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

20,798 篇 会议
87 篇 期刊文献
65 册 图书

馆藏范围

20,949 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

13,274 篇 工学
- 10,922 篇 计算机科学与技术...
- 2,484 篇 机械工程
- 2,307 篇 软件工程
- 913 篇 光学工程
- 770 篇 电气工程
- 556 篇 控制科学与工程
- 405 篇 信息与通信工程
- 210 篇 测绘科学与技术
- 131 篇 生物医学工程（可授...
- 104 篇 电子科学与技术（可...
- 100 篇 生物工程
- 92 篇 仪器科学与技术
- 56 篇 化学工程与技术
- 52 篇 建筑学
- 48 篇 土木工程
- 44 篇 安全科学与工程
- 38 篇 力学（可授工学、理...
- 38 篇 航空宇航科学与技...
- 35 篇 交通运输工程
3,457 篇 医学
- 3,449 篇 临床医学
- 34 篇 基础医学(可授医学...
2,315 篇 理学
- 1,154 篇 数学
- 1,132 篇 物理学
- 417 篇 统计学（可授理学、...
- 386 篇 生物学
- 252 篇 系统科学
- 57 篇 化学
353 篇 管理学
- 184 篇 图书情报与档案管...
- 176 篇 管理科学与工程(可...
- 32 篇 工商管理
28 篇 法学
20 篇 农学
15 篇 教育学
9 篇 经济学
8 篇 艺术学
5 篇 文学
5 篇 军事学

主题

8,202 篇 computer vision
3,009 篇 pattern recognit...
2,732 篇 training
1,769 篇 computational mo...
1,657 篇 visualization
1,482 篇 cameras
1,415 篇 shape
1,369 篇 three-dimensiona...
1,369 篇 face recognition
1,285 篇 image segmentati...
1,272 篇 feature extracti...
1,178 篇 robustness
1,090 篇 semantics
1,040 篇 layout
1,006 篇 object detection
975 篇 object recogniti...
968 篇 computer science
946 篇 computer archite...
946 篇 benchmark testin...
931 篇 codes

机构

174 篇 univ sci & techn...
154 篇 carnegie mellon ...
148 篇 univ chinese aca...
144 篇 chinese univ hon...
113 篇 microsoft resear...
103 篇 zhejiang univ pe...
99 篇 swiss fed inst t...
97 篇 tsinghua univ pe...
93 篇 tsinghua univers...
91 篇 microsoft res as...
88 篇 shanghai ai lab ...
81 篇 zhejiang univers...
76 篇 alibaba grp peop...
74 篇 hong kong univ s...
73 篇 university of sc...
72 篇 peking univ peop...
69 篇 university of ch...
68 篇 shanghai jiao to...
66 篇 google res mount...
66 篇 univ oxford oxfo...

作者

80 篇 van gool luc
71 篇 zhang lei
59 篇 timofte radu
48 篇 yang yi
47 篇 xiaoou tang
44 篇 darrell trevor
43 篇 tian qi
43 篇 luc van gool
42 篇 loy chen change
42 篇 sun jian
42 篇 li fei-fei
40 篇 qi tian
39 篇 li stan z.
37 篇 liu yang
37 篇 chen xilin
36 篇 shan shiguang
35 篇 liu xiaoming
35 篇 vasconcelos nuno
35 篇 torralba antonio
32 篇 zhou jie

语言

20,927 篇 英文
14 篇 中文
6 篇 其他
2 篇 日文
2 篇 土耳其文

检索条件"任意字段=2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009"

共 20950 条记录，以下是461-470 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：

Doubly Right Object recognition: A Why Prompt for Visual Rationales

Doubly Right Object Recognition: A Why Prompt for Visual Rat...

引用

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

作者： Mao, Chengzhi Teotial, Revant Sundari, Amrutha Menon, Sachit Yang, Junfeng Wang, Xin Vondrick, Carl Columbia Univ New York NY 10027 USA Microsoft Res Redmond WA USA

ISBN: (纸本)9798350301298

Many visual recognition models are evaluated only on their classification accuracy, a metric for which they obtain strong performance. In this paper, we investigate whether computer vision models can also provide correct rationales for their predictions. We propose a "doubly right" object recognition benchmark, where the metric requires the model to simultaneously produce both the right labels as well as the right rationales. We find that state-of-the-art visual models, such as CLIP, often provide incorrect rationales for their categorical predictions. However, by transferring the rationales from language models into visual representations through a tailored dataset, we show that we can learn a "why prompt," which adapts large visual representations to produce correct rationales. Visualizations and empirical experiments show that our prompts significantly improve performance on doubly right object recognition, in addition to zero-shot transfer to unseen tasks and datasets.

关键词： Explainable computer vision

来源：评论

学校读者我要写书评

暂无评论

Single-Model and Any-Modality for Video Object Tracking

Single-Model and Any-Modality for Video Object Tracking

引用

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

作者： Wu, Zongwei Zheng, Jilai Ren, Xiangxuan Vasluianu, Florin-Alexandru Ma, Chao Paudel, Danda Pani Luc Van Gool Timofte, Radu Univ Wurzburg Comp Vision Lab CAIDAS & IFI Wurzburg Germany Shanghai Jiao Tong Univ AI Inst Shanghai Peoples R China Sofia Univ INSAIT Sofia Bulgaria Swiss Fed Inst Technol CVL Zurich Switzerland

ISBN: (纸本)9798350353006

In the realm of video object tracking, auxiliary modalities such as depth, thermal, or event data have emerged as valuable assets to complement the RGB trackers. In practice, most existing RGB trackers learn a single set of parameters to use them across datasets and applications. However, a similar single-model unification for multimodality tracking presents several challenges. These challenges stem from the inherent heterogeneity of inputs - each with modality-specific representations, the scarcity of multi-modal datasets, and the absence of all the modalities at all times. In this work, we introduce Un-Track, a Unified Tracker of a single set of parameters for any modality. To handle any modality, our method learns their common latent space through low-rank factorization and reconstruction techniques. More importantly, we use only the RGBX pairs to learn the common latent space. This unique shared representation seamlessly binds all modalities together, enabling effective unification and accommodating any missing modality, all within a single transformer-based architecture. Our Un-Track achieves +8.1 absolute F-score gain, on the DepthTrack dataset, by introducing only +2.14 (over 21.50) GFLOPs with +6.6M (over 93M) parameters, through a simple yet efficient prompting strategy. Extensive comparisons on five benchmark datasets with different modalities show that Un-Track surpasses both SOTA unified trackers and modality-specific counterparts, validating our effectiveness and practicality. The source code is publicly available at https:// github. com/ Zongwei97/ UnTrack.

关键词：

来源：评论

学校读者我要写书评

暂无评论

What, when, and where? Self-Supervised Spatio-Temporal Grounding in Untrimmed Multi-Action Videos from Narrated Instructions

What, when, and where? Self-Supervised Spatio-Temporal Groun...

引用

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

作者： Chen, Brian Shvetsova, Nina Rouditchenko, Andrew Kondermann, Daniel Thomas, Samuel Chang, Shih-Fu Feris, Rogerio Glass, James Kuehne, Hilde Columbia Univ New York NY 10027 USA Goethe Univ Frankfurt Frankfurt Germany Univ Bonn Bonn Germany MIT CSAIL Cambridge MA USA Qual Match GmbH Heidelberg Germany IBM Res AI Yorktown Hts NY USA MIT IBM Watson Lab Cambridge MA USA

ISBN: (纸本)9798350353006

Spatio-temporal grounding describes the task of localizing events in space and time, e.g., in video data, based on verbal descriptions only. Models for this task are usually trained with human-annotated sentences and bounding box supervision. This work addresses this task from a multimodal supervision perspective, proposing a frame-work for spatio-temporal action grounding trained on loose video and subtitle supervision only, without human annotation. To this end, we combine local representation learning, which focuses on leveraging fine-grained spatial information, with a global representation encoding that captures higher-level representations and incorporates both in a joint approach. To evaluate this challenging task in a real-life setting, a new benchmark dataset is proposed, providing dense spatio-temporal grounding annotations in long, untrimmed, multi-action instructional videos for over 5K events. We evaluate the proposed approach and other methods on the proposed and standard downstream tasks, showing that our method improves over current baselines in various settings, including spatial, temporal, and untrimmed multi-action spatio-temporal grounding.

关键词： Grounding Multimodal learning Self-supervised learning Video understanding vision and language

来源：评论

学校读者我要写书评

暂无评论

Behavioral Analysis of vision-and-Language Navigation Agents

Behavioral Analysis of Vision-and-Language Navigation Agents

引用

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

作者： Yang, Zijiao Majumdar, Arjun Lee, Stefan Oregon State Univ Corvallis OR 97331 USA Georgia Inst Technol Atlanta GA USA

ISBN: (纸本)9798350301298

To be successful, vision-and-Language Navigation (VLN) agents must be able to ground instructions to actions based on their surroundings. In this work, we develop a methodology to study agent behavior on a skill-specific basis - examining how well existing agents ground instructions about stopping, turning, and moving towards specified objects or rooms. Our approach is based on generating skill-specific interventions and measuring changes in agent predictions. We present a detailed case study analyzing the behavior of a recent agent and then compare multiple agents in terms of skill-specific competency scores. This analysis suggests that biases from training have lasting effects on agent behavior and that existing models are able to ground simple referring expressions. Our comparisons between models show that skill-specific scores correlate with improvements in overall VLN task performance.

关键词： language reasoning vision

来源：评论

学校读者我要写书评

暂无评论

Deep Video Codec Control for vision Models

Deep Video Codec Control for Vision Models

引用

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

作者： Reich, Christoph Debnath, Biplob Patel, Deep Prangemeier, Tim Cremers, Daniel Chakradhar, Srimat NEC Labs Amer Inc San Jose CA 95110 USA Tech Univ Munich Munich Germany Tech Univ Darmstadt Darmstadt Germany Munich Ctr Machine Learning MCML Munich Germany

ISBN: (纸本)9798350365474

Standardized lossy video coding is at the core of almost all real-world video processing pipelines. Rate control is used to enable standard codecs to adapt to different network bandwidth conditions or storage constraints. However, standard video codecs (e.g., H.264) and their rate control modules aim to minimize video distortion w.r.t. human quality assessment. We demonstrate empirically that standard-coded videos vastly deteriorate the performance of deep vision models. To overcome the deterioration of vision performance, this paper presents the first end-to-end learnable deep video codec control that considers both bandwidth constraints and downstream deep vision performance, while adhering to existing standardization. We demonstrate that our approach better preserves downstream deep vision performance than traditional standard video coding.

关键词： Codec Coding for Machines Deep Video Codec Control Deep vision Models End-to-end Learning Rate Control Self-supervised Learning Standardization Video Coding

来源：评论

学校读者我要写书评

暂无评论

Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for vision Applications

Efficient Deformable ConvNets: Rethinking Dynamic and Sparse...

引用

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

作者： Xiong, Yuwen Li, Zhiqi Chen, Yuntao Wang, Feng Zhu, Xizhou Luo, Jiapeng Wang, Wenhai Lu, Tong Li, Hongsheng Qiao, Yu Lu, Lewei Zhou, Jie Dai, Jifeng Univ Toronto Toronto ON Canada Shanghai AI Lab OpenGVLab Shanghai Peoples R China Nanjing Univ Nanjing Peoples R China Chinese Acad Sci CAIR HKISI Beijing Peoples R China Tsinghua Univ Beijing Peoples R China SenseTime Res Hong Kong Peoples R China Chinese Univ Hong Kong Hong Kong Peoples R China

ISBN: (纸本)9798350353013;9798350353006

We introduce Deformable Convolution v4 (DCNv4), a highly efficient and effective operator designed for a broad spectrum of vision applications. DCNv4 addresses the limitations of its predecessor, DCNv3, with two key enhancements: 1. removing softmax normalization in spatial aggregation to enhance its dynamic property and expressive power and 2. optimizing memory access to minimize redundant operations for speedup. These improvements result in a significantly faster convergence compared to DCNv3 and a substantial increase in processing speed, with DCNv4 achieving more than three times the forward speed. DCNv4 demonstrates exceptional performance across various tasks, including image classification, instance and semantic segmentation, and notably, image generation. When integrated into generative models like U-Net in the latent diffusion model, DCNv4 outperforms its baseline, underscoring its possibility to enhance generative models. In practical applications, replacing DCNv3 with DCNv4 in the InternImage model to create FlashInternImage results in up to 80% speed increase and further performance improvement without further modifications. The advancements in speed and efficiency of DCNv4, combined with its robust performance across diverse vision tasks, show its potential as a foundational building block for future vision models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Super-Resolution Reconstruction from Bayer-pattern Spike Streams

Super-Resolution Reconstruction from Bayer-Pattern Spike Str...

引用

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

作者： Dong, Yanchen Xiong, Ruiqin Zhang, Jian Yu, Zhaofei Fan, Xiaopeng Zhu, Shuyuan Huang, Tiejun Peking Univ Sch Comp Sci Beijing Peoples R China Peking Univ Sch Elect & Comp Engn Beijing Peoples R China Peking Univ Inst Artificial Intelligence Beijing Peoples R China Harbin Inst Technol Sch Comp Sci & Technol Harbin Peoples R China Univ Elect Sci & Technol China Chengdu Peoples R China

ISBN: (纸本)9798350353006

Spike camera is a neuromorphic vision sensor that can capture highly dynamic scenes by generating a continuous stream of binary spikes to represent the arrival of photons at very high temporal resolution. Equipped with Bayer color filter array (CFA), color spike camera (CSC) has been invented to capture color information. Although spike camera has already demonstrated great potential for high-speed imaging, its spatial resolution is limited compared with conventional digital cameras. This paper proposes a Color Spike Camera Super-Resolution (CSCSR) network to super-resolve higher-resolution color images from spike camera streams with Bayer CFA. To be specific, we first propose a representation for Bayer-pattern spike streams, exploring local temporal information with global perception to represent the binary data. Then we exploit the CFA layout and sub-pixel level motion to collect temporal pixels for the spatial super-resolution of each color channel. In particular, a residual-based module for feature refinement is developed to reduce the impact of motion estimation errors. Considering color correlation, we jointly utilize the multi-stage temporal-pixel features of color channels to reconstruct the high-resolution color image. Experimental results demonstrate that the proposed scheme can reconstruct satisfactory color images with both high temporal and spatial resolution from low-resolution Bayer-pattern spike streams. The source codes are available at https://***/csycdong/CSCSR.

关键词： Bayer pattern Color filter arrary Demosaicing Neuromorphic sensor Spike camera Super resolution

来源：评论

学校读者我要写书评

暂无评论

IDGI: A Framework to Eliminate Explanation Noise from Integrated Gradients

IDGI: A Framework to Eliminate Explanation Noise from Integr...

引用

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

作者： Yang, Ruo Wang, Binghui Bilgic, Mustafa IIT Dept Comp Sci Chicago IL 60616 USA

ISBN: (纸本)9798350301298

Integrated Gradients (IG) as well as its variants are well-known techniques for interpreting the decisions of deep neural networks. While IG-based approaches attain state-of-the-art performance, they often integrate noise into their explanation saliency maps, which reduce their interpretability. To minimize the noise, we examine the source of the noise analytically and propose a new approach to reduce the explanation noise based on our analytical findings. We propose the Important Direction Gradient Integration (IDGI) framework, which can be easily incorporated into any IG-based method that uses the Reimann Integration for integrated gradient computation. Extensive experiments with three IG-based methods show that IDGI improves them drastically on numerous interpretability metrics. The source code for IDGI is available at https://***/yangruo1226/IDGI.

关键词： Explainable computer vision

来源：评论

学校读者我要写书评

暂无评论

Collaborative Visual Place recognition through Federated Learning

Collaborative Visual Place Recognition through Federated Lea...

引用

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

作者： Dutto, Mattia Berton, Gabriele Caldarola, Debora Fani, Eros Trivigno, Gabriele Masone, Carlo Politecn Torino Turin Italy

ISBN: (纸本)9798350365474

Visual Place recognition (VPR) aims to estimate the location of an image by treating it as a retrieval problem. VPR uses a database of geo-tagged images and leverages deep neural networks to extract a global representation, called descriptor, from each image. While the training data for VPR models often originates from diverse, geographically scattered sources (geo-tagged images), the training process itself is typically assumed to be centralized. This research revisits the task of VPR through the lens of Federated Learning (FL), addressing several key challenges associated with this adaptation. VPR data inherently lacks well-defined classes, and models are typically trained using contrastive learning, which necessitates a data mining step on a centralized database. Additionally, client devices in federated systems can be highly heterogeneous in terms of their processing capabilities. The proposed FedVPR framework not only presents a novel approach for VPR but also introduces a new, challenging, and realistic task for FL research, paving the way to other image retrieval tasks in FL.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

RGB no more: Minimally-decoded JPEG vision Transformers

RGB no more: Minimally-decoded JPEG Vision Transformers

引用

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

作者： Park, Jeongsoo Johnson, Justin Univ Michigan Ann Arbor MI 48109 USA

ISBN: (纸本)9798350301298

Most neural networks for computer vision are designed to infer using RGB images. However, these RGB images are commonly encoded in JPEG before saving to disk;decoding them imposes an unavoidable overhead for RGB networks. Instead, our work focuses on training vision Transformers (ViT) directly from the encoded features of JPEG. This way, we can avoid most of the decoding overhead, accelerating data load. Existing works have studied this aspect but they focus on CNNs. Due to how these encoded features are structured, CNNs require heavy modification to their architecture to accept such data. Here, we show that this is not the case for ViTs. In addition, we tackle data augmentation directly on these encoded features, which to our knowledge, has not been explored in-depth for training in this setting. With these two improvements - ViT and data augmentation - we show that our ViT-Ti model achieves up to 39.2% faster training and 17.9% faster inference with no accuracy loss compared to the RGB counterpart. (1)

关键词： and reasoning language vision

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 << < 43 44 45 46 47 48 49 50 51 52 > >>

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：