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

23,134 篇 会议
91 篇 期刊文献
15 册 图书

馆藏范围

23,239 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

13,630 篇 工学
- 11,162 篇 计算机科学与技术...
- 3,337 篇 软件工程
- 2,414 篇 机械工程
- 1,662 篇 光学工程
- 1,204 篇 电气工程
- 972 篇 控制科学与工程
- 738 篇 信息与通信工程
- 381 篇 仪器科学与技术
- 322 篇 生物工程
- 239 篇 生物医学工程（可授...
- 188 篇 电子科学与技术（可...
- 109 篇 化学工程与技术
- 104 篇 安全科学与工程
- 99 篇 测绘科学与技术
- 85 篇 建筑学
- 82 篇 土木工程
- 82 篇 交通运输工程
- 56 篇 力学（可授工学、理...
3,696 篇 医学
- 3,684 篇 临床医学
- 76 篇 基础医学(可授医学...
3,137 篇 理学
- 1,880 篇 物理学
- 1,604 篇 数学
- 547 篇 统计学（可授理学、...
- 466 篇 生物学
- 243 篇 系统科学
- 107 篇 化学
491 篇 管理学
- 290 篇 图书情报与档案管...
- 212 篇 管理科学与工程(可...
- 74 篇 工商管理
252 篇 艺术学
- 251 篇 设计学（可授艺术学...
58 篇 法学
38 篇 农学
25 篇 教育学
19 篇 经济学
10 篇 军事学
3 篇 文学

主题

10,395 篇 computer vision
3,893 篇 pattern recognit...
3,101 篇 training
2,104 篇 computational mo...
1,897 篇 visualization
1,799 篇 cameras
1,487 篇 feature extracti...
1,475 篇 three-dimensiona...
1,464 篇 shape
1,447 篇 image segmentati...
1,287 篇 robustness
1,234 篇 computer archite...
1,213 篇 semantics
1,112 篇 benchmark testin...
1,111 篇 conferences
1,104 篇 layout
1,093 篇 object detection
1,085 篇 computer science
1,026 篇 codes
907 篇 face recognition

机构

137 篇 univ sci & techn...
124 篇 univ chinese aca...
121 篇 chinese univ hon...
108 篇 tsinghua univers...
108 篇 carnegie mellon ...
105 篇 microsoft resear...
97 篇 zhejiang univ pe...
91 篇 swiss fed inst t...
85 篇 university of sc...
84 篇 zhejiang univers...
81 篇 shanghai ai lab ...
79 篇 university of ch...
75 篇 shanghai jiao to...
69 篇 microsoft res as...
68 篇 alibaba grp peop...
66 篇 adobe research
65 篇 national laborat...
64 篇 peking univ peop...
61 篇 univ oxford oxfo...
59 篇 peng cheng labor...

作者

80 篇 van gool luc
71 篇 timofte radu
65 篇 zhang lei
43 篇 luc van gool
40 篇 yang yi
37 篇 loy chen change
34 篇 li stan z.
33 篇 liu yang
33 篇 xiaoou tang
33 篇 murino vittorio
33 篇 chen chen
33 篇 qi tian
33 篇 li fei-fei
32 篇 tian qi
32 篇 sun jian
30 篇 ying shan
30 篇 pascal fua
29 篇 darrell trevor
28 篇 li xin
28 篇 hanqing lu

语言

23,161 篇 英文
52 篇 其他
20 篇 中文
5 篇 土耳其文
2 篇 日文

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

共 23240 条记录，以下是171-180 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：

Split to Merge: Unifying Separated Modalities for Unsupervised Domain Adaptation

Split to Merge: Unifying Separated Modalities for Unsupervis...

引用

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

作者： Li, Xinyao Li, Yuke Du, Zhekai Li, Fengling Lu, Ke Li, Jingjing Univ Elect Sci & Technol China Chengdu Peoples R China Boston Coll Chestnut Hill MA 02167 USA Univ Technol Sydney Sydney NSW Australia

ISBN: (纸本)9798350353006

Large vision-language models (VLMs) like CLIP have demonstrated good zero-shot learning performance in the unsupervised domain adaptation task. Yet, most transfer approaches for VLMs focus on either the language or visual branches, overlooking the nuanced interplay between both modalities. In this work, we introduce a Unified Modality Separation (UniMoS) framework for unsupervised domain adaptation. Leveraging insights from modality gap studies, we craft a nimble modality separation network that distinctly disentangles CLIP's features into language-associated and vision-associated components. Our proposed Modality-Ensemble Training (MET) method fosters the exchange of modality-agnostic information while maintaining modality-specific nuances. We align features across domains using a modality discriminator. Comprehensive evaluations on three benchmarks reveal our approach sets a new state-of-the-art with minimal computational costs. Code: https://***/TL-UESTC/UniMoS.

关键词： deep learning Unsupervised domain adaptation vision-language model

来源：评论

学校读者我要写书评

暂无评论

One Embedding to Predict Them All: Visible and Thermal Universal Face Representations for Soft Biometric Estimation via vision Transformers

One Embedding to Predict Them All: Visible and Thermal Unive...

引用

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

作者： Mirabet-Herranz, Nelida Galdi, Chiara Dugelay, Jean-Luc EURECOM Campus SophiaTech450 Route Chappes F-06410 Biot France

ISBN: (纸本)9798350365474

Human faces encode a vast amount of information including not only uniquely distinctive features of the individual but also demographic information such as a person's age, gender, and weight. Such information is referred to as soft-biometrics, which are physical, behavioral or adhered human characteristics, classifiable in pre-defined human compliant categories. As we often say 'one look is worth a thousand words'. vision Transformers have emerged as a powerful deep learning architecture able to achieve accurate classifications for different computer vision tasks, but these models have not been yet applied to soft-biometrics. In this work, we propose the Bidirectional Encoder Face representation from image Transformers (BEFiT), a model that leverages the multi-attention mechanisms to capture local and global features and produce a multi-purpose face embedding. This unique embedding enables the estimation of different demographics without having to re-train the model for each soft-biometric trait, ensuring high efficiency without compromising accuracy. Our approach explores the use of visible and thermal images to achieve powerful face embedding in different light spectra. We demonstrate that the BEFiT embeddings can capture essential information for gender, age, and weight estimation, surpassing the performance of dedicated deep learning structures for the estimation of a single soft biometric trait. The code of BEFiT implementation is publicly available(1)

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

Summarize the Past to Predict the Future: Natural Language Descriptions of Context Boost Multimodal Object Interaction Anticipation

Summarize the Past to Predict the Future: Natural Language D...

引用

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

作者： Pasca, Razvan-George Gavryushin, Alexey Hamza, Muhammad Kuo, Yen-Ling Mo, Kaichun Van Gool, Luc Hilliges, Otmar Wang, Xi Swiss Fed Inst Technol Zurich Switzerland Univ Zurich Zurich Switzerland Univ Virginia Charlottesville VA USA NVIDIA Santa Clara CA USA Katholieke Univ Leuven Leuven Belgium INSAIT Sofia Bulgaria

ISBN: (纸本)9798350353006

We study object interaction anticipation in egocentric videos. This task requires an understanding of the spatio-temporal context formed by past actions on objects, coined action context. We propose TransFusion, a multimodal transformer-based architecture for short-term object interaction anticipation. Our method exploits the representational power of language by summarizing the action context textually, after leveraging pre-trained vision-language foundation models to extract the action context from past video frames. The summarized action context and the last observed video frame are processed by the multimodal fusion module to forecast the next object interaction. Experiments on the Ego4D next active object interaction dataset show the effectiveness of our multimodal fusion model and highlight the benefits of using the power of foundation models and language-based context summaries in a task where vision may appear to suffice. Our novel approach outperforms all state-of-the-art methods on both versions of the Ego4D dataset. A project video and code are available at https://***/transfusion-proj/.

关键词： computer vision Egocentric vision Human Behavior Prediction Multimodal Learning Object Interaction Anticipation vision-Language Models

来源：评论

学校读者我要写书评

暂无评论

Task-aligned Part-aware Panoptic Segmentation through Joint Object-Part Representations

Task-aligned Part-aware Panoptic Segmentation through Joint ...

引用

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

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

ISBN: (纸本)9798350353013;9798350353006

Part-aware panoptic segmentation (PPS) requires (a) that each foreground object and background region in an image is segmented and classified, and (b) that all parts within foreground objects are segmented, classified and linked to their parent object. Existing methods approach PPS by separately conducting object-level and part-level segmentation. However, their part-level predictions are not linked to individual parent objects. Therefore, their learning objective is not aligned with the PPS task objective, which harms the PPS performance. To solve this, and make more accurate PPS predictions, we propose Task-Aligned Part-aware Panoptic Segmentation (TAPPS). This method uses a set of shared queries to jointly predict (a) object-level segments, and (b) the part-level segments within those same objects. As a result, TAPPS learns to predict part-level segments that are linked to individual parent objects, aligning the learning objective with the task objective, and allowing TAPPS to leverage joint object-part representations. With experiments, we show that TAPPS considerably outperforms methods that predict objects and parts separately, and achieves new state-of-the-art PPS results.

关键词： computer vision image segmentation panoptic segmentation part segmentation part-aware panoptic segmentation scene understanding semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

QAttn: Efficient GPU Kernels for mixed-precision vision Transformers

QAttn: Efficient GPU Kernels for mixed-precision Vision Tran...

引用

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

作者： Kluska, Piotr Castello, Adrian Scheidegger, Florian Malossi, A. Cristiano I. Quintana-Orti, Enrique S. IBM Res Europe Ruschlikon Switzerland Univ Politecn Valencia Valencia Spain

ISBN: (纸本)9798350365474

vision Transformers have demonstrated outstanding performance in computer vision tasks. Nevertheless, this superior performance for large models comes at the expense of increasing memory usage for storing the parameters and intermediate activations. To accelerate model inference, in this work we develop and evaluate integer and mixed-precision kernels in Triton for the efficient execution of two fundamental building blocks of transformers -linear layer and attention- on graphics processing units (GPUs). On an NVIDIA A100 GPU, our kernel implementations of vision Transformers achieve a throughput speedup of up to 7x compared with reference kernels in PyTorch floating-point single precision (FP32). Additionally, the accuracy for the ViT Large model top-1 drops by less than one percent on the ImageNet1K classification task. We also observe up to 6x increased throughput by applying our kernels to the Segment Anything Model image encoder while keeping the mIOU close to the FP32 reference on the COCO2017 dataset for static and dynamic quantization. Furthermore, our kernels demonstrate improved speed to the TensorRT INT8 linear layer, and we improve the throughput of base FP16 (half precision) Triton attention on average by up to 19 +/- 4.01%. We have open-sourced the QAtnn framework, which is tightly integrated with the PyTorch quantization workflow https://***/IBM/qattn.

关键词： compression instance segmentation object classification quantization vision transformers

来源：评论

学校读者我要写书评

暂无评论

Convolutional Prompting meets Language Models for Continual Learning

Convolutional Prompting meets Language Models for Continual ...

引用

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

作者： Roy, Anurag Moulick, Riddhiman Verma, Vinay K. Ghosh, Saptarshi Das, Abir IIT Kharagpur Kharagpur W Bengal India IML Amazon India Hyderabad India

ISBN: (纸本)9798350353006

Continual Learning (CL) enables machine learning models to learn from continuously shifting new training data in absence of data from old tasks. Recently, pretrained vision transformers combined with prompt tuning have shown promise for overcoming catastrophic forgetting in CL. These approaches rely on a pool of learnable prompts which can be inefficient in sharing knowledge across tasks leading to inferior performance. In addition, the lack of fine-grained layer specific prompts does not allow these to fully express the strength of the prompts for CL. We address these limitations by proposing ConvPrompt, a novel convolutional prompt creation mechanism that maintains layer-wise shared embeddings, enabling both layer-specific learning and better concept transfer across tasks. The intelligent use of convolution enables us to maintain a low parameter overhead without compromising performance. We further leverage Large Language Models to generate fine-grained text descriptions of each category which are used to get task similarity and dynamically decide the number of prompts to be learned. Extensive experiments demonstrate the superiority of ConvPrompt and improves SOTA by 3% with significantly less parameter overhead. We also perform strong ablation over various modules to disentangle the importance of different components.(1)

关键词： Continual Learning Language Models Prompt Tuning vision Transformer

来源：评论

学校读者我要写书评

暂无评论

AM-RADIO: Agglomerative vision Foundation Model Reduce All Domains Into One

AM-RADIO: Agglomerative Vision Foundation Model Reduce All D...

引用

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

作者： Ranzinger, Mike Heinrich, Greg Kautz, Jan Molchanov, Pavlo NVIDIA Santa Clara CA 95051 USA

ISBN: (纸本)9798350353006

A handful of visual foundation models (VFMs) have recently emerged as the backbones for numerous downstream tasks. VFMs like CLIP, DINOv2, SAM are trained with distinct objectives, exhibiting unique characteristics for various downstream tasks. We find that despite their conceptual differences, these models can be effectively merged into a unified model through multi-teacher distillation. We name this approach AM-RADIO (Agglomerative Model - Reduce All Domains Into One). This integrative approach not only surpasses the performance of individual teacher models but also amalgamates their distinctive features, such as zero-shot vision-language comprehension, detailed pixel-level understanding, and open vocabulary segmentation capabilities. Additionally, in pursuit of the most hardware-efficient backbone, we evaluated numerous architectures in our multi-teacher distillation pipeline using the same training recipe. This led to the development of a novel architecture (E-RADIO) that exceeds the performance of its predecessors and is at least 6x faster than the teacher models at matched resolution. Our comprehensive benchmarking process covers downstream tasks including ImageNet classification, semantic segmentation linear probing, COCO object detection and integration into LLaVa-1.5. Code: https://***/NVlabs/RADIO.

关键词： Distillation Knowledge Distillation Semantic Segmentation Visual Foundation Model Visual Large Language Models Zero Shot Classification

来源：评论

学校读者我要写书评

暂无评论

Transductive Zero-Shot and Few-Shot CLIP

Transductive Zero-Shot and Few-Shot CLIP

引用

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

作者： Martin, Segolene Huang, Yunshi Shakeri, Fereshteh Pesquet, Jean-Christophe Ben Ayed, Ismail Univ Paris Saclay CVN Cent Supelec INRIA Paris France ETS Montreal Montreal PQ Canada

ISBN: (纸本)9798350353006

Transductive inference has been widely investigated in few-shot image classification, but completely overlooked in the recent, fast growing literature on adapting vision-langage models like CLIP. This paper addresses the transductive zero-shot and few-shot CLIP classification challenge, in which inference is performed jointly across a mini-batch of unlabeled query samples, rather than treating each instance independently. We initially construct informative vision-text probability features, leading to a classification problem on the unit simplex set. Inspired by Expectation-Maximization (EM), our optimization-based classification objective models the data probability distribution for each class using a Dirichlet law. The minimization problem is then tackled with a novel block Majorization-Minimization algorithm, which simultaneously estimates the distribution parameters and class assignments. Extensive numerical experiments on 11 datasets underscore the benefits and efficacy of our batch inference approach. On zero-shot tasks with test batches of 75 samples, our approach yields near 20% improvement in ImageNet accuracy over CLIP's zero-shot performance. Additionally, we outperform state-of-the-art methods in the few-shot setting. The code is available at: https://***/SegoleneMartin/transductive-CLIP.

关键词： expectation-maximization few-shot text-vision models transductive learning zero-shot

来源：评论

学校读者我要写书评

暂无评论

Fair-VPT: Fair Visual Prompt Tuning for Image Classification

Fair-VPT: Fair Visual Prompt Tuning for Image Classification

引用

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

作者： Park, Sungho Byun, Hy Eran Yonsei Univ Seoul South Korea

ISBN: (纸本)9798350353006

Despite the remarkable success of vision Transformers (ViT) across diverse fields in computer vision, they have a clear drawback of expensive adaption cost for downstream tasks due to the increased scale. To address this, Visual Prompt Tuning (VPT) incorporates learnable parameters in the input space of ViT. While freezing the ViT backbone and tuning only the prompts, it exhibits superior performances to full fine-tuning. However, despite the outstanding advantage, we point out that VPT may lead to serious unfairness in downstream classification. Initially, we investigate the causes of unfairness in VPT, identifying the biasedly pre-trained ViT as a principal factor. Motivated by this observation, we propose a Fair Visual Prompt Tuning (Fair-VPT) which removes biased information in the pre-trained ViT while adapting it to downstream classification tasks. To this end, we categorize prompts into "cleaner prompts" and "target prompts". Based on this, we encode the class token in two different ways by either masking or not masking the target prompts in the self-attention process. These encoded tokens are trained with distinct objective functions, resulting in the inclusion of different information in the target and cleaner prompts. Moreover, we introduce a disentanglement loss based on contrastive learning to further decorrelate them. In experiments across diverse benchmarks, the proposed method demonstrates the most superior performance in terms of balanced classification accuracy and fairness.

关键词： FAI Fair-VPT Fairness Large vision Model vision Transformer Visual Prompt Tuning ViT VPT

来源：评论

学校读者我要写书评

暂无评论

H-ViT: A Hierarchical vision Transformer for Deformable Image Registration

H-ViT: A Hierarchical Vision Transformer for Deformable Imag...

引用

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

作者： Ghahremani, Morteza Khateri, Mohammad Jian, Bailiang Wiestler, Benedikt Adeli, Ehsan Wachinger, Christian Tech Univ Munich Munich Germany Munich Ctr Machine Learning Munich Germany Univ Eastern Finland Espoo Finland Stanford Univ Stanford CA 94305 USA

ISBN: (纸本)9798350353006

This paper introduces a novel top-down representation approach for deformable image registration, which estimates the deformation field by capturing various short-and long-range flow features at different scale levels. As a Hierarchical vision Transformer (H-ViT), we propose a dual self-attention and cross-attention mechanism that uses high-level features in the deformation field to represent low-level ones, enabling information streams in the deformation field across all voxel patch embeddings irrespective of their spatial proximity. Since high-level features contain abstract flow patterns, such patterns are expected to effectively contribute to the representation of the deformation field in lower scales. When the self-attention module utilizes within-scale short-range patterns for representation, the cross-attention modules dynamically look for the key tokens across different scales to further interact with the local query voxel patches. Our method shows superior accuracy and visual quality over the state-of-the-art registration methods in five publicly available datasets, highlighting a substantial enhancement in the performance of medical imaging registration. The project link is available at https://***/hvit.

关键词： Deformable Image Registration Hierarchical cross-attention Medical Imaging vision Transformer

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 << < 14 15 16 17 18 19 20 21 22 23 > >>

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：