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

22,771 篇 会议
112 篇 期刊文献
23 册 图书

馆藏范围

22,905 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

13,398 篇 工学
- 10,880 篇 计算机科学与技术...
- 3,450 篇 软件工程
- 2,430 篇 机械工程
- 1,721 篇 光学工程
- 1,010 篇 控制科学与工程
- 998 篇 电气工程
- 761 篇 信息与通信工程
- 393 篇 仪器科学与技术
- 337 篇 生物工程
- 257 篇 生物医学工程（可授...
- 215 篇 电子科学与技术（可...
- 113 篇 化学工程与技术
- 112 篇 安全科学与工程
- 98 篇 测绘科学与技术
- 92 篇 交通运输工程
- 86 篇 建筑学
- 82 篇 土木工程
3,362 篇 医学
- 3,348 篇 临床医学
- 79 篇 基础医学(可授医学...
3,250 篇 理学
- 1,953 篇 物理学
- 1,664 篇 数学
- 567 篇 统计学（可授理学、...
- 484 篇 生物学
- 245 篇 系统科学
- 109 篇 化学
506 篇 管理学
- 299 篇 图书情报与档案管...
- 219 篇 管理科学与工程(可...
- 75 篇 工商管理
252 篇 艺术学
- 252 篇 设计学（可授艺术学...
62 篇 法学
- 59 篇 社会学
40 篇 农学
25 篇 教育学
19 篇 经济学
11 篇 军事学
3 篇 文学

主题

10,126 篇 computer vision
4,025 篇 pattern recognit...
2,900 篇 training
1,958 篇 computational mo...
1,792 篇 cameras
1,758 篇 visualization
1,485 篇 shape
1,466 篇 image segmentati...
1,447 篇 feature extracti...
1,412 篇 three-dimensiona...
1,288 篇 robustness
1,169 篇 computer archite...
1,144 篇 layout
1,142 篇 computer science
1,134 篇 semantics
1,071 篇 object detection
1,043 篇 conferences
1,009 篇 benchmark testin...
967 篇 codes
810 篇 face recognition

机构

135 篇 univ sci & techn...
118 篇 univ chinese aca...
118 篇 chinese univ hon...
110 篇 carnegie mellon ...
99 篇 tsinghua univers...
99 篇 microsoft resear...
94 篇 swiss fed inst t...
92 篇 zhejiang univ pe...
82 篇 university of sc...
81 篇 zhejiang univers...
77 篇 shanghai ai lab ...
77 篇 university of ch...
72 篇 shanghai jiao to...
68 篇 microsoft res as...
65 篇 national laborat...
65 篇 alibaba grp peop...
64 篇 tsinghua univ pe...
63 篇 adobe research
60 篇 peking univ peop...
59 篇 peng cheng labor...

作者

78 篇 van gool luc
72 篇 timofte radu
63 篇 zhang lei
45 篇 luc van gool
40 篇 yang yi
37 篇 loy chen change
33 篇 xiaoou tang
33 篇 li stan z.
33 篇 qi tian
32 篇 sun jian
31 篇 liu yang
31 篇 li fei-fei
30 篇 chen chen
30 篇 tian qi
30 篇 pascal fua
29 篇 darrell trevor
28 篇 ying shan
27 篇 li xin
27 篇 vasconcelos nuno
27 篇 hanqing lu

语言

22,844 篇 英文
35 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=1994 IEEE Computer-Society Conference on Computer Vision and Pattern Recognition"

共 22906 条记录，以下是451-460 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：

Extend Your Own Correspondences: Unsupervised Distant Point Cloud Registration by Progressive Distance Extension

Extend Your Own Correspondences: Unsupervised Distant Point ...

引用

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

作者： Liu, Quan Zhul, Hongzi Wang, Zhenxi Zhou, Yunsong Chang, Shan Guo, Minyi Shanghai Jiao Tong Univ Shanghai Peoples R China Donghua Univ Shanghai Peoples R China

ISBN: (纸本)9798350353006

Registration of point clouds collected from a pair of distant vehicles provides a comprehensive and accurate 3D view of the driving scenario, which is vital for driving safety related applications, yet existing literature suffers from the expensive pose label acquisition and the deficiency to generalize to new data distributions. In this paper, we propose EYOC, an unsupervised distant point cloud registration method that adapts to new point cloud distributions on the fly, requiring no global pose labels. The core idea of EYOC is to train a feature extractor in a progressive fashion, where in each round, the feature extractor, trained with near point cloud pairs, can label slightly farther point cloud pairs, enabling self- supervision on such far point cloud pairs. This process continues until the derived extractor can be used to register distant point clouds. Particularly, to enable high-fidelity correspondence label generation, we devise an effective spatial filtering scheme to select the most representative correspondences to register a point cloud pair, and then utilize the aligned point clouds to discover more correct correspondences. Experiments show that EYOC can achieve comparable performance with state-of-the-art supervised methods at a lower training cost. Moreover, it outwits supervised methods regarding generalization performance on new data distributions.

关键词： 3D vision Autonomous Driving Point Cloud Registration Unsupervised Learning

来源：评论

学校读者我要写书评

暂无评论

Do You Remember? Dense Video Captioning with Cross-Modal Memory Retrieval

Do You Remember? Dense Video Captioning with Cross-Modal Mem...

引用

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

作者： Kim, Minkuk Kim, Hyeon Bae Moon, Jinyoung Choi, Jinwoo Kim, Seong Tae Kyung Hee Univ Seoul South Korea Elect & Telecommun Res Inst ETRI Daejeon South Korea

ISBN: (纸本)9798350353006

There has been significant attention to the research on dense video captioning, which aims to automatically localize and caption all events within untrimmed video. Several studies introduce methods by designing dense video captioning as a multitasking problem of event localization and event captioning to consider inter-task relations. However, addressing both tasks using only visual input is challenging due to the lack of semantic content. In this study, we address this by proposing a novel framework inspired by the cognitive information processing of humans. Our model utilizes external memory to incorporate prior knowledge. The memory retrieval method is proposed with cross-modal video-to-text matching. To effectively incorporate retrieved text features, the versatile encoder and the decoder with visual and textual cross-attention modules are designed. Comparative experiments have been conducted to show the effectiveness of the proposed method on ActivityNet Captions and YouCook2 datasets. Experimental results show promising performance of our model with-out extensive pretraining from a large video dataset. Our code is available at https://***/ailab-kyunghee/CM2_DVC.

关键词： Dense Video Captioning Launguage Reasoning Retrieval Agumented Generation Video Captioning vision

来源：评论

学校读者我要写书评

暂无评论

Multi-criteria Token Fusion with One-step-ahead Attention for Efficient vision Transformers

Multi-criteria Token Fusion with One-step-ahead Attention fo...

引用

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

作者： Lee, Sanghyeok Choi, Joonmyung Kim, Hyunwoo J. Korea Univ Dept Comp Sci & Engn Seoul South Korea

ISBN: (纸本)9798350353006

vision Transformer (ViT) has emerged as a prominent backbone for computer vision. For more efficient ViTs, recent works lessen the quadratic cost of the self- attention layer by pruning or fusing the redundant tokens. However, these works faced the speed-accuracy trade-off caused by the loss of information. Here, we argue that token fusion needs to consider diverse relations between tokens to minimize information loss. In this paper, we propose a Multi-criteria Token Fusion (MCTF), that gradually fuses the tokens based on multi-criteria (i.e., similarity, informativeness, and size of fused tokens). Further, we utilize the one-step-ahead attention, which is the improved approach to capture the informativeness of the tokens. By training the model equipped with MCTF using a token reduction consistency, we achieve the best speed-accuracy tradeoff in the image classification (ImageNet1K). Experimental results prove that MCTF consistently surpasses the previous reduction methods with and without training. Specifically, DeiT-T and DeiT-S with MCTF reduce FLOPs by about 44% while improving the performance (+0.5%, and +0.3%) over the base model, respectively. We also demonstrate the applicability of MCTF in various vision Transformers (e.g., T2T-ViT, LV-ViT), achieving at least 31% speedup without performance degradation. Code is available at https://***/mlvlab/MCTF.

关键词： Efficient ViTs Token Fusion Token Merging Token Reduction

来源：评论

学校读者我要写书评

暂无评论

LAMP: Learn A Motion pattern for Few-Shot Video Generation

LAMP: Learn A Motion Pattern for Few-Shot Video Generation

引用

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

作者： Wu, Ruiqi Chen, Liangyu Yang, Tong Guo, Chunle Li, Chongyi Zhang, Xiangyu Nankai Univ CS VCIP Tianjin Peoples R China NKIARI Shenzhen Futian Peoples R China MEGVII Technol Beijing Peoples R China

ISBN: (纸本)9798350353013;9798350353006

In this paper, we present a few-shot text-to-video framework, LAMP, which enables a text-to-image diffusion model to Learn A specific Motion pattern with 8 16 videos on a single GPU. Unlike existing methods, which require a large number of training resources or learn motions that are precisely aligned with template videos, it achieves a trade-off between the degree of generation freedom and the resource costs for model training. Specifically, we design a motion-content decoupled pipeline that uses an off-the-shelf text-to-image model for content generation so that our tuned video diffusion model mainly focuses on motion learning. The well-developed text-to-image techniques can provide visually pleasing and diverse content as generation conditions, which highly improves video quality and generation freedom. To capture the features of temporal dimension, we expand the pre-trained 2D convolution layers of the T2I model to our novel temporal-spatial motion learning layers and modify the attention blocks to the temporal level. Additionally, we develop an effective inference trick, shared-noise sampling, which can improve the stability of videos without computational costs. Our method can also be flexibly applied to other tasks, e.g. real-world image animation and video editing. Extensive experiments demonstrate that LAMP can effectively learn the motion pattern on limited data and generate high-quality videos. The code and models are available at https://rqwu. ***/projects/LAMP.

关键词： Image coding

来源：评论

学校读者我要写书评

暂无评论

COTR: Compact Occupancy TRansformer for vision-based 3D Occupancy Prediction

COTR: Compact Occupancy TRansformer for Vision-based 3D Occu...

引用

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

作者： Ma, Qihang Tan, Xin Qu, Yanyun Ma, Lizhuang Zhang, Zhizhong Xie, Yuan East China Normal Univ Shanghai Peoples R China East China Normal Univ Chongqing Inst Chongqing Peoples R China Xiamen Univ Fujian Peoples R China

ISBN: (纸本)9798350353006

The autonomous driving community has shown significant interest in 3D occupancy prediction, driven by its exceptional geometric perception and general object recognition capabilities. To achieve this, current works try to construct a Tri-Perspective View (TPV) or Occupancy (OCC) representation extending from the Bird-Eye-View perception. However, compressed views like TPV representation lose 3D geometry information while raw and sparse OCC representation requires heavy but redundant computational costs. To address the above limitations, we propose Compact Occupancy TRansformer (COTR), with a geometry-aware occupancy encoder and a semantic-aware group decoder to reconstruct a compact 3D OCC representation. The occupancy encoder first generates a compact geometrical OCC feature through efficient explicit-implicit view transformation. Then, the occupancy decoder further enhances the semantic discriminability of the compact OCC representation by a coarse-to-fine semantic grouping strategy. Empirical experiments show that there are evident performance gains across multiple baselines, e.g., COTR outperforms baselines with a relative improvement of 8%-15%, demonstrating the superiority of our method. The code is available at https://***/NotACracker/COTR.

关键词：

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

DeiT-LT: Distillation Strikes Back for vision Transformer Training on Long-Tailed Datasets

DeiT-LT: Distillation Strikes Back for Vision Transformer Tr...

引用

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

作者： Rangwani, Harsh Mondal, Pradipto Mishra, Mayank Asokan, Ashish Ramayee Babu, R. Venkatesh Indian Inst Sci Bangalore Karnataka India Indian Inst Technol Kharagpur W Bengal India

ISBN: (纸本)9798350353006

vision Transformer (ViT) has emerged as a prominent architecture for various computer vision tasks. In ViT, we divide the input image into patch tokens and process them through a stack of self-attention blocks. However, unlike Convolutional Neural Network (CNN), ViT's simple architecture has no informative inductive bias (e.g., locality, etc.). Due to this, ViT requires a large amount of data for pre-training. Various data-efficient approaches (DeiT) have been proposed to train ViT on balanced datasets effectively. However, limited literature discusses the use of ViT for datasets with long-tailed imbalances. In this work, we introduce DeiT-LT to tackle the problem of training ViTs from scratch on long-tailed datasets. In DeiT-LT, we introduce an efficient and effective way of distillation from CNN via distillation DIST token by using out-of-distribution images and re-weighting the distillation loss to enhance focus on tail classes. This leads to the learning of local CNN-like features in early ViT blocks, improving generalization for tail classes. Further, to mitigate overfitting, we propose distilling from a flat CNN teacher, which leads to learning low-rank generalizable features for DIST tokens across all ViT blocks. With the proposed DeiT-LT scheme, the distillation DIST token becomes an expert on the tail classes, and the classifier CLS token becomes an expert on the head classes. The experts help to effectively learn features corresponding to both the majority and minority classes using a distinct set of tokens within the same ViT architecture. We show the effectiveness of DeiT-LT for training ViT from scratch on datasets ranging from small-scale CIFAR-10 LT to large-scale iNaturalist-2018. Project Page: https://***/DeiT-LT.

关键词： distillation long-tail-learning vision transformers vit

来源：评论

学校读者我要写书评

暂无评论

Initialization Noise in Image Gradients and Saliency Maps

Initialization Noise in Image Gradients and Saliency Maps

引用

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

作者： Woerl, Ann-Christin Disselhoff, Jan Wand, Michael Johannes Gutenberg Univ Mainz Inst Comp Sci Mainz Germany

ISBN: (纸本)9798350301298

In this paper, we examine gradients of logits of image classification CNNs by input pixel values. We observe that these fluctuate considerably with training randomness, such as the random initialization of the networks. We extend our study to gradients of intermediate layers, obtained via GradCAM, as well as popular network saliency estimators such as DeepLIFT, SHAP, LIME, Integrated Gradients, and SmoothGrad. While empirical noise levels vary, qualitatively different attributions to image features are still possible with all of these, which comes with implications for interpreting such attributions, in particular when seeking data-driven explanations of the phenomenon generating the data. Finally, we demonstrate that the observed artefacts can be removed by marginalization over the initialization distribution by simple stochastic integration.

关键词： Explainable computer vision

来源：评论

学校读者我要写书评

暂无评论

Low-Rank Rescaled vision Transformer Fine-Tuning: A Residual Design Approach

Low-Rank Rescaled Vision Transformer Fine-Tuning: A Residual...

引用

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

作者： Dong, Wei Zhang, Xing Chen, Bihui Yang, Dawei Lin, Zhijun Yang, Qingsen Wang, Peng Yang, Yang Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu Sichuan Peoples R China Xian Univ Architecture & Technol Coll Informat & Control Engn Xian Shaanxi Peoples R China Northwestern Polytech Univ Sch Comp Sci Xian Shaanxi Peoples R China

ISBN: (纸本)9798350353006

Parameter-efficient fine-tuning for pre-trained vision Transformers aims to adeptly tailor a model to downstream tasks by learning a minimal set of new adaptation parameters while preserving the frozen majority of pre-trained parameters. Striking a balance between retaining the generalizable representation capacity of the pre-trained model and acquiring task-specific features poses a key challenge. Currently, there is a lack of focus on guiding this delicate trade-off. In this study, we approach the problem from the perspective of Singular Value Decomposition (SVD) of pre-trained parameter matrices, providing insights into the tuning dynamics of existing methods. Building upon this understanding, we propose a Residual-based Low-Rank Rescaling (RLRR) fine-tuning strategy. This strategy not only enhances flexibility in parameter tuning but also ensures that new parameters do not deviate excessively from the pre-trained model through a residual design. Extensive experiments demonstrate that our method achieves competitive performance across various downstream image classification tasks, all while maintaining comparable new parameters. We believe this work takes a step forward in offering a unified perspective for interpreting existing methods and serves as motivation for the development of new approaches that move closer to effectively considering the crucial trade-off mentioned above. Our code is available at https://***/zstarN70/***.

关键词： Low-Rank Adaptation Parameter-efficient fine-tuning Singular Value Decomposition

来源：评论

学校读者我要写书评

暂无评论

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

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 << < 42 43 44 45 46 47 48 49 50 51 > >>

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：