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

20,994 篇 会议
99 册 图书
85 篇 期刊文献
1 篇 学位论文

馆藏范围

21,178 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

13,603 篇 工学
- 11,179 篇 计算机科学与技术...
- 2,631 篇 机械工程
- 2,542 篇 软件工程
- 990 篇 光学工程
- 849 篇 电气工程
- 676 篇 控制科学与工程
- 487 篇 信息与通信工程
- 242 篇 仪器科学与技术
- 215 篇 测绘科学与技术
- 159 篇 生物医学工程（可授...
- 150 篇 生物工程
- 139 篇 电子科学与技术（可...
- 69 篇 安全科学与工程
- 67 篇 化学工程与技术
- 55 篇 建筑学
- 53 篇 土木工程
- 43 篇 力学（可授工学、理...
- 41 篇 航空宇航科学与技...
3,462 篇 医学
- 3,452 篇 临床医学
- 41 篇 基础医学(可授医学...
2,483 篇 理学
- 1,247 篇 数学
- 1,213 篇 物理学
- 446 篇 统计学（可授理学、...
- 418 篇 生物学
- 269 篇 系统科学
- 67 篇 化学
424 篇 管理学
- 218 篇 管理科学与工程(可...
- 217 篇 图书情报与档案管...
- 43 篇 工商管理
144 篇 艺术学
- 142 篇 设计学（可授艺术学...
41 篇 法学
31 篇 农学
12 篇 经济学
10 篇 教育学
6 篇 文学
3 篇 军事学

主题

8,072 篇 computer vision
2,879 篇 pattern recognit...
2,859 篇 training
1,808 篇 computational mo...
1,718 篇 visualization
1,478 篇 cameras
1,381 篇 shape
1,374 篇 face recognition
1,364 篇 three-dimensiona...
1,342 篇 feature extracti...
1,269 篇 image segmentati...
1,156 篇 robustness
1,109 篇 semantics
982 篇 layout
978 篇 object detection
953 篇 computer archite...
952 篇 benchmark testin...
931 篇 codes
918 篇 object recogniti...
899 篇 computer science

机构

174 篇 univ sci & techn...
154 篇 carnegie mellon ...
149 篇 univ chinese aca...
144 篇 chinese univ hon...
110 篇 microsoft resear...
104 篇 zhejiang univ pe...
98 篇 swiss fed inst t...
93 篇 tsinghua univ pe...
92 篇 tsinghua univers...
90 篇 microsoft res as...
88 篇 shanghai ai lab ...
83 篇 zhejiang univers...
76 篇 alibaba grp peop...
74 篇 hong kong univ s...
73 篇 university of sc...
72 篇 peking univ peop...
68 篇 shanghai jiao to...
68 篇 university of ch...
66 篇 google res mount...
66 篇 univ oxford oxfo...

作者

83 篇 van gool luc
71 篇 zhang lei
60 篇 timofte radu
49 篇 yang yi
49 篇 luc van gool
48 篇 xiaoou tang
43 篇 darrell trevor
43 篇 tian qi
42 篇 loy chen change
42 篇 sun jian
41 篇 qi tian
37 篇 vasconcelos nuno
37 篇 liu yang
37 篇 chen xilin
37 篇 li fei-fei
36 篇 liu xiaoming
36 篇 shan shiguang
36 篇 li stan z.
36 篇 torralba antonio
33 篇 zhou jie

语言

21,129 篇 英文
31 篇 中文
12 篇 其他
5 篇 土耳其文
2 篇 日文

检索条件"任意字段=2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011"

共 21179 条记录，以下是1321-1330 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：

Calibrating Higher-Order Statistics for Few-Shot Class-Incremental Learning with Pre-trained vision Transformers

Calibrating Higher-Order Statistics for Few-Shot Class-Incre...

引用

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

作者： Goswami, Dipam Twardowski, Bartlomiej van de Weijer, Joost Univ Autonoma Barcelona Dept Comp Sci Barcelona Spain Comp Vis Ctr Barcelona Spain IDEAS NCBR Warsaw Poland

ISBN: (纸本)9798350365474

Few-shot class-incremental learning (FSCIL) aims to adapt the model to new classes from very few data (5 samples) without forgetting the previously learned classes. Recent works in many-shot CIL (MSCIL) (using all available training data) exploited pre-trained models to reduce forgetting and achieve better plasticity. In a similar fashion, we use ViT models pre-trained on large-scale datasets for few-shot settings, which face the critical issue of low plasticity. FSCIL methods start with a many-shot first task to learn a very good feature extractor and then move to the few-shot setting from the second task onwards. While the focus of most recent studies is on how to learn the many-shot first task so that the model generalizes to all future few-shot tasks, we explore in this work how to better model the few-shot data using pre-trained models, irrespective of how the first task is trained. Inspired by recent works in MSCIL, we explore how using higher-order feature statistics can influence the classification of few-shot classes. We identify the main challenge of obtaining a good covariance matrix from few-shot data and propose to calibrate the covariance matrix for new classes based on semantic similarity to the many-shot base classes. Using the calibrated feature statistics in combination with existing methods significantly improves few-shot continual classification on several FSCIL benchmarks. Code is available at https://***/dipamgoswami/FSCIL-Calibration.

关键词： Continual Learning Few-Shot Class-Incremental Learning

来源：评论

学校读者我要写书评

暂无评论

MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical vision Transformers

MixMAE: Mixed and Masked Autoencoder for Efficient Pretraini...

引用

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

作者： Liu, Jihao Huang, Xin Zheng, Jinliang Liu, Yu Li, Hongsheng CUHK MMLab Shenzhen Peoples R China SenseTime Res Hong Kong Peoples R China InnoHK CPII Hong Kong Peoples R China

ISBN: (纸本)9798350301298

In this paper, we propose Mixed and Masked AutoEncoder (MixMAE), a simple but efficient pretraining method that is applicable to various hierarchical vision Transformers. Existing masked image modeling (MIM) methods for hierarchical vision Transformers replace a random subset of input tokens with a special [MASK] symbol and aim at reconstructing original image tokens from the corrupted image. However, we find that using the [MASK] symbol greatly slows down the training and causes pretraining-finetuning inconsistency, due to the large masking ratio (e.g., 60% in SimMIM). On the other hand, MAE does not introduce [MASK] tokens at its encoder at all but is not applicable for hierarchical vision Transformers. To solve the issue and accelerate the pretraining of hierarchical models, we replace the masked tokens of one image with visible tokens of another image, i.e., creating a mixed image. We then conduct dual reconstruction to reconstruct the two original images from the mixed input, which significantly improves efficiency. While MixMAE can be applied to various hierarchical Transformers, this paper explores using Swin Transformer with a large window size and scales up to huge model size (to reach 600M parameters). Empirical results demonstrate that MixMAE can learn high-quality visual representations efficiently. Notably, MixMAE with Swin-B/W14 achieves 85.1% top-1 accuracy on ImageNet-1K by pretraining for 600 epochs. Besides, its transfer performances on the other 6 datasets show that MixMAE has better FLOPs / performance tradeoff than previous popular MIM methods.

关键词： Self-supervised or unsupervised representation learning

来源：评论

学校读者我要写书评

暂无评论

Decomposed Soft Prompt Guided Fusion Enhancing for Compositional Zero-Shot Learning

Decomposed Soft Prompt Guided Fusion Enhancing for Compositi...

引用

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

作者： Lu, Xiaocheng Guo, Song Liu, Ziming Guo, Jingcai Hong Kong Polytech Univ Dept Comp Hong Kong Peoples R China Hong Kong Polytech Univ Shenzhen Res Inst Hong Kong Peoples R China

ISBN: (纸本)9798350301298

Compositional Zero-Shot Learning (CZSL) aims to recognize novel concepts formed by known states and objects during training. Existing methods either learn the combined state-object representation, challenging the generalization of unseen compositions, or design two classifiers to identify state and object separately from image features, ignoring the intrinsic relationship between them. To jointly eliminate the above issues and construct a more robust CZSL system, we propose a novel framework termed Decomposed Fusion with Soft Prompt (DFSP)1, by involving vision-language models (VLMs) for unseen composition recognition. Specifically, DFSP constructs a vector combination of learnable soft prompts with state and object to establish the joint representation of them. In addition, a cross-modal decomposed fusion module is designed between the language and image branches, which decomposes state and object among language features instead of image features. Notably, being fused with the decomposed features, the image features can be more expressive for learning the relationship with states and objects, respectively, to improve the response of unseen compositions in the pair space, hence narrowing the domain gap between seen and unseen sets. Experimental results on three challenging benchmarks demonstrate that our approach significantly outperforms other state-of-the-art methods by large margins.

关键词： Low-level vision

来源：评论

学校读者我要写书评

暂无评论

Event-guided Person Re-Identification via Sparse-Dense Complementary Learning

Event-guided Person Re-Identification via Sparse-Dense Compl...

引用

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

作者： Cao, Chengzhi Fu, Xueyang Liu, Hongjian Huang, Yukun Wang, Kunyu Luo, Jiebo Zha, Zheng-Jun Univ Sci & Technol China Hefei Peoples R China Univ Rochester Rochester NY 14627 USA

ISBN: (纸本)9798350301298

Video-based person re-identification (Re-ID) is a prominent computer vision topic due to its wide range of video surveillance applications. Most existing methods utilize spatial and temporal correlations in frame sequences to obtain discriminative person features. However, inevitable degradation, e.g., motion blur contained in frames, leading to the loss of identity-discriminating cues. Recently, a new bio-inspired sensor called event camera, which can asynchronously record intensity changes, brings new vitality to the Re-ID task. With the microsecond resolution and low latency, it can accurately capture the movements of pedestrians even in the degraded environments. In this work, we propose a Sparse-Dense Complementary Learning (SDCL) Framework, which effectively extracts identity features by fully exploiting the complementary information of dense frames and sparse events. Specifically, for frames, we build a CNN-based module to aggregate the dense features of pedestrian appearance step by step, while for event streams, we design a bio-inspired spiking neural network (SNN) backbone, which encodes event signals into sparse feature maps in a spiking form, to extract the dynamic motion cues of pedestrians. Finally, a cross feature alignment module is constructed to fuse motion information from events and appearance cues from frames to enhance identity representation learning. Experiments on several benchmarks show that by employing events and SNN into Re-ID, our method significantly outperforms competitive methods. The code is available at https://***/ChengzhiCao/SDCL.

关键词： detection recognition: Categorization retrieval

来源：评论

学校读者我要写书评

暂无评论

Siamese Image Modeling for Self-Supervised vision Representation Learning

Siamese Image Modeling for Self-Supervised Vision Representa...

引用

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

作者： Tao, Chenxin Zhu, Xizhou Su, Weijie Huang, Gao Li, Bin Zhou, Jie Qiao, Yu Wang, Xiaogang Dai, Jifeng Tsinghua Univ Beijing Peoples R China SenseTime Res Hong Kong Peoples R China Univ Sci & Technol China Hefei Peoples R China Shanghai Artificial Intelligence Lab Shanghai Peoples R China Chinese Univ Hong Kong Hong Kong Peoples R China

ISBN: (纸本)9798350301298

Self-supervised learning (SSL) has delivered superior performance on a variety of downstream vision tasks. Two main-stream SSL frameworks have been proposed, i.e., Instance Discrimination (ID) and Masked Image Modeling (MIM). ID pulls together representations from different views of the same image, while avoiding feature collapse. It lacks spatial sensitivity, which requires modeling the local structure within each image. On the other hand, MIM reconstructs the original content given a masked image. It instead does not have good semantic alignment, which requires projecting semantically similar views into nearby representations. To address this dilemma, we observe that (1) semantic alignment can be achieved by matching different image views with strong augmentations;(2) spatial sensitivity can benefit from predicting dense representations with masked images. Driven by these analysis, we propose Siamese Image Modeling (SiameseIM), which predicts the dense representations of an augmented view, based on another masked view from the same image but with different augmentations. SiameseIM uses a Siamese network with two branches. The online branch encodes the first view, and predicts the second view's representation according to the relative positions between these two views. The target branch produces the target by encoding the second view. SiameseIM can surpass both ID and MIM on a wide range of downstream tasks, including ImageNet finetuning and linear probing, COCO and LVIS detection, and ADE20k semantic segmentation. The improvement is more significant in few-shot, long-tail and robustness-concerned scenarios. Code shall be released.

关键词： detection recognition: Categorization retrieval

来源：评论

学校读者我要写书评

暂无评论

Context-aware Alignment and Mutual Masking for 3D-Language Pre-training

Context-aware Alignment and Mutual Masking for 3D-Language P...

引用

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

作者： Jin, Zhao Hayat, Munawar Yang, Yuwei Guo, Yulan Lei, Yinjie Sichuan Univ Chengdu Peoples R China Monash Univ Melbourne Vic Australia Sun Yat Sen Univ Guangzhou Peoples R China

ISBN: (纸本)9798350301298

3D visual language reasoning plays an important role in effective human-computer interaction. The current approaches for 3D visual reasoning are task-specific, and lack pre-training methods to learn generic representations that can transfer across various tasks. Despite the encouraging progress in vision-language pre-training for image-text data, 3D-language pre-training is still an open issue due to limited 3D-language paired data, highly sparse and irregular structure of point clouds and ambiguities in spatial relations of 3D objects with viewpoint changes. In this paper, we present a generic 3D-language pre-training approach, that tackles multiple facets of 3D-language reasoning by learning universal representations. Our learning objective constitutes two main parts. 1) Context aware spatial-semantic alignment to establish fine-grained correspondence between point clouds and texts. It reduces relational ambiguities by aligning 3D spatial relationships with textual semantic context. 2) Mutual 3D-Language Masked modeling to enable cross-modality information exchange. Instead of reconstructing sparse 3D points for which language can hardly provide cues, we propose masked proposal reasoning to learn semantic class and mask-invariant representations. Our proposed 3D-language pre-training method achieves promising results once adapted to various downstream tasks, including 3D visual grounding, 3D dense captioning and 3D question answering. Our codes are available at https://***/leolyj/3D-VLP

关键词： language reasoning vision

来源：评论

学校读者我要写书评

暂无评论

CVT-SLR: Contrastive Visual-Textual Transformation for Sign Language recognition with Variational Alignment

CVT-SLR: Contrastive Visual-Textual Transformation for Sign ...

引用

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

作者： Zheng, Jiangbin Wang, Yile Tan, Cheng Li, Siyuan Wang, Ge Xia, Jun Chen, Yidong Li, Stan Z. Westlake Univ AI Lab Res Ctr Ind Future Hangzhou Peoples R China Tsinghua Univ Inst AI Ind Res AIR Beijing Peoples R China Xiamen Univ Sch Informat Xiamen Peoples R China

ISBN: (纸本)9798350301298

Sign language recognition (SLR) is a weakly supervised task that annotates sign videos as textual glosses. Recent studies show that insufficient training caused by the lack of large-scale available sign datasets becomes the main bottleneck for SLR. Most SLR works thereby adopt pretrained visual modules and develop two mainstream solutions. The multi-stream architectures extend multi-cue visual features, yielding the current SOTA performances but requiring complex designs and might introduce potential noise. Alternatively, the advanced single-cue SLR frameworks using explicit cross-modal alignment between visual and textual modalities are simple and effective, potentially competitive with the multi-cue framework. In this work, we propose a novel contrastive visual-textual transformation for SLR, CVT-SLR, to fully explore the pretrained knowledge of both the visual and language modalities. Based on the single-cue cross-modal alignment framework, we propose a variational autoencoder (VAE) for pretrained contextual knowledge while introducing the complete pretrained language module. The VAE implicitly aligns visual and textual modalities while benefiting from pretrained contextual knowledge as the traditional contextual module. Meanwhile, a contrastive cross-modal alignment algorithm is designed to explicitly enhance the consistency constraints. Extensive experiments on public datasets (PHOENIX-2014 and PHOENIX-2014T) demonstrate that our proposed CVT-SLR consistently outperforms existing single-cue methods and even outperforms SOTA multi-cue methods. The source codes and models are available at https://***/binbinjiang/CVT-SLR.

关键词： language reasoning vision

来源：评论

学校读者我要写书评

暂无评论

The Casual Conversations v2 Dataset A diverse, large benchmark for measuring fairness and robustness in audio/vision/speech models

The Casual Conversations v2 Dataset A diverse, large benchma...

引用

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

作者： Porgali, Bilal Albiero, Vitor Ryda, Jordan Ferrer, Cristian Canton Hazirbas, Caner Meta AI Menlo Pk CA 94025 USA

ISBN: (纸本)9798350302493

This paper introduces a new large consent-driven dataset aimed at assisting in the evaluation of algorithmic bias and robustness of computer vision and audio speech models in regards to 11 attributes that are self-provided or labeled by trained annotators. The dataset includes 26,467 videos of 5,567 unique paid participants, with an average of almost 5 videos per person, recorded in Brazil, India, Indonesia, Mexico, Vietnam, Philippines, and the USA, representing diverse demographic characteristics. The participants agreed for their data to be used in assessing fairness of AI models and provided self-reported age, gender, language/dialect, disability status, physical adornments, physical attributes and geo-location information, while trained annotators labeled apparent skin tone using the Fitzpatrick Skin Type and Monk Skin Tone scales, and voice timbre. Annotators also labeled for different recording setups and per-second activity annotations.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Dual Alignment Unsupervised Domain Adaptation for Video-Text Retrieval

Dual Alignment Unsupervised Domain Adaptation for Video-Text...

引用

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

作者： Hao, Xiaoshuai Zhang, Wanqian Wu, Dayan Zhu, Fei Li, Bo Chinese Acad Sci Inst Informat Engn Beijing Peoples R China Univ Chinese Acad Sci Sch Cyber Secur Beijing Peoples R China

ISBN: (纸本)9798350301298

Video-text retrieval is an emerging stream in both computer vision and natural language processing communities, which aims to find relevant videos given text queries. In this paper, we study the notoriously challenging task, i.e., Unsupervised Domain Adaptation Video-text Retrieval (UDAVR), wherein training and testing data come from different distributions. Previous works merely alleviate the domain shift, which however overlook the pairwise misalignment issue in target domain, i.e., there exist no semantic relationships between target videos and texts. To tackle this, we propose a novel method named Dual Alignment Domain Adaptation (DADA). Specifically, we first introduce the cross-modal semantic embedding to generate discriminative source features in a joint embedding space. Besides, we utilize the video and text domain adaptations to smoothly balance the minimization of the domain shifts. To tackle the pairwise misalignment in target domain, we propose the Dual Alignment Consistency (DAC) to fully exploit the semantic information of both modalities in target domain. The proposed DAC adaptively aligns the video-text pairs which are more likely to be relevant in target domain, enabling that positive pairs are increasing progressively and the noisy ones will potentially be aligned in the later stages. To that end, our method can generate more truly aligned target pairs and ensure the discriminability of target features. Compared with the state-of-the-art methods, DADA achieves 20.18% and 18.61% relative improvements on R@1 under the setting of TGIF -> MSR-VTT and TGIF -> MSVD respectively, demonstrating the superiority of our method.

关键词： language reasoning vision

来源：评论

学校读者我要写书评

暂无评论

Visual Language Pretrained Multiple Instance Zero-Shot Transfer for Histopathology Images

Visual Language Pretrained Multiple Instance Zero-Shot Trans...

引用

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

作者： Lu, Ming Y. Chen, Bowen Zhang, Andrew Williamson, Drew F. K. Chen, Richard J. Ding, Tong Le, Long Phi Chuang, Yung-Sung Mahmood, Faisal MIT Cambridge MA 02139 USA Harvard Univ Cambridge MA 02138 USA Mass Gen Brigham Boston MA 02199 USA

ISBN: (纸本)9798350301298

Contrastive visual language pretraining has emerged as a powerful method for either training new language-aware image encoders or augmenting existing pretrained models with zero-shot visual recognition capabilities. However, existing works typically train on large datasets of image-text pairs and have been designed to perform downstream tasks involving only small to medium sized-images, neither of which are applicable to the emerging field of computational pathology where there are limited publicly available paired image-text datasets and each image can span up to 100,000 x 100,000 pixels. In this paper we present MI-Zero, a simple and intuitive framework for unleashing the zero-shot transfer capabilities of contrastively aligned image and text models on gigapixel histopathology whole slide images, enabling multiple downstream diagnostic tasks to be carried out by pretrained encoders without requiring any additional labels. MI-Zero reformulates zero-shot transfer under the framework of multiple instance learning to overcome the computational challenge of inference on extremely large images. We used over 550k pathology reports and other available in-domain text corpora to pre-train our text encoder. By effectively leveraging strong pre-trained encoders, our best model pretrained on over 33k histopathology image-caption pairs achieves an average median zero-shot accuracy of 70.2% across three different real-world cancer subtyping tasks. Our code is available at: https://***/mahmoodlab/MI-Zero.

关键词： cell microscopy Medical and biological 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500页 << < 129 130 131 132 133 134 135 136 137 138 > >>

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：