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

4,653 篇 会议
2 篇 期刊文献

馆藏范围

4,655 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,715 篇 工学
- 1,623 篇 计算机科学与技术...
- 182 篇 软件工程
- 142 篇 机械工程
- 133 篇 光学工程
- 41 篇 生物工程
- 29 篇 信息与通信工程
- 18 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 控制科学与工程
- 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
173 篇 理学
- 135 篇 物理学
- 42 篇 生物学
- 30 篇 数学
- 16 篇 统计学（可授理学、...
- 10 篇 化学
- 2 篇 大气科学
14 篇 管理学
- 7 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
10 篇 医学
- 10 篇 临床医学
5 篇 法学
- 3 篇 社会学
- 2 篇 法学
3 篇 教育学
- 3 篇 教育学
2 篇 农学
1 篇 经济学

主题

2,867 篇 computer vision
1,227 篇 training
1,038 篇 pattern recognit...
870 篇 computational mo...
794 篇 conferences
693 篇 visualization
593 篇 three-dimensiona...
469 篇 codes
460 篇 benchmark testin...
422 篇 semantics
420 篇 computer archite...
349 篇 accuracy
301 篇 adaptation model...
282 篇 feature extracti...
267 篇 transformers
242 篇 cameras
225 篇 diffusion models
223 篇 solid modeling
214 篇 pipelines
210 篇 measurement

机构

72 篇 tsinghua univers...
69 篇 zhejiang univers...
58 篇 university of sc...
57 篇 shanghai jiao to...
52 篇 google research
47 篇 nanyang technolo...
44 篇 national univers...
40 篇 shanghai ai labo...
39 篇 university of ch...
37 篇 adobe research
37 篇 the university o...
37 篇 the chinese univ...
35 篇 stanford univers...
34 篇 harbin institute...
34 篇 shanghai artific...
34 篇 carnegie mellon ...
33 篇 university of el...
30 篇 peng cheng labor...
30 篇 sun yat-sen univ...
29 篇 s-lab nanyang te...

作者

75 篇 timofte radu
24 篇 yu qiao
22 篇 luc van gool
19 篇 ying shan
16 篇 van gool luc
15 篇 radu timofte
14 篇 xin li
13 篇 li xin
12 篇 chen chen
12 篇 zhang zhao
12 篇 boxin shi
11 篇 lizhuang ma
11 篇 fan haoqiang
11 篇 loy chen change
11 篇 zheng-jun zha
11 篇 liu shuaicheng
11 篇 kai zhang
11 篇 marcos v. conde
11 篇 chen wei-ting
11 篇 ziwei liu

语言

4,654 篇 英文
1 篇 中文

检索条件"任意字段=2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024"

共 4655 条记录，以下是691-700 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：

Delving into High-Quality Synthetic Face Occlusion Segmentation Datasets

Delving into High-Quality Synthetic Face Occlusion Segmentat...

引用

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

作者： Voo, Kenny T. R. Jiang, Liming Loy, Chen Change Nanyang Technol Univ S Lab Singapore Singapore

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

This paper performs comprehensive analysis on datasets for occlusion-aware face segmentation, a task that is crucial for many downstream applications. The collection and annotation of such datasets are time-consuming and labor-intensive. Although some efforts have been made in synthetic data generation, the naturalistic aspect of data remains less explored. In our study, we propose two occlusion generation techniques, Naturalistic Occlusion Generation (NatOcc), for producing high-quality naturalistic synthetic occluded faces;and Random Occlusion Generation (RandOcc), a more general synthetic occluded data generation method (Figure 1). We empirically show the effectiveness and robustness of both methods, even for unseen occlusions. To facilitate model evaluation, we present two high-resolution real-world occluded face datasets with fine-grained annotations, RealOcc and RealOcc-Wild, featuring both careful alignment preprocessing and an in-the-wild setting for robustness test. We further conduct a comprehensive analysis on a newly introduced segmentation benchmark, offering insights for future exploration. Our code and dataset are available at https://***/kennyvoo/faceocclusion-generation.

关键词： computer vision Codes Annotations Face recognition conferences Benchmark testing Robustness

来源：评论

学校读者我要写书评

暂无评论

Learned Low Bitrate Video Compression with Space-Time Super-Resolution

Learned Low Bitrate Video Compression with Space-Time Super-...

引用

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

作者： Yang, Jiayu Yang, Chunhui Xiong, Fei Wang, Feng Wang, Ronggang Peking Univ Shenzhen Grad Sch Shenzhen Peoples R China

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

This paper presents a learned low bitrate video compression framework that consists of pre-processing, compression and post-processing. In pre-processing stage, the source videos are optionally reduced to low-resolution or low-frame-rate ones to better meet with the limited bandwidth. In compression stage, inter-frame prediction is performed by deformable convolution (DCN). The predicted frame is then used as temporal conditions to compress the current frame. In post-processing stage, the decoded videos are fed into a Space-Time Super-Resolution module, in which the videos are restored to original spatial and temporal resolutions. Experimental results on CLIC22 video test conditions demonstrate that the proposed method shows better performance on both objective and subjective quality at low bitrate. Our team name is PKUSZ-LVC.

关键词： computer vision Convolution conferences Computational modeling Superresolution Bit rate Video compression

来源：评论

学校读者我要写书评

暂无评论

AuxMix: Semi-Supervised Learning with Unconstrained Unlabeled Data

AuxMix: Semi-Supervised Learning with Unconstrained Unlabele...

引用

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

作者： Banitalebi-Dehkordi, Amin Gujjar, Pratik Zhang, Yong Huawei Technol Canada Co Ltd Vancouver BC Canada

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Semi-supervised learning (SSL) has seen great strides when labeled data is scarce but unlabeled data is abundant. Critically, most recent work assume that such unlabeled data is drawn from the same distribution as the labeled data. In this work, we show that state-of-the-art SSL algorithms suffer a degradation in performance in the presence of unlabeled auxiliary data that does not necessarily possess the same class distribution as the labeled set. We term this problem as Auxiliary-SSL and propose AuxMix, an algorithm that leverages self-supervised learning tasks to learn generic features in order to mask auxiliary data that are not semantically similar to the labeled set. We also propose to regularize learning by maximizing the predicted entropy for dissimilar auxiliary samples. We show an improvement of 5% over existing baselines on a ResNet-50 model when trained on CIFAR10 dataset with 4k labeled samples and all unlabeled data is drawn from the Tiny-Imagenet dataset. We report competitive results on several datasets and conduct ablation studies.

关键词： Degradation computer vision conferences Self-supervised learning Semisupervised learning Prediction algorithms Entropy

来源：评论

学校读者我要写书评

暂无评论

Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld

Embodied Multi-Modal Agent trained by an LLM from a Parallel...

引用

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

作者： Yang, Yijun Zhou, Tianyi Li, Kanxue Tao, Dapeng Li, Lusong Shen, Li He, Xiaodong Jiang, Jing Shi, Yuhui Southern Univ Sci & Technol Shenzhen Peoples R China Univ Maryland College Pk MD 20742 USA Yunnan Univ Kunming Yunnan Peoples R China JD Explore Acad Beijing Peoples R China Univ Technol Sydney Sydney NSW Australia

ISBN: (纸本)9798350353006

While large language models (LLMs) excel in a simulated world of texts, they struggle to interact with the more realistic world without perceptions of other modalities such as visual or audio signals. Although vision-language models (VLMs) integrate LLM modules (1) aligned with static image features, and (2) may possess prior knowledge of world dynamics (as demonstrated in the text world), they have not been trained in an embodied visual world and thus cannot align with its dynamics. On the other hand, training an embodied agent in a noisy visual world without expert guidance is often challenging and inefficient. In this paper, we train a VLM agent living in a visual world using an LLM agent excelling in a parallel text world. Specifically, we distill LLM's reflection outcomes (improved actions by analyzing mistakes) in a text world's tasks to finetune the VLM on the same tasks of the visual world, resulting in an Embodied Multi-Modal Agent (EMMA) quickly adapting to the visual world dynamics. Such cross-modality imitation learning between the two parallel worlds is achieved by a novel DAgger-DPO algorithm, enabling EMMA to generalize to a broad scope of new tasks without any further guidance from the LLM expert. Extensive evaluations on the ALFWorld benchmark's diverse tasks highlight EMMA's superior performance to SOTA VLM-based agents, e.g., 20%-70% improvement in the success rate.

关键词： Embodied AI Imitation Learning Large Language Models vision Language Models

来源：评论

学校读者我要写书评

暂无评论

Sea Situational Awareness (SeaSAw) Dataset

Sea Situational Awareness (SeaSAw) Dataset

引用

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

作者： Kaur, Parneet Aziz, Arslan Jain, Darshan Patel, Harshil Hirokawa, Jonathan Townsend, Lachlan Reimers, Christoph Hua, Fiona

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Vessels move 90% of international cargo by volume, with the marine economy contributing to 5.1% of global GDP. As one of the oldest industries, the marine industry has yet to embrace innovations in modern technology to safeguard the blue economy. Situational awareness from intelligent vessel systems can enable enhanced safety and decision-making for mariners. As the foundation for these intelligent systems, advanced perception technology requires sufficient real-world operational data to leverage recent AI technologies. In this work, we introduce the Sea Situational Awareness (SeaSAw) dataset - a novel dataset that is comprised of 1.9 million images with 14.6 million objects associated with 20.4 million attributes from 12 object classes, making it the largest maritime dataset for object detection, fine-grained classification and tracking. Furthermore, this dataset consists of 9 sources in combination with various RGB cameras, mounted on different moving vessels, operating in different geographic locations globally, having variations in scenario, weather and illumination conditions. This data collection took place across 4 years with rigorous efforts on data selection, annotation, management and analysis to enhance the marine perception technology.

关键词： Industries computer vision Technological innovation Image resolution Lighting Object detection Safety

来源：评论

学校读者我要写书评

暂无评论

Ice hockey player identification via transformers and weakly supervised learning

Ice hockey player identification via transformers and weakly...

引用

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

作者： Vats, Kanav McNally, William Walters, Pascale Clausi, David A. Zelek, John S. Univ Waterloo Syst Design Engn Waterloo ON Canada Stathletes Inc St Catharines ON Canada

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Identifying players in video is a foundational step in computer vision-based sports analytics. Obtaining player identities is essential for analyzing the game and is used in downstream tasks such as game event recognition. Transformers are the existing standard in natural language processing (NLP) and are swiftly gaining traction in computer vision. Motivated by the increasing success of transformers in computer vision, we introduce a transformer network for recognizing players through their jersey numbers in broadcast National Hockey League (NHL) videos. The transformer takes temporal sequences of player frames (called player tracklets) as input and outputs the probabilities of jersey numbers present in the frames. The proposed network performs better than the previous benchmark on the same dataset. We implement a weakly-supervised training approach by generating approximate frame-level labels for jersey number presence and use the frame-level labels for faster training. We also utilize player shifts available in the NHL play-by-play data by reading the game time using optical character recognition (OCR) to get the players on the ice rink at a certain game time. Using player-shifts improved the player identification accuracy by 6%.

关键词： Training computer vision Optical character recognition Supervised learning Games Transformers Ice

来源：评论

学校读者我要写书评

暂无评论

Less is More: Proxy Datasets in NAS approaches

Less is More: Proxy Datasets in NAS approaches

引用

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

作者： Moser, Brian Raue, Federico Hees, Joern Dengel, Andreas German Res Ctr Artificial Intelligence DFKI Darmstadt Germany TU Kaiserslautern Kaiserslautern Germany

ISBN: (纸本)9781665487399

Neural Architecture Search (NAS) defines the design of Neural Networks as a search problem. Unfortunately, NAS is computationally intensive because of various possibilities depending on the number of elements in the design and the possible connections between them. In this work, we extensively analyze the role of the dataset size based on several sampling approaches for reducing the dataset size (unsupervised and supervised cases) as an agnostic approach to reduce search time. We compared these techniques with four common NAS approaches in NAS-Bench-201 in roughly 1,400 experiments on CIFAR-100. One of our surprising findings is that in most cases we can reduce the amount of training data to 25%, consequently also reducing search time to 25%, while at the same time maintaining the same accuracy as if training on the full dataset. In addition, some designs derived from subsets out-perform designs derived from the full dataset by up to 22 p.p. accuracy.

关键词： Training computer vision conferences Neural networks Training data computer architecture Search problems

来源：评论

学校读者我要写书评

暂无评论

vision Transformers with Mixed-Resolution Tokenization

Vision Transformers with Mixed-Resolution Tokenization

引用

2023 ieee/cvf conference on computer vision and pattern recognition workshops, cvprw 2023

作者： Ronen, Tomer Levy, Omer Golbert, Avram Tel Aviv University Israel Google Research

ISBN: (纸本)9798350302493

vision Transformer models process input images by dividing them into a spatially regular grid of equal-size patches. Conversely, Transformers were originally introduced over natural language sequences, where each token represents a subword - a chunk of raw data of arbitrary size. In this work, we apply this approach to vision Transformers by introducing a novel image tokenization scheme, replacing the standard uniform grid with a mixed-resolution sequence of tokens, where each token represents a patch of arbitrary size. Using the Quadtree algorithm and a novel saliency scorer, we construct a patch mosaic where low-saliency areas of the image are processed in low resolution, routing more of the model's capacity to important image regions. Using the same architecture as vanilla ViTs, our Quadformer models achieve substantial accuracy gains on image classification when controlling for the computational budget. Code and models are publicly available at https://***/TomerRonen34/mixed-resolution-vit. © 2023 ieee.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating vision-Language Transformer

MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for...

引用

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

作者： Cao, Jianjian Ye, Peng Li, Shengze Yu, Chong Tang, Yansong Lu, Jiwen Chen, Tao Fudan Univ Sch Informat Sci & Technol Shanghai Peoples R China Fudan Univ Acad Engn & Technol Shanghai Peoples R China Tsinghua Univ Tsinghua Shenzhen Int Grad Sch Beijing Peoples R China Tsinghua Univ Dept Automat Beijing Peoples R China

ISBN: (纸本)9798350353006

vision-Language Transformers (VLTs) have shown great success recently, but are meanwhile accompanied by heavy computation costs, where a major reason can be attributed to the large number of visual and language tokens. Existing token pruning research for compressing VLTs mainly follows a single-modality-based scheme yet ignores the critical role of aligning different modalities for guiding the token pruning process, causing the important tokens for one modality to be falsely pruned in another modality branch. Meanwhile, existing VLT pruning works also lack the flexibility to dynamically compress each layer based on different input samples. To this end, we propose a novel framework named Multimodal Alignment-Guided Dynamic Token Pruning (MADTP) for accelerating various VLTs. Specifically, we first introduce a well-designed Multi-modality Alignment Guidance (MAG) module that can align features of the same semantic concept from different modalities, to ensure the pruned tokens are less important for all modalities. We further design a novel Dynamic Token Pruning (DTP) module, which can adaptively adjust the token compression ratio in each layer based on different input instances. Extensive experiments on various benchmarks demonstrate that MADTP significantly reduces the computational complexity of kinds of multimodal models while preserving competitive performance. Notably, when applied to the BLIP model in the NLVR2 dataset, MADTP can reduce the GFLOPs by 80% with less than 4% performance degradation. The code is available at https://***/double125/MADTP.

关键词： Model Compress Token Pruning

来源：评论

学校读者我要写书评

暂无评论

SPIN: Simplifying Polar Invariance for Neural networks Application to vision-based irradiance forecasting

SPIN: Simplifying Polar Invariance for Neural networks Appli...

引用

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

作者： Paletta, Quentin Hu, Anthony Arbod, Guillaume Blanc, Philippe Lasenby, Joan Univ Cambridge Cambridge England ENGIE Lab CRIGEN Stains France MINES ParisTech Paris France

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Translational invariance induced by pooling operations is an inherent property of convolutional neural networks, which facilitates numerous computer vision tasks such as classification. Yet to leverage rotational invariant tasks, convolutional architectures require specific rotational invariant layers or extensive data augmentation to learn from diverse rotated versions of a given spatial configuration. Unwrapping the image into its polar coordinates provides a more explicit representation to train a convolutional architecture as the rotational invariance becomes translational, hence the visually distinct but otherwise equivalent rotated versions of a given scene can be learnt from a single image. We show with two common vision-based solar irradiance forecasting challenges (i.e. using ground-taken sky images or satellite images), that this preprocessing step significantly improves prediction results by standardising the scene representation, while decreasing training time by a factor of 4 compared to augmenting data with rotations. In addition, this transformation magnifies the area surrounding the centre of the rotation, leading to more accurate short-term irradiance predictions.

关键词： Training computer vision Satellites Neural networks computer architecture Predictive models Cameras

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466页 << < 66 67 68 69 70 71 72 73 74 75 > >>

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：