess and harness various vision Foundation Models (VFMs) in the context of Domain Generalized Semantic Segmentation (DGSS). Driven by the motivation that Leveraging Stronger pre-trained models and Fewer trainable parameters for Superior generalizability, we introduce a robust fine-tuning approach, namely "Rein", to parameter-efficiently harness VFMs for DGSS. Built upon a set of trainable tokens, each linked to distinct instances, Rein precisely refines and forwards the feature maps from each layer to the next layer within the backbone. This process produces diverse refinements for different categories within a single image. With fewer trainable parameters, Rein efficiently fine-tunes VFMs for DGSS tasks, surprisingly surpassing full parameter fine-tuning. Extensive experiments across various settings demonstrate that Rein significantly outperforms state-of-the-art methods. Remarkably, with just an extra 1% of trainable parameters within the frozen backbone, Rein achieves a mIoU of 78.4% on the Cityscapes, without accessing any real urban-scene datasets. Code is available at https://***/w1oves/***.

关键词： Domain Generalized Semantic Segmentation parameter-efficient fine-tuning Semantic Segmentation vision Foundation Models

来源：评论

学校读者我要写书评

暂无评论

How to Benchmark vision Foundation Models for Semantic Segmentation?

How to Benchmark Vision Foundation Models for Semantic Segme...

引用

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

作者： Kerssies, Tommie de Geus, Daan Dubbelman, Gijs Eindhoven Univ Technol Eindhoven Netherlands

ISBN: (纸本)9798350365474

Recent vision foundation models (VFMs) have demonstrated proficiency in various tasks but require supervised fine-tuning to perform the task of semantic segmentation effectively. Benchmarking their performance is essential for selecting current models and guiding future model developments for this task. The lack of a standardized benchmark complicates comparisons. Therefore, the primary objective of this paper is to study how VFMs should be benchmarked for semantic segmentation. To do so, various VFMs are finetuned under various settings, and the impact of individual settings on the performance ranking and training time is assessed. Based on the results, the recommendation is to finetune the ViT-B variants of VFMs with a 16 x 16 patch size and a linear decoder, as these settings are representative of using a larger model, more advanced decoder and smaller patch size, while reducing training time by more than 13 times. Using multiple datasets for training and evaluation is also recommended, as the performance ranking across datasets and domain shifts varies. Linear probing, a common practice for some VFMs, is not recommended, as it is not representative of end-to-end fine-tuning. The benchmarking setup recommended in this paper enables a performance analysis of VFMs for semantic segmentation. The findings of such an analysis reveal that pretraining with promptable segmentation is not beneficial, whereas masked image modeling (MIM) with abstract representations is crucial, even more important than the type of supervision used. The code for efficiently fine-tuning VFMs for semantic segmentation can be accessed through the project page(1).

关键词： benchmark semantic segmentation vision foundation models

来源：评论

学校读者我要写书评

暂无评论

ZeroShape: Regression-based Zero-shot Shape Reconstruction

ZeroShape: Regression-based Zero-shot Shape Reconstruction

引用

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

作者： Huang, Zixuan Stojanov, Stefan Thai, Anh Jampani, Varun Rehg, James M. Univ Illinois Champaign IL 61820 USA Georgia Inst Technol Atlanta GA 30332 USA Stabil AI London England

ISBN: (纸本)9798350353006

We study the problem of single-image zero-shot 3D shape reconstruction. Recent works learn zero-shot shape reconstruction through generative modeling of 3D assets, but these models are computationally expensive at train and inference time. In contrast, the traditional approach to this problem is regression-based, where deterministic models are trained to directly regress the object shape. Such regression methods possess much higher computational efficiency than generative methods. This raises a natural question: is generative modeling necessary for high performance, or conversely, are regression-based approaches still competitive? To answer this, we design a strong regression-based model, called ZeroShape, based on the converging findings in this field and a novel insight. We also curate a large real-world evaluation benchmark, with objects from three different real-world 3D datasets. This evaluation benchmark is more diverse and an order of magnitude larger than what prior works use to quantitatively evaluate their models, aiming at reducing the evaluation variance in our field. We show that ZeroShape not only achieves superior performance over state-of-the-art methods, but also demonstrates significantly higher computational and data efficiency.(1)

关键词： 3D generation 3D reconstruction 3D vision computer vision Deep Learning

来源：评论

学校读者我要写书评

暂无评论

InVERGe: Intelligent Visual Encoder for Bridging Modalities in Report Generation

InVERGe: Intelligent Visual Encoder for Bridging Modalities ...

引用

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

作者： Deria, Ankan Kumar, Komal Chakraborty, Snehashis Mahapatra, Dwarikanath Roy, Sudipta Jio Inst Artificial Intelligence & Data Sci Navi Mumbai 410206 India Incept Inst Artificial Intelligence Abu Dhabi U Arab Emirates

ISBN: (纸本)9798350365474

Medical image captioning plays an important role in modern healthcare, improving clinical report generation and aiding radiologists in detecting abnormalities and reducing misdiagnosis. The complex visual and textual data biases make this task more challenging. Recent advancements in transformer-based models have significantly improved the generation of radiology reports from medical images. However, these models require substantial computational resources for training and have been observed to produce unnatural language outputs when trained solely on raw image-text pairs. Our aim is to generate more detailed reports specific to images and to explain the reasoning behind the generated text through image-text alignment. Given the high computational demands of end-to-end model training, we introduce a two-step training methodology with an Intelligent Visual Encoder for Bridging Modalities in Report Generation (InVERGe) model. This model incorporates a lightweight transformer known as the Cross-Modal Query Fusion Layer (CMQFL), which utilizes the output from a frozen encoder to identify the most relevant text-grounded image embedding. This layer bridges the gap between the encoder and decoder, significantly reducing the workload on the decoder and enhancing the alignment between vision and language. Our experimental results, conducted using the MIMIC-CXR, Indiana University chest X-ray images, and CDD-CESM breast images datasets, demonstrate the effectiveness of our approach. Code: https://***/labsroy007/InVERGe

关键词： computer vision Deep Learning Large Language Model Medical Imaging Report Generation

来源：评论

学校读者我要写书评

暂无评论

Test-Time Adaptation for Depth Completion

Test-Time Adaptation for Depth Completion

引用

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

作者： Park, Hyoungseob Gupta, Anjali Wong, Alex Yale Vision Lab New Haven CT 06501 USA

ISBN: (纸本)9798350353006

It is common to observe performance degradation when transferring models trained on some (source) datasets to target testing data due to a domain gap between them. Existing methods for bridging this gap, such as domain adaptation (DA), may require the source data on which the model was trained (often not available), while others, i.e., source-free DA, require many passes through the testing data. We propose an online test-time adaptation method for depth completion, the task of inferring a dense depth map from a single image and associated sparse depth map, that closes the performance gap in a single pass. We first present a study on how the domain shift in each data modality affects model performance. Based on our observations that the sparse depth modality exhibits a much smaller covariate shift than the image, we design an embedding module trained in the source domain that preserves a mapping from features encoding only sparse depth to those encoding image and sparse depth. During test time, sparse depth features are projected using this map as a proxy for source domain features and are used as guidance to train a set of auxiliary parameters (i.e., adaptation layer) to align image and sparse depth features from the target test domain to that of the source domain. We evaluate our method on indoor and outdoor scenarios and show that it improves over baselines by an average of 21.1%. Code available at ***/seobbro/TTA-depth-completion.

关键词： 3D computer vision Depth completion Depth estimation Multi-modal fusion Test time adaptation

来源：评论

学校读者我要写书评

暂无评论

Distilling vision-Language Models on Millions of Videos

Distilling Vision-Language Models on Millions of Videos

引用

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

作者： Zhao, Yue Zhao, Long Zhou, Xingyi Wu, Jialin Chu, Chun-Te Mia, Hui Schroff, Florian Adam, Hartwig Liu, Ting Gong, Boqing Krahenbuhl, Philipp Yuan, Liangzhe Google Res Mountain View CA 94043 USA Univ Texas Austin Austin TX 78712 USA

ISBN: (纸本)9798350353006

The recent advance in vision-language models is largely attributed to the abundance of image-text data. We aim to replicate this success for video-language models, but there simply is not enough human- curated video-text data available. We thus resort to fine-tuning a video-language model from a strong image-language baseline with synthesized instructional data. The resulting video model by video-instruction-tuning (VIIT) is then used to auto-label millions of videos to generate high-quality captions. We show the adapted video-language model performs well on a wide range of video-language benchmarks. For instance, it surpasses the best prior result on open-ended NExT-QA by 2.8%. Besides, our model generates detailed descriptions for previously unseen videos, which provide better textual supervision than existing methods. Experiments show that a video-language dual-encoder model contrastively trained on these auto-generated captions is 3.8% better than the strongest baseline that also leverages vision-language models. Our best model outperforms state-of-the-art methods on MSR-VTT zero-shot text-to-video retrieval by 6%. As a side product, we generate the largest video capation dataset to date.

关键词： Video analysis

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 << < 24 25 26 27 28 29 30 31 32 33 > >>

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：