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

8,905 篇 会议
43 篇 期刊文献
18 册 图书

馆藏范围

8,965 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

4,564 篇 工学
- 4,024 篇 计算机科学与技术...
- 2,182 篇 软件工程
- 1,241 篇 光学工程
- 558 篇 控制科学与工程
- 433 篇 信息与通信工程
- 430 篇 机械工程
- 294 篇 电气工程
- 288 篇 仪器科学与技术
- 179 篇 生物工程
- 159 篇 生物医学工程（可授...
- 119 篇 电子科学与技术（可...
- 64 篇 安全科学与工程
- 58 篇 建筑学
- 58 篇 化学工程与技术
- 52 篇 土木工程
- 52 篇 交通运输工程
- 40 篇 力学（可授工学、理...
2,066 篇 理学
- 1,382 篇 物理学
- 1,198 篇 数学
- 420 篇 统计学（可授理学、...
- 238 篇 生物学
- 55 篇 化学
- 36 篇 系统科学
266 篇 管理学
- 182 篇 图书情报与档案管...
- 92 篇 管理科学与工程(可...
- 47 篇 工商管理
223 篇 医学
- 222 篇 临床医学
- 39 篇 基础医学(可授医学...
205 篇 艺术学
- 205 篇 设计学（可授艺术学...
45 篇 法学
- 43 篇 社会学
21 篇 农学
14 篇 教育学
9 篇 经济学
6 篇 军事学

主题

3,414 篇 computer vision
1,216 篇 pattern recognit...
946 篇 cameras
908 篇 conferences
765 篇 computer science
674 篇 image segmentati...
618 篇 layout
598 篇 training
548 篇 shape
518 篇 robustness
451 篇 feature extracti...
448 篇 humans
445 篇 face recognition
405 篇 computational mo...
402 篇 object detection
365 篇 visualization
356 篇 computer archite...
336 篇 application soft...
304 篇 lighting
257 篇 image reconstruc...

机构

41 篇 microsoft resear...
30 篇 department of co...
25 篇 department of co...
23 篇 institute for co...
22 篇 department of co...
22 篇 school of comput...
20 篇 university of sc...
20 篇 swiss fed inst t...
19 篇 tsinghua univers...
19 篇 institute of com...
18 篇 swiss fed inst t...
17 篇 the robotics ins...
17 篇 carnegie mellon ...
17 篇 computer vision ...
17 篇 department of co...
16 篇 institute of inf...
16 篇 school of comput...
15 篇 school of comput...
15 篇 carnegie mellon ...
14 篇 national laborat...

作者

57 篇 timofte radu
25 篇 huang thomas s.
24 篇 van gool luc
23 篇 s.k. nayar
22 篇 nayar shree k.
22 篇 t. kanade
21 篇 jain anil k.
20 篇 luc van gool
19 篇 t.s. huang
18 篇 xiaoou tang
18 篇 murino vittorio
18 篇 horst bischof
17 篇 a.k. jain
17 篇 t. darrell
16 篇 g. healey
16 篇 bowyer kevin w.
16 篇 bischof horst
15 篇 m.j. black
15 篇 li stan z.
15 篇 m. shah

语言

8,904 篇 英文
53 篇 其他
8 篇 中文
1 篇 土耳其文

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

共 8966 条记录，以下是1111-1120 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：

Exploring the Zero-Shot Capabilities of vision-Language Models for Improving Gaze Following

Exploring the Zero-Shot Capabilities of Vision-Language Mode...

引用

ieee computer society conference on computer vision and pattern recognition workshops (CVPRW)

作者： Anshul Gupta Pierre Vuillecard Arya Farkhondeh Jean-Marc Odobez Idiap Research Institute Martigny Switzerland École Polytechnique Fédérale de Lausanne Switzerland

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Contextual cues related to a person’s pose and interactions with objects and other people in the scene can provide valuable information for gaze following. While existing methods have focused on dedicated cue extraction methods, in this work we investigate the zero-shot capabilities of vision-Language Models (VLMs) for extracting a wide array of contextual cues to improve gaze following performance. We first evaluate various VLMs, prompting strategies, and in-context learning (ICL) techniques for zero-shot cue recognition performance. We then use these insights to extract contextual cues for gaze following, and investigate their impact when incorporated into a state of the art model for the task. Our analysis indicates that BLIP-2 is the overall top performing VLM and that ICL can improve performance. We also observe that VLMs are sensitive to the choice of the text prompt although ensembling over multiple text prompts can provide more robust performance. Additionally, we discover that using the entire image along with an ellipse drawn around the target person is the most effective strategy for visual prompting. For gaze following, incorporating the extracted cues results in better generalization performance, especially when considering a larger set of cues, highlighting the potential of this approach.

关键词： Visualization computer vision conferences Computational modeling Predictive models pattern recognition Context modeling

来源：评论

学校读者我要写书评

暂无评论

A Closer Look at Self-training for Zero-Label Semantic Segmentation

A Closer Look at Self-training for Zero-Label Semantic Segme...

引用

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

作者： Pastore, Giuseppe Cermelli, Fabio Xian, Yongqin Mancini, Massimiliano Akata, Zeynep Caputo, Barbara Politecn Torino Turin Italy Italian Inst Technol Genoa Italy MPI Informat Saarbrucken Germany Univ Tubingen Tubingen Germany MPI Intelligent Syst Saarbrucken Germany

ISBN: (纸本)9781665448994

Being able to segment unseen classes not observed during training is an important technical challenge in deep learning, because of its potential to reduce the expensive annotation required for semantic segmentation. Prior zero-label semantic segmentation works approach this task by learning visual-semantic embeddings or generative models. However, they are prone to overfitting on the seen classes because there is no training signal for them. In this paper, we study the challenging generalized zero-label semantic segmentation task where the model has to segment both seen and unseen classes at test time. We assume that pixels of unseen classes could be present in the training images but without being annotated. Our idea is to capture the latent information on unseen classes by supervising the model with self-produced pseudo-labels for unlabeled pixels. We propose a consistency regularizer to filter out noisy pseudolabels by taking the intersections of the pseudo-labels generated from different augmentations of the same image. Our framework generates pseudo-labels and then retrain the model with human-annotated and pseudo-labelled data. This procedure is repeated for several iterations. As a result, our approach achieves the new state-of-the-art on PascalVOC12 and COCO-stuff datasets in the challenging generalized zero-label semantic segmentation setting, surpassing other existing methods addressing this task with more complex strategies. Code can be found at https: //***/giuseppepastore10/STRICT.

关键词： Training Image segmentation Semantics Pipelines Predictive models Information filters pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Phenology Alignment Network: A Novel Framework for Cross-Regional Time Series Crop Classification

Phenology Alignment Network: A Novel Framework for Cross-Reg...

引用

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

作者： Wang, Ziqiao Zhang, Hongyan He, Wei Zhang, Liangpei Wuhan Univ State Key Lab Informat Engn Surveying Mapping & R Wuhan 430079 Peoples R China RIKEN Ctr Adv Intelligence Project AIP Tokyo 1030027 Japan

ISBN: (纸本)9781665448994

Timely and accurate crop type classification plays an essential role in the study of agricultural application. However, large area or cross-regional crop classification confronts huge challenges owing to dramatic phenology discrepancy among training and test regions. In this work, we propose a novel framework to address these challenges based on deep recurrent network and unsupervised domain adaptation (DA). Specifically, we firstly propose a Temporal Spatial Network (TSNet) for pixelwise crop classification, which contains stacked RNN and self-attention module to adaptively extract multi-level features from crop samples under various planting conditions. To deal with the cross-regional challenge, an unsupervised DA-based framework named Phenology Alignment Network (PAN) is proposed. PAN consists of two branches of two identical TSNet pre-trained on source domain;one branch takes source samples while the other takes target samples as input. Through aligning the hierarchical deep features extracted from two branches, the discrepancy between two regions is decreased and the pre-trained model is adapted to the target domain without using target label information. As another contribution, a time series dataset based on Sentinel-2 was annotated containing winter crop samples collected on three study sites of China. Cross-regional experiments demonstrate that TSNet shows comparable accuracy to state-of-the-art methods, and PAN further improves the overall accuracy by 5.62%, and macro average F1 score by 0.094 unsupervisedly.

关键词： Training computer vision Adaptation models conferences Time series analysis Feature extraction Agriculture

来源：评论

学校读者我要写书评

暂无评论

Boosting Co-teaching with Compression Regularization for Label Noise

Boosting Co-teaching with Compression Regularization for Lab...

引用

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

作者： Chen, Yingyi Shen, Xi Hu, Shell Xu Suykens, Johan A. K. Katholieke Univ Leuven ESAT STADIUS Leuven Belgium UPE Ecole Ponts LIGM UMR 8049 Champs Sur Marne France Upload AI LLC Houston TX USA

ISBN: (纸本)9781665448994

In this paper, we study the problem of learning image classification models in the presence of label noise. We revisit a simple compression regularization named Nested Dropout [22]. We find that Nested Dropout [22], though originally proposed to perform fast information retrieval and adaptive data compression, can properly regularize a neural network to combat label noise. Moreover, owing to its simplicity, it can be easily combined with Co-teaching [5] to further boost the performance. Our final model remains simple yet effective: it achieves comparable or even better performance than the state-of-the-art approaches on two real-world datasets with label noise which are Clothing1M [28] and ANIMAL-10N [24]. On Clothing1M [28], our approach obtains 74.9% accuracy which is slightly better than that of DivideMix [12]. On ANIMAL-10N [24], we achieve 84.1% accuracy while the best public result by PLC [30] is 83.4%. We hope that our simple approach can be served as a strong baseline for learning with label noise. Our implementation is available at https://***/yingyichen-cyy/Nested-Co-teaching.

关键词： Adaptation models computer vision Image coding conferences Neural networks Data compression Information retrieval

来源：评论

学校读者我要写书评

暂无评论

DeCAtt: Efficient vision Transformers with Decorrelated Attention Heads

DeCAtt: Efficient Vision Transformers with Decorrelated Atte...

引用

ieee computer society conference on computer vision and pattern recognition workshops (CVPRW)

作者： Mayukh Bhattacharyya Soumitri Chattopadhyay Sayan Nag Stony Brook University Jadavpur University University of Toronto

The advent of vision Transformers (ViT) has led to significant performance gains across various computer vision tasks over the last few years, surpassing the de facto standard CNN architectures. However, most of the prominent variations of vision Transformers are resource-intensive architectures with huge parameter sizes. They are known to be data-hungry and overfit quickly on comparatively smaller datasets. Consequently, this holds back their widespread usage across low-resource settings, which brings forth the need to develop resource-efficient vision transformers. To this end, we introduce a regularization loss that prioritizes efficient utilization of model parameters by decorrelating the heads of a multi-headed attention block in a vision transformer. This forces the heads to learn distinct features rather than focus on the same ones. Using this loss provides a consistent performance improvement over a wide range of varying scenarios of models and datasets as we show in our experiments, which proves its superior effectiveness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Continual Domain Adaptation through Pruning-aided Domain-specific Weight Modulation

Continual Domain Adaptation through Pruning-aided Domain-spe...

引用

ieee computer society conference on computer vision and pattern recognition workshops (CVPRW)

作者： Prasanna B Sunandini Sanyal R. Venkatesh Babu Vision and AI Lab Indian Institute of Science Bengaluru

In this paper, we propose to develop a method to address unsupervised domain adaptation (UDA) in a practical setting of continual learning (CL). The goal is to update the model on continually changing domains while preserving domain-specific knowledge to prevent catastrophic forgetting of past-seen domains. To this end, we build a framework for preserving domain-specific features utilizing the inherent model capacity via pruning. We also perform effective inference using a novel batch-norm based metric to predict the final model parameters to be used accurately. Our approach achieves not only state-of-the-art performance but also prevents catastrophic forgetting of past domains significantly. Our code is made publicly available. 1 .

关键词：

来源：评论

学校读者我要写书评

暂无评论

End-to-End Interactive Prediction and Planning with Optical Flow Distillation for Autonomous Driving

End-to-End Interactive Prediction and Planning with Optical ...

引用

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

作者： Wang, Hengli Cai, Peide Fan, Rui Sun, Yuxiang Liu, Ming Hong Kong Univ Sci & Technol Hong Kong Peoples R China Univ Calif San Diego La Jolla CA 92093 USA Hong Kong Polytech Univ Hong Kong Peoples R China

ISBN: (纸本)9781665448994

With the recent advancement of deep learning technology, data-driven approaches for autonomous car prediction and planning have achieved extraordinary performance. Nevertheless, most of these approaches follow a non-interactive prediction and planning paradigm, hypothesizing that a vehicle's behaviors do not affect others. The approaches based on such a non-interactive philosophy typically perform acceptably in sparse traffic scenarios but can easily fail in dense traffic scenarios. Therefore, we propose an end-to-end interactive neural motion planner (INMP) for autonomous driving in this paper. Given a set of past surrounding-view images and a high definition map, our INMP first generates a feature map in bird's-eye-view space, which is then processed to detect other agents and perform interactive prediction and planning jointly. Also, we adopt an optical flow distillation paradigm, which can effectively improve the network performance while still maintaining its real-time inference speed. Extensive experiments on the nuScenes dataset and in the closed-loop Carla simulation environment demonstrate the effectiveness and efficiency of our INMP for the detection, prediction, and planning tasks. Our project page is at ***/view/inmp-ofd.

关键词： Philosophical considerations Predictive models Feature extraction Real-time systems Planning pattern recognition Task analysis

来源：评论

学校读者我要写书评

暂无评论

A Joint Spatial and Magnification Based Attention Framework for Large Scale Histopathology Classification

A Joint Spatial and Magnification Based Attention Framework ...

引用

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

作者： Zhang, Jingwei Ma, Ke Van Arnam, John Gupta, Rajarsi Saltz, Joel Vakalopoulou, Maria Samaras, Dimitris SUNY Stony Brook Stony Brook NY 11794 USA Univ Paris Saclay Cent Supelec Paris France

ISBN: (纸本)9781665448994

Deep learning has achieved great success in processing large size medical images such as histopathology slides. However, conventional deep learning methods cannot handle the enormous image sizes;instead, they split the image into patches which are exhaustively processed, usually through multi-instance learning approaches. Moreover and especially in histopathology, determining the most appropriate magnification to generate these patches is also exhaustive: a model needs to traverse all the possible magnifications to select the optimal one. These limitations make the application of deep learning on large medical images and in particular histopathological images markedly inefficient. To tackle these problems, we propose a novel spatial and magnification based attention sampling strategy. First, we use a down-sampled large size image to estimate an attention map that represents a spatial probability distribution of informative patches at different magnifications. Then a small number of patches are cropped from the large size medical image at certain magnifications based on the obtained attention. The final label of the large size image is predicted solely by these patches using an end-to-end training strategy. Our experiments on two different histopathology datasets, the publicly available BACH and a subset of the TCGA-PRAD dataset, demonstrate that the proposed method runs 2.5 times faster with automatic magnification selection in training and at least 1.6 times faster than using all patches in inference as the most of state-of-the-art methods do, without loosing in performance.

关键词： Training Deep learning Histopathology Microscopy Tools Probability distribution pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Is Multimodal vision Supervision Beneficial to Language?

Is Multimodal Vision Supervision Beneficial to Language?

引用

ieee computer society conference on computer vision and pattern recognition workshops (CVPRW)

作者： Avinash Madasu Vasudev Lal Department of Computer Science UNC Chapel Hill USA Cognitive Computing Research Intel Labs USA

vision (image & video) - Language (VL) pre-training is the recent popular paradigm that achieved state-of-the-art results on multi-modal tasks like image-retrieval, video-retrieval, visual question answering etc. These models are trained in an unsupervised way and greatly benefit from the complementary modality supervision. In this paper, we explore if the language representations trained using vision supervision perform better than vanilla language representations on Natural Language Understanding and commonsense reasoning benchmarks. We experiment with a diverse set of image-text models such as ALBEF, BLIP, METER and video-text models like ALPRO, Frozen in Time, VIOLET. We compare the performance of language representations of stand-alone text encoders of these models to the language representations of text encoders learnt through vision supervision. Our experiments suggest that vanilla language representations show superior performance on most of the tasks. These results shed light on the current drawbacks of the vision-language models. The code is available at https://***/avinashsai/MML

关键词：

来源：评论

学校读者我要写书评

暂无评论

DeepShift: Towards Multiplication-Less Neural Networks

DeepShift: Towards Multiplication-Less Neural Networks

引用

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

作者： Elhoushi, Mostafa Chen, Zihao Shafiq, Farhan Tian, Ye Henry Li, Joey Yiwei Huawei Technol Markham ON Canada Univ Toronto Toronto ON Canada

ISBN: (纸本)9781665448994

The high computation, memory, and power budgets of inferring convolutional neural networks (CNNs) are major bottlenecks of model deployment to edge computing platforms, e.g., mobile devices and IoT. Moreover, training CNNs is time and energy-intensive even on high-grade servers. Convolution layers and fully connected layers, because of their intense use of multiplications, are the dominant contributor to this computation budget. We propose to alleviate this problem by introducing two new operations: convolutional shifts and fully-connected shifts which replace multiplications with bitwise shift and sign flipping during both training and inference. During inference, both approaches require only 5 bits (or less) to represent the weights. This family of neural network architectures (that use convolutional shifts and fully connected shifts) is referred to as DeepShift models. We propose two methods to train DeepShift models: DeepShift-Q which trains regular weights constrained to powers of 2, and DeepShift-PS that trains the values of the shifts and sign flips directly. Very close accuracy, and in some cases higher accuracy, to baselines are achieved. Converting pre-trained 32bit floating-point baseline models of ResNet18, ResNet50, VGG16, and GoogleNet to DeepShift and training them for 15 to 30 epochs, resulted in Top-1/Top-5 accuracies higher than that of the original model. Last but not least, we implemented the convolutional shifts and fully connected shift GPU kernels and showed a reduction in latency time of 25% when inferring ResNet18 compared to unoptimized multiplication-based GPU kernels. The code can be found at https://***/mostafaelhoushi/DeepShift.

关键词： Training Convolutional codes Computational modeling Neural networks Graphics processing units Mobile handsets pattern recognition

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 << < 108 109 110 111 112 113 114 115 116 117 > >>

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：