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

11,267 篇 会议
14 篇 期刊文献

馆藏范围

11,281 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

7,859 篇 工学
- 7,418 篇 计算机科学与技术...
- 799 篇 机械工程
- 390 篇 电气工程
- 377 篇 软件工程
- 224 篇 控制科学与工程
- 68 篇 光学工程
- 32 篇 信息与通信工程
- 26 篇 生物工程
- 10 篇 生物医学工程（可授...
- 8 篇 化学工程与技术
- 7 篇 电子科学与技术（可...
- 6 篇 交通运输工程
- 5 篇 安全科学与工程
- 3 篇 仪器科学与技术
- 2 篇 力学（可授工学、理...
- 2 篇 材料科学与工程（可...
- 2 篇 动力工程及工程热...
- 2 篇 航空宇航科学与技...
3,103 篇 医学
- 3,102 篇 临床医学
- 4 篇 基础医学(可授医学...
297 篇 理学
- 199 篇 系统科学
- 69 篇 物理学
- 27 篇 生物学
- 24 篇 数学
- 9 篇 统计学（可授理学、...
- 7 篇 化学
23 篇 管理学
- 14 篇 图书情报与档案管...
- 9 篇 管理科学与工程(可...
- 4 篇 工商管理
6 篇 法学
- 6 篇 社会学
2 篇 农学
1 篇 教育学
1 篇 艺术学

主题

5,461 篇 computer vision
2,564 篇 training
2,118 篇 pattern recognit...
1,632 篇 computational mo...
1,454 篇 visualization
1,325 篇 three-dimensiona...
1,070 篇 semantics
972 篇 codes
968 篇 benchmark testin...
930 篇 computer archite...
885 篇 deep learning
831 篇 task analysis
729 篇 feature extracti...
541 篇 conferences
530 篇 neural networks
526 篇 face recognition
503 篇 transformers
480 篇 object detection
478 篇 image segmentati...
469 篇 cameras

机构

169 篇 univ sci & techn...
146 篇 tsinghua univ pe...
142 篇 univ chinese aca...
142 篇 carnegie mellon ...
132 篇 chinese univ hon...
122 篇 peng cheng lab p...
102 篇 zhejiang univ pe...
96 篇 sensetime res pe...
95 篇 swiss fed inst t...
90 篇 shanghai ai lab ...
86 篇 tsinghua univers...
86 篇 stanford univ st...
84 篇 shanghai jiao to...
80 篇 zhejiang univers...
79 篇 alibaba grp peop...
79 篇 univ hong kong p...
76 篇 peng cheng labor...
76 篇 tech univ munich...
74 篇 australian natl ...
73 篇 peking univ peop...

作者

67 篇 timofte radu
60 篇 van gool luc
50 篇 zhang lei
43 篇 yang yi
36 篇 loy chen change
36 篇 tao dacheng
31 篇 liu yang
30 篇 zhou jie
30 篇 chen chen
30 篇 tian qi
29 篇 sun jian
28 篇 zha zheng-jun
27 篇 qi tian
27 篇 boxin shi
26 篇 li xin
26 篇 vasconcelos nuno
26 篇 pollefeys marc
24 篇 liu xiaoming
24 篇 zheng wei-shi
24 篇 luo ping

语言

11,274 篇 英文
6 篇 其他
1 篇 中文

检索条件"任意字段=2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020"

共 11281 条记录，以下是141-150 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：

VicTR: Video-conditioned Text Representations for Activity recognition

VicTR: Video-conditioned Text Representations for Activity R...

引用

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

作者： Kahatapitiya, Kumara Arnab, Anurag Nagrani, Arsha Ryoo, Michael S. SUNY Stony Brook Stony Brook NY 11794 USA Google Res Mountain View CA USA

ISBN: (纸本)9798350353006

vision-Language models (VLMs) have excelled in the image-domain- especially in zero-shot settings- thanks to the availability of vast pretraining data (i.e., paired image-text samples). However for videos, such paired data is not as abundant. Therefore, video- VLMs are usually designed by adapting pretrained image- VLMs to the video-domain, instead of training from scratch. All such recipes rely on aug-menting visual embeddings with temporal information (i.e., image -+ video), often keeping text embeddings unchanged or even being discarded. In this paper, we argue the contrary, that better video- VLMs can be designed by focusing more on augmenting text, rather than visual information. More specifically, we introduce Video-conditioned Text Representations (Vi c TR): a form of text embeddings optimized w.r.t. vi-sual embeddings, creating a more-flexible contrastive latent space. Our model canfurther make use offreely-available semantic information, in the form of visually- grounded aux-iliary text (e.g. object or scene information). We evaluate our model on few-shot, zero-shot (HMDB-51, UCF-10l), short-form (Kinetics-400) and long-form (Charades) activ-ity recognition benchmarks, showing strong performance among video-VLMs.

关键词： Activity recognition Video Understanding Video-conditioned Text vision-language models

来源：评论

学校读者我要写书评

暂无评论

Language Model Guided Interpretable Video Action Reasoning

Language Model Guided Interpretable Video Action Reasoning

引用

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

作者： Wang, Ning Zhu, Guangming Li, H. S. Zhang, Liang Shah, Syed Afaq Ali Bennamoun, Mohammed Xidian Univ Xian Peoples R China Edith Cowan Univ Joondalup Australia Univ Western Australia Perth Australia

ISBN: (纸本)9798350353006

While neural networks have excelled in video action recognition tasks, their "black-box" nature often obscures the understanding of their decision-making processes. Recent approaches used inherently interpretable models to analyze video actions in a manner akin to human reasoning. These models, however, usually fall short in performance compared to their "black-box" counterparts. In this work, we present a new framework named Language-guided Interpretable Action recognition framework (LaIAR). LaIAR leverages knowledge from language models to enhance both the recognition capabilities and the interpretability of video models. In essence, we redefine the problem of understanding video model decisions as a task of aligning video and language models. Using the logical reasoning captured by the language model, we steer the training of the video model. This integrated approach not only improves the video model's adaptability to different domains but also boosts its overall performance. Extensive experiments on two complex video action datasets, Charades & CAD-120, validates the improved performance and interpretability of our LaIAR framework. The code of LaIAR is available at https://***/NingWang2049/LaIAR.

关键词： action recognition Explainable AI video understanding

来源：评论

学校读者我要写书评

暂无评论

A Study of Dropout-Induced Modality Bias on Robustness to Missing Video Frames for Audio-Visual Speech recognition

A Study of Dropout-Induced Modality Bias on Robustness to Mi...

引用

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

作者： Dai, Yusheng Chen, Hang Du, Jun Wang, Ruoyu Chen, Shihao Wang, Haotian Lee, Chin-Hui Univ Sci & Technol China Hefei Peoples R China Georgia Inst Technol Atlanta GA 30332 USA

ISBN: (纸本)9798350353006

Advanced Audio-Visual Speech recognition (AVSR) systems have been observed to be sensitive to missing video frames, performing even worse than single-modality models. While applying the common dropout techniques to the video modality enhances robustness to missing frames, it simultaneously results in a performance loss when dealing with complete data input. In this study, we delve into this contrasting phenomenon through the lens of modality bias and uncover that an excessive modality bias towards the audio modality induced by dropout constitutes the fundamental cause. Next, we present the Modality Bias Hypothesis (MBH) to systematically describe the relationship between the modality bias and the robustness against missing modality in multimodal systems. Building on these findings, we propose a novel Multimodal Distribution Approximation with Knowledge Distillation (MDA-KD) framework to reduce over-reliance on the audio modality, maintaining performance and robustness simultaneously. Finally, to address an entirely missing modality, we adopt adapters to dynamically switch decision strategies. The effectiveness of our proposed approach is evaluated through comprehensive experiments on the MISP2021 and MISP2022 datasets. Our code is available at https://***/dalision/ModalBiasAVSR.

关键词： Audio-Visual Processing Audio-Visual Speech recognition Multimodality

来源：评论

学校读者我要写书评

暂无评论

Convolutional Prompting meets Language Models for Continual Learning

Convolutional Prompting meets Language Models for Continual ...

引用

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

作者： Roy, Anurag Moulick, Riddhiman Verma, Vinay K. Ghosh, Saptarshi Das, Abir IIT Kharagpur Kharagpur W Bengal India IML Amazon India Hyderabad India

ISBN: (纸本)9798350353006

Continual Learning (CL) enables machine learning models to learn from continuously shifting new training data in absence of data from old tasks. Recently, pretrained vision transformers combined with prompt tuning have shown promise for overcoming catastrophic forgetting in CL. These approaches rely on a pool of learnable prompts which can be inefficient in sharing knowledge across tasks leading to inferior performance. In addition, the lack of fine-grained layer specific prompts does not allow these to fully express the strength of the prompts for CL. We address these limitations by proposing ConvPrompt, a novel convolutional prompt creation mechanism that maintains layer-wise shared embeddings, enabling both layer-specific learning and better concept transfer across tasks. The intelligent use of convolution enables us to maintain a low parameter overhead without compromising performance. We further leverage Large Language Models to generate fine-grained text descriptions of each category which are used to get task similarity and dynamically decide the number of prompts to be learned. Extensive experiments demonstrate the superiority of ConvPrompt and improves SOTA by 3% with significantly less parameter overhead. We also perform strong ablation over various modules to disentangle the importance of different components.(1)

关键词： Continual Learning Language Models Prompt Tuning vision Transformer

来源：评论

学校读者我要写书评

暂无评论

OOSTraj: Out-of-Sight Trajectory Prediction With vision-Positioning Denoising

OOSTraj: Out-of-Sight Trajectory Prediction With Vision-Posi...

引用

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

作者： Zhang, Haichao Xu, Yi Lu, Hongsheng Shimizu, Takayuki Fu, Yun Northeastern Univ 360 Huntington Ave Boston MA 02115 USA Toyota Motor North Amer 465 N Bernardo Ave Mountain View CA 94043 USA

ISBN: (纸本)9798350353006

Trajectory prediction is fundamental in computer vision and autonomous driving, particularly for understanding pedestrian behavior and enabling proactive decision-making. Existing approaches in this field often assume precise and complete observational data, neglecting the challenges associated with out-of-view objects and the noise inherent in sensor data due to limited camera range, physical obstructions, and the absence of ground truth for denoised sensor data. Such oversights are critical safety concerns, as they can result in missing essential, non-visible objects. To bridge this gap, we present a novel method for out-of-sight trajectory prediction that leverages a vision-positioning technique. Our approach denoises noisy sensor observations in an unsupervised manner and precisely maps sensor-based trajectories of out-of-sight objects into visual trajectories. This method has demonstrated state-of-the-art performance in out-of-sight noisy sensor trajectory denoising and prediction on the Vi-Fi and JRDB datasets. By enhancing trajectory prediction accuracy and addressing the challenges of out-of-sight objects, our work significantly contributes to improving the safety and reliability of autonomous driving in complex environments. Our work represents the first initiative towards Out-Of-Sight Trajectory prediction (OOSTraj), setting a new benchmark for future research.

关键词： autonomous driving denosing OOSTraj Out-of-Sight Trajectory Prediction Trajectory Prediction vision-Positioning

来源：评论

学校读者我要写书评

暂无评论

Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary

Transcending the Limit of Local Window: Advanced Super-Resol...

引用

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

作者： Zhang, Leheng Li, Yawei Zhou, Xingyu Zhao, Xiaorui Gu, Shuhang Univ Elect Sci & Technol China Chengdu Peoples R China Swiss Fed Inst Technol Comp Vis Lab Zurich Switzerland Swiss Fed Inst Technol Integrated Syst Lab Zurich Switzerland

ISBN: (纸本)9798350353013;9798350353006

Single Image Super-Resolution is a classic computer vision problem that involves estimating high-resolution (HR) images from low-resolution (LR) ones. Although deep neural networks (DNNs), especially Transformers for super-resolution, have seen significant advancements in recent years, challenges still remain, particularly in limited receptive field caused by window-based self-attention. To address these issues, we introduce a group of auxiliary Adaptive Token Dictionary to SR Transformer and establish an ATD-SR method. The introduced token dictionary could learn prior information from training data and adapt the learned prior to specific testing image through an adaptive refinement step. The refinement strategy could not only provide global information to all input tokens but also group image tokens into categories. Based on category partitions, we further propose a category-based self-attention mechanism designed to leverage distant but similar tokens for enhancing input features. The experimental results show that our method achieves the best performance on various single image super-resolution benchmarks.

关键词： dictionary learning image super-resolution vision transformer

来源：评论

学校读者我要写书评

暂无评论

Task-aligned Part-aware Panoptic Segmentation through Joint Object-Part Representations

Task-aligned Part-aware Panoptic Segmentation through Joint ...

引用

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

作者： de Geus, Daan Dubbelman, Gijs Eindhoven Univ Technol Eindhoven Netherlands

ISBN: (纸本)9798350353013;9798350353006

Part-aware panoptic segmentation (PPS) requires (a) that each foreground object and background region in an image is segmented and classified, and (b) that all parts within foreground objects are segmented, classified and linked to their parent object. Existing methods approach PPS by separately conducting object-level and part-level segmentation. However, their part-level predictions are not linked to individual parent objects. Therefore, their learning objective is not aligned with the PPS task objective, which harms the PPS performance. To solve this, and make more accurate PPS predictions, we propose Task-Aligned Part-aware Panoptic Segmentation (TAPPS). This method uses a set of shared queries to jointly predict (a) object-level segments, and (b) the part-level segments within those same objects. As a result, TAPPS learns to predict part-level segments that are linked to individual parent objects, aligning the learning objective with the task objective, and allowing TAPPS to leverage joint object-part representations. With experiments, we show that TAPPS considerably outperforms methods that predict objects and parts separately, and achieves new state-of-the-art PPS results.

关键词： computer vision image segmentation panoptic segmentation part segmentation part-aware panoptic segmentation scene understanding semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

SocialCounterfactuals: Probing and Mitigating Intersectional Social Biases in vision-Language Models with Counterfactual Examples

SocialCounterfactuals: Probing and Mitigating Intersectional...

引用

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

作者： Howard, Phillip Madasu, Avinash Le, Tiep Moreno, Gustavo Lujan Bhiwandiwalla, Anahita Lal, Vasudev Intel Labs Santa Clara CA 95052 USA

ISBN: (纸本)9798350353006

While vision-language models (VLMs) have achieved remarkable performance improvements recently, there is growing evidence that these models also posses harmful biases with respect to social attributes such as gender and race. Prior studies have primarily focused on probing such bias attributes individually while ignoring biases associated with intersections between social attributes. This could be due to the difficulty of collecting an exhaustive set of image-text pairs for various combinations of social attributes. To address this challenge, we employ text-to-image diffusion models to produce counterfactual examples for probing intersectional social biases at scale. Our approach utilizes Stable Diffusion with cross attention control to produce sets of counterfactual image-text pairs that are highly similar in their depiction of a subject (e.g., a given occupation) while differing only in their depiction of intersectional social attributes (e.g., race & gender). Through our over-generate-then-filter methodology, we produce SocialCounterfactuals, a high-quality dataset containing 171k image-text pairs for probing intersectional biases related to gender, race, and physical characteristics. We conduct extensive experiments to demonstrate the usefulness of our generated dataset for probing and mitigating intersectional social biases in state-of-the-art VLMs.

关键词： counterfactuals Fairness intersectionality social bias vision-language models

来源：评论

学校读者我要写书评

暂无评论

Projecting Trackable Thermal patterns for Dynamic computer vision

Projecting Trackable Thermal Patterns for Dynamic Computer V...

引用

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

作者： Sheinin, Mark Sankaranarayanan, Aswin C. Narasimhan, Srinivasa G. Carnegie Mellon Univ Pittsburgh PA 15213 USA

ISBN: (纸本)9798350353006

Adding artificial patterns to objects, like QR codes, can ease tasks such as object tracking, robot navigation, and conveying information (e.g., a label or a website link). However, these patterns require a physical application and they alter the object's appearance. Conversely, projected patterns can temporarily change the object's appearance, aiding tasks like 3D scanning and retrieving object textures and shading. However, projected patterns impede dynamic tasks like object tracking because they do not 'stick' to the object's surface. Or do they? This paper introduces a novel approach combining the advantages of projected and persistent physical patterns. Our system projects heat patterns using a laser beam (similar in spirit to a LIDAR), which a thermal camera observes and tracks. Such thermal patterns enable tracking poorly-textured objects whose tracking is highly challenging with standard cameras while not affecting the object's appearance or physical properties. To avail these thermal patterns in existing vision frameworks, we train a network to reverse heat diffusion's effects and remove inconsistent pattern points between different thermal frames. We prototyped and tested this approach on dynamic vision tasks like structure from motion, optical flow, and object tracking of everyday textureless objects.

关键词： 3d reconstruction heat Heat diffusion laser optical flow slam structure from motion thermal tracking

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

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 << < 11 12 13 14 15 16 17 18 19 20 > >>

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：