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531-540 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：

Harnessing Large Language Models for Training-free Video Anomaly Detection

Harnessing Large Language Models for Training-free Video Ano...

引用

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

作者： Zanella, Luca Menapace, Willi Mancini, Massimiliano Wang, Yiming Ricci, Elisa Univ Trento Trenton NJ 38122 USA Fdn Bruno Kessler Trenton NJ USA

ISBN: (纸本)9798350353006

Video anomaly detection (VAD) aims to temporally locate abnormal events in a video. Existing works mostly rely on training deep models to learn the distribution of normality with either video-level supervision, one-class supervision, or in an unsupervised setting. Training-based methods are prone to be domain-specific, thus being costly for practical deployment as any domain change will involve data collection and model training. In this paper, we radically depart from previous efforts and propose LAnguage-based VAD (LAVAD), a method tackling VAD in a novel, training-free paradigm, exploiting the capabilities of pre-trained large language models (LLMs) and existing vision-language models (VLMs). We leverage VLM-based captioning models to generate textual descriptions for each frame of any test video. With the textual scene description, we then devise a prompting mechanism to unlock the capability of LLMs in terms of temporal aggregation and anomaly score estimation, turning LLMs into an effective video anomaly detector. We further leverage modality-aligned VLMs and propose effective techniques based on cross-modal similarity for cleaning noisy captions and refining the LLM-based anomaly scores. We evaluate LAVAD on two large datasets featuring real-world surveillance scenarios (UCF-Crime and XD-Violence), showing that it outperforms both unsupervised and one-class methods without requiring any training or data collection.

关键词： large language models video anomaly detection vision-language models

来源：评论

学校读者我要写书评

暂无评论

Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding

Chat-UniVi: Unified Visual Representation Empowers Large Lan...

引用

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

作者： Jin, Peng Takanobu, Ryuichi Zhang, Wancai Cao, Xiaochun Yuan, Li Peking Univ Sch Elect & Comp Engn Shenzhen Peoples R China Peng Cheng Lab Shenzhen Peoples R China Peking Univ Ai Sci AI4S Preferred Program Shenzhen Grad Sch Shenzhen Peoples R China Nari Technol Co Ltd Beijing Peoples R China Sun Yat Sen Univ Sch Cyber Sci & Tech Shenzhen Campus Shenzhen Peoples R China

ISBN: (纸本)9798350353006

Large language models have demonstrated impressive universal capabilities across a wide range of open-ended tasks and have extended their utility to encompass multi-modal conversations. However, existing methods encounter challenges in effectively handling both image and video understanding, particularly with limited visual tokens. In this work, we introduce Chat-UniVi, a Unified vision-language model capable of comprehending and engaging in conversations involving images and videos through a unified visual representation. Specifically, we employ a set of dynamic visual tokens to uniformly represent images and videos. This representation framework empowers the model to efficiently utilize a limited number of visual tokens to simultaneously capture the spatial details necessary for images and the comprehensive temporal relationship required for videos. Moreover, we leverage a multi-scale representation, enabling the model to perceive both high-level semantic concepts and low-level visual details. Notably, ChatUniVi is trained on a mixed dataset containing both images and videos, allowing direct application to tasks involving both mediums without requiring any modifications. Extensive experimental results demonstrate that Chat-UniVi consistently outperforms even existing methods exclusively designed for either images or videos. Code is available at https://***/PKU-YuanGroup/Chat-UniVi.

关键词： Image Understanding Large Language Models Video Understanding vision Language Model

来源：评论

学校读者我要写书评

暂无评论

SOK-Bench: A Situated Video Reasoning Benchmark with Aligned Open-World Knowledge

SOK-Bench: A Situated Video Reasoning Benchmark with Aligned...

引用

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

作者： Wang, Andong Wu, Bo Chen, Sunli Chen, Zhenfang Guan, Haotian Lee, Wei-Ning Li, Li Erran Gan, Chuang Univ Hong Kong Hong Kong Peoples R China MIT IBM Watson AI Lab Cambridge MA USA Tsinghua Univ Beijing Peoples R China AWS AI Seattle WA USA UMass Amherst Amherst MA USA

ISBN: (纸本)9798350353006

Learning commonsense reasoning from visual contexts and scenes in real-world is a crucial step toward advanced artificial intelligence. However, existing video reasoning benchmarks are still inadequate since they were mainly designed for factual or situated reasoning and rarely involve broader knowledge in the real world. Our work aims to delve deeper into reasoning evaluations, specifically within dynamic, open-world, and structured context knowledge. We propose a new benchmark (SOK-Bench), consisting of 44K questions and 10K situations with instance-level annotations depicted in the videos. The reasoning process is required to understand and apply situated knowledge and general knowledge for problem-solving. To create such a dataset, we propose an automatic and scalable generation method to generate question-answer pairs, knowledge graphs, and rationales by instructing the combina-tions of LLMs and MLLMs. Concretely, we first extract observable situated entities, relations, and processes from videos for situated knowledge and then extend to open-world knowledge beyond the visible content. The task generation is facilitated through multiple dialogues as iterations and subsequently corrected and refined by our designed self-promptings and demonstrations. With a corpus of both explicit situated facts and implicit commonsense, we generate associated question-answer pairs and reasoning processes, finally followed by manual reviews for quality assurance. We evaluated recent mainstream large vision-language models on the benchmark and found several insightful conclusions. For more information, please refer to our benchmark at ***/SOKBench.

关键词： benchmark commonsense reasoning video understanding vision language foundation models visual reasoning

来源：评论

学校读者我要写书评

暂无评论

Unknown Prompt, the only Lacuna: Unveiling CLIP's Potential for Open Domain Generalization

Unknown Prompt, the only Lacuna: Unveiling CLIP's Potential ...

引用

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

作者： Singha, Mainak Jha, Ankit Bose, Shirsha Nair, Ashwin Abdar, Moloud Banerjee, Biplab Aisin Corp Kariya Aichi Japan Indian Inst Technol Bombay Maharashtra India Tech Univ Munich Munich Germany IISER Thiruvananthapuram Thiruvananthapuram Kerala India Deakin Univ Geelong Vic Australia

ISBN: (纸本)9798350353006

We delve into Open Domain Generalization (ODG), marked by domain and category shifts between training's labeled source and testing's unlabeled target domains. Existing solutions to ODG face limitations due to constrained generalizations of traditional CNN backbones and errors in detecting target open samples in the absence of prior knowledge. Addressing these pitfalls, we introduce ODG-CLIP, harnessing the semantic prowess of the vision-language model, CLIP. Our framework brings forth three primary innovations: Firstly, distinct from prevailing paradigms, we conceptualize ODG as a multi-class classification challenge encompassing both known and novel categories. Central to our approach is modeling a unique prompt tailored for detecting unknown class samples, and to train this, we employ a readily accessible stable diffusion model, elegantly generating proxy images for the open class. Secondly, aiming for domain-tailored classification (prompt) weights while ensuring a balance of precision and simplicity, we devise a novel visual style-centric prompt learning mechanism. Finally, we infuse images with class-discriminative knowledge derived from the prompt space to augment the fidelity of CLIP's visual embeddings. We introduce a novel objective to safeguard the continuity of this infused semantic intel across domains, especially for the shared classes. Through rigorous testing on diverse datasets, covering closed and open-set DG contexts, ODG-CLIP demonstrates clear supremacy, consistently outpacing peers with performance boosts between 8%-16%. Code will be available at https://***/mainaksingha01/ODG-CLIP.

关键词： open domain generalization vision-language models

来源：评论

学校读者我要写书评

暂无评论

Boundary-aware Image Inpainting with Multiple Auxiliary Cues

Boundary-aware Image Inpainting with Multiple Auxiliary Cues

引用

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

作者： Yamashita, Yohei Shimosato, Kodai Ukita, Norimichi Toyota Technol Inst Nagoya Japan

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Image inpainting (a.k.a. image completion) allows us to remove unexpected foreground objects from an observed image and to restore the removed region with background pixels. The performance of image inpainting is improved by auxiliary cues such as edge boundaries and segmentation regions. As a new auxiliary cue, this paper focuses on a depth image that is estimated from an input RGB image by monocular depth estimation. In the depth image, boundaries between different objects (e.g., objects located in different distances) with similar pixel values might be available, while those boundaries are difficult to be detected by edge detection and segmentation. Our proposed method employs those boundaries in the edge and depth images as auxiliary cues. Experiments demonstrate that our proposed method augmented by the depth image outperforms its baseline quantitatively (i.e., 1.17dB and 0.74dB PSNR gains on the Paris-StreetView and Places datasets, respectively) and qualitatively.

关键词： Image segmentation computer vision Image edge detection conferences Estimation pattern recognition Image restoration

来源：评论

学校读者我要写书评

暂无评论

Multimodal Shape Completion via Implicit Maximum Likelihood Estimation

Multimodal Shape Completion via Implicit Maximum Likelihood ...

引用

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

作者： Arora, Himanshu Mishra, Saurabh Peng, Shichong Li, Ke Mahdavi-Amiri, Ali Simon Fraser Univ Burnaby BC Canada

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Shape completion is the problem of completing partial input shapes such as partial scans. This problem finds important applications in computer vision and robotics due to issues such as occlusion or sparsity in real-world data. However, most of the existing research related to shape completion has been focused on completing shapes by learning a one-to-one mapping which limits the diversity and creativity of the produced results. We propose a novel multimodal shape completion technique that is effectively able to learn a one-to-many mapping and generates diverse complete shapes. Our approach is based on the conditional Implicit Maximum Likelihood Estimation (IMLE) technique wherein we condition our inputs on partial 3D point clouds. We extensively evaluate our approach by comparing it to various baselines both quantitatively and qualitatively. We show that our method is superior to alternatives in terms of completeness and diversity of shapes.

关键词： Point cloud compression Maximum likelihood estimation computer vision Three-dimensional displays Shape conferences pattern recognition

来源：评论

学校读者我要写书评

暂无评论

A Deeper Look into Aleatoric and Epistemic Uncertainty Disentanglement

A Deeper Look into Aleatoric and Epistemic Uncertainty Disen...

引用

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

作者： Valdenegro-Toro, Matias Mori, Daniel Saromo Univ Groningen Dept AI Bernoulli Inst Groningen Netherlands Pontifical Catholic Univ Peru Artificial Intelligence Res Grp San Miguel Peru

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Neural networks are ubiquitous in many tasks, but trusting their predictions is an open issue. Uncertainty quantification is required for many applications, and disentangled aleatoric and epistemic uncertainties are best. In this paper, we generalize methods to produce disentangled uncertainties to work with different uncertainty quantification methods, and evaluate their capability to produce disentangled uncertainties. Our results show that: there is an interaction between learning aleatoric and epistemic uncertainty, which is unexpected and violates assumptions on aleatoric uncertainty, some methods like Flipout produce zero epistemic uncertainty, aleatoric uncertainty is unreliable in the out-of-distribution setting, and Ensembles provide overall the best disentangling quality. We also explore the error produced by the number of samples hyper-parameter in the sampling softmax function, recommending N > 100 samples. We expect that our formulation and results help practitioners and researchers choose uncertainty methods and expand the use of disentangled uncertainties, as well as motivate additional research into this topic.

关键词： computer vision Uncertainty conferences Neural networks pattern recognition Task analysis

来源：评论

学校读者我要写书评

暂无评论

Constellations: A novel dataset for studying iterative inference in humans and AI

Constellations: A novel dataset for studying iterative infer...

引用

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

作者： Khajuria, Tarun Tulver, Kadi Luik, Taavi Aru, Jaan Univ Tartu Inst Comp Sci Tartu Estonia

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Under complex viewing conditions, human perception relies on generating hypotheses and revising them in an iterative fashion. We developed novel visual stimuli to study such iterative inference in humans and AI. In these stimuli, called "constellations", all local information about the object has been removed and it can only be recognized when taking into account the global pattern. We here describe the dataset and demonstrate that humans indeed use an iterative process of generating hypotheses and refining them to solve these images. We also provide code that allows researchers to create their own constellation images. The constellation dataset allows researchers to develop sketching algorithms for guessing the hidden object. As such algorithms used by humans appear to be iterative in nature, this dataset will facilitate the study of iterative inference in minds and machines.

关键词： Visualization Image recognition Machine vision conferences Refining Iterative algorithms Inference algorithms

来源：评论

学校读者我要写书评

暂无评论

Curriculum Learning for Data-Efficient vision-Language Alignment

Curriculum Learning for Data-Efficient Vision-Language Align...

引用

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

作者： Srinivasan, Tejas Ren, Xiang Thomason, Jesse University of Southern California United States

ISBN: (纸本)9798350302493

Aligning image and text encoders from scratch using contrastive learning requires large amounts of paired image-text data. We alleviate this need by aligning individually pre-trained language and vision representation models using a much smaller amount of paired data with a curriculum learning algorithm to learn fine-grained vision-language alignments. TOnICS (Training with Ontology-Informed Contrastive Sampling) initially samples minibatches whose image-text pairs contain a wide variety of objects to learn object-level vision-language alignment, and progressively samples minibatches where all image-text pairs contain the same object to learn finer-grained contextual alignment. Aligning pre-trained BERT and VinVL-OD models to each other using TOnICS outperforms CLIP on downstream zero-shot image retrieval using © 2023 ieee.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

Rethinking Transformers Pre-training for Multi-Spectral Satellite Imagery

Rethinking Transformers Pre-training for Multi-Spectral Sate...

引用

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

作者： Noman, Mubashir Naseer, Muzammal Cholakkal, Hisham Anwar, Rao Muhammad Khan, Salman Khan, Fahad Shahbaz Mohamed bin Zayed Univ AI Abu Dhabi U Arab Emirates Australian Natl Univ Canberra ACT Australia Linkoping Univ Linkoping Sweden

ISBN: (纸本)9798350353006

Recent advances in unsupervised learning have demonstrated the ability of large vision models to achieve promising results on downstream tasks by pre-training on large amount of unlabelled data. Such pre-training techniques have also been explored recently in the remote sensing domain due to the availability of large amount of unlabelled data. Different from standard natural image datasets, remote sensing data is acquired from various sensor technologies and exhibit diverse range of scale variations as well as modalities. Existing satellite image pre-training methods either ignore the scale information present in the remote sensing imagery or restrict themselves to use only a single type of data modality. In this paper, we re-visit transformers pre-training and leverage multi-scale information that is effectively utilized with multiple modalities. Our proposed approach, named SatMAE++, performs multiscale pre-training and utilizes convolution based upsampling blocks to reconstruct the image at higher scales making it extensible to include more scales. Compared to existing works, the proposed SatMAE++ with multi-scale pre-training is equally effective for both optical as well as multi-spectral imagery. Extensive experiments on six datasets reveal the merits of proposed contributions, leading to state-of-the-art performance on all datasets. SatMAE++ achieves mean average precision (mAP) gain of 2.5% for multi-label classification task on BigEarthNet dataset. Our code and pre-trained models are available at https://***/techmn/satmae_pp.

关键词： multi-scale mask auto encoder multi-spectral imagery remote sensing scene classification self-supervised learning vision Transformers

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 << < 50 51 52 53 54 55 56 57 58 59 > >>

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：