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361-370 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：

MV-TAL: Mulit-view Temporal Action Localization in Naturalistic Driving

MV-TAL: Mulit-view Temporal Action Localization in Naturalis...

引用

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

作者： Li, Wei Chen, Shimin Gu, Jianyang Wang, Ning Chen, Chen Guo, Yandong OPPO Res Inst Beijing Peoples R China Zhejiang Univ Hangzhou Peoples R China East China Univ Sci & Technol Shanghai Peoples R China

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Human risky behavior in driving is an important visual recognition problem. In this paper, we propose a multi-view temporal action localization system based on the grayscale video to achieve action recognition in naturalistic driving. Specifically, we adopted SwinTransformer as feature extractor, and a single framework to detect boundary and class at the same time. Also, we improve multiple loss function for explicit constraints of embedded feature distributions. Our proposed framework achieves the overall F1 -score of 0.3154 on A2 dataset.

关键词： Location awareness Measurement Visualization computer vision conferences Aggregates Gray-scale

来源：评论

学校读者我要写书评

暂无评论

SHViT: Single-Head vision Transformer with Memory Efficient Macro Design

SHViT: Single-Head Vision Transformer with Memory Efficient ...

引用

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

作者： Yun, Seokju Ro, Youngmin Univ Seoul Machine Intelligence Lab Seoul South Korea

ISBN: (纸本)9798350353013;9798350353006

Recently, efficient vision Transformers have shown great performance with low latency on resource-constrained devices. Conventionally, they use 4x4 patch embeddings and a 4-stage structure at the macro level, while utilizing sophisticated attention with multi-head configuration at the micro level. This paper aims to address computational redundancy at all design levels in a memory-efficient manner. We discover that using larger-stride patchify stem not only reduces memory access costs but also achieves competitive performance by leveraging token representations with reduced spatial redundancy from the early stages. Furthermore, our preliminary analyses suggest that attention layers in the early stages can be substituted with convolutions, and several attention heads in the latter stages are computationally redundant. To handle this, we introduce a single-head attention module that inherently prevents head redundancy and simultaneously boosts accuracy by parallelly combining global and local information. Building upon our solutions, we introduce SHViT, a SingleHead vision Transformer that obtains the state-of-the-art speed-accuracy tradeoff. For example, on ImageNet-1k, our SHViT-S4 is 3.3x, 8.1x, and 2.4x faster than MobileViTv2 x1.0 on GPU, CPU, and iPhone12 mobile device, respectively, while being 1.3% more accurate. For object detection and instance segmentation on MS COCO using MaskRCNN head, our model achieves performance comparable to FastViT-SA12 while exhibiting 3.8x and 2.0x lower backbone latency on GPU and mobile device, respectively.

关键词： CNNs efficient visual backbone vision Transformer

来源：评论

学校读者我要写书评

暂无评论

Robustness and Adaptation to Hidden Factors of Variation

Robustness and Adaptation to Hidden Factors of Variation

引用

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

作者： Paul, William Burlina, Philippe Johns Hopkins Univ Appl Phys Lab Laurel MD 20723 USA

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

We tackle here a specific, still not widely addressed aspect, of AI robustness, which consists of seeking invariance / insensitivity of model performance to hidden factors of variations in the data. Towards this end, we employ a two step strategy that a) does unsupervised discovery, via generative models, of sensitive factors that cause models to under-perform, and b) intervenes models to make their performance invariant to these sensitive factors' influence. We consider 3 separate interventions for robustness, including: data augmentation, semantic consistency, and adversarial alignment. We evaluate our method using metrics that measure trade offs between invariance (insensitivity) and overall performance (utility) and show the benefits of our method for 3 settings (unsupervised, semi-supervised and generalization).

关键词： Measurement computer vision conferences Semantics Robustness Data models pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Masked AutoDecoder is Effective Multi-Task vision Generalist

Masked AutoDecoder is Effective Multi-Task Vision Generalist

引用

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

作者： Qiu, Han Huang, Jiaxing Gao, Peng Lu, Lewei Zhang, Xiaoqin Lu, Shijian Nanyang Technol Univ S Lab Singapore Singapore Shanghai Artificial Intelligence Lab Shanghai Peoples R China Sensetime Res Beijing Peoples R China Zhejiang Univ Technol Coll Comp Sci & Technol Hangzhou Peoples R China

ISBN: (纸本)9798350353006

Inspired by the success of general-purpose models in NLP, recent studies attempt to unify different vision tasks in the same sequence format and employ autoregressive Transformers for sequence prediction. They apply uni-directional attention to capture sequential dependencies and generate task sequences recursively. However, such autoregressive Transformers may not fit vision tasks well, as vision task sequences usually lack the sequential dependencies typically observed in natural languages. In this work, we design Masked AutoDecoder (MAD), an effective multi-task vision generalist. MAD consists of two core designs. First, we develop a parallel decoding framework that introduces bi-directional attention to capture contextual dependencies comprehensively and decode vision task sequences in parallel. Second, we design a masked sequence modeling approach that learns rich task contexts by masking and reconstructing task sequences. In this way, MAD handles all the tasks by a single network branch and a simple cross-entropy loss with minimal task-specific designs. Extensive experiments demonstrate the great potential of MAD as a new paradigm for unifying various vision tasks. MAD achieves superior performance and inference efficiency compared to autoregressive counterparts while obtaining competitive accuracy with task-specific models. Code will be released at https://***/hanqiu-hq/MAD.

关键词： Masked AutoDecoder Masked Sequence Modeling Transformer vision Generalist

来源：评论

学校读者我要写书评

暂无评论

Boosting Adversarial Transferability by Block Shuffle and Rotation

Boosting Adversarial Transferability by Block Shuffle and Ro...

引用

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

作者： Wang, Kunyu He, Xuanran Wang, Wenxuan Wang, Xiaosen Chinese Univ Hong Kong Hong Kong Peoples R China Nanyang Technol Univ Singapore Singapore Huawei Singular Secur Lab Beijing Peoples R China

ISBN: (纸本)9798350353006

Adversarial examples mislead deep neural networks with imperceptible perturbations and have brought significant threats to deep learning. An important aspect is their transferability, which refers to their ability to deceive other models, thus enabling attacks in the black-box setting. Though various methods have been proposed to boost transferability, the performance still falls short compared with white-box attacks. In this work, we observe that existing input transformation based attacks, one of the mainstream transfer-based attacks, result in different attention heatmaps on various models, which might limit the transferability. We also find that breaking the intrinsic relation of the image can disrupt the attention heatmap of the original image. Based on this finding, we propose a novel input transformation based attack called block shuffle and rotation (BSR). Specifically, BSR splits the input image into several blocks, then randomly shuffles and rotates these blocks to construct a set of new images for gradient calculation. Empirical evaluations on the ImageNet dataset demonstrate that BSR could achieve significantly better transferability than the existing input transformation based methods under single-model and ensemble-model settings. Combining BSR with the current input transformation method can further improve the transferability, which significantly outperforms the state-of-the-art methods. Code is available at https://***/Trustworthy-AI-Group/BSR.

关键词： adversarial attack computer vision

来源：评论

学校读者我要写书评

暂无评论

User-Guided Variable Rate Learned Image Compression

User-Guided Variable Rate Learned Image Compression

引用

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

作者： Gupta, Rushil Suryateja, B., V Kapoor, Nikhil Jaiswal, Rajat Nangi, Sharmila Kulkarni, Kuldeep Adobe Res Bengaluru India Indian Inst Technol Delhi Delhi India Stanford Univ Stanford CA 94305 USA

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

We propose a learning-based image compression method that achieves any arbitrary input bitrate via user-guided bit allocation to preferred regions. We verify our hypothesis of incorporating user guidance for bitrate control by experimenting with alternatives that do not have any guidance. We conduct extensive evaluation on CelebA-HQ and CityScapes dataset using standard quantitative metrics and human studies showing that our single model for multiple bitrates achieves similar or better performance as compared to previous learned image compression methods that require re-training for each new bitrate.

关键词： Measurement computer vision Image coding conferences Computational modeling Bit rate pattern recognition

来源：评论

学校读者我要写书评

暂无评论

PeVL: Pose-Enhanced vision-Language Model for Fine-Grained Human Action recognition

PeVL: Pose-Enhanced Vision-Language Model for Fine-Grained H...

引用

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

作者： Zhang, Haosong Leong, Mei Chee Li, Liyuan Lin, Weisi Nanyang Technol Univ Inst Infocomm Res I2R A STAR Singapore Singapore

ISBN: (纸本)9798350353006

Recent progress in vision-Language (VL) foundation models has revealed the great advantages of cross-modality learning. However, due to a large gap between vision and text, they might not be able to sufficiently utilize the benefits of cross-modality information. In the field of human action recognition, the additional pose modality may bridge the gap between vision and text to improve the effectiveness of cross-modality learning. In this paper, we propose a novel framework, called Pose-enhanced vision-Language (PeVL) model, to adapt the VL model with pose modality to learn effective knowledge of fine-grained human actions. Our PeVL model includes two novel components: an Unsymmetrical Cross-Modality Refinement (UCMR) block and a Semantic-Guided Multi-level Contrastive (SGMC) module. The UCMR block includes Pose-guided Visual Refinement (P2V-R) and Visual-enriched Pose Refinement (V2P-R) for effective cross-modality learning. The SGMC module includes Multi-level Contrastive Associations of vision-text and pose-text at both action and sub-action levels, and a Semantic-Guided Loss, enabling effective contrastive learning with text. Built upon a pre-trained VL foundation model, our model integrates trainable adapters and can be trained end-to-end. Our novel PeVL design over VL foundation model yields remarkable performance gains on four fine-grained human action recognition datasets, achieving a new SOTA with a significantly small number of FLOPs for low-cost re-training.(1)

关键词： Semantics

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-Modal Hallucination Control by Visual Information Grounding

Multi-Modal Hallucination Control by Visual Information Grou...

引用

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

作者： Favero, Alessandro Zancato, Luca Trager, Matthew Choudhary, Siddharth Perera, Pramuditha Achille, Alessandro Swaminathan, Ashwin Soatto, Stefano AWS AI Labs Lausanne Switzerland

ISBN: (纸本)9798350353006

Generative vision-Language Models (VLMs) are prone to generate plausible-sounding textual answers that, however, are not always grounded in the input image. We investigate this phenomenon, usually referred to as "hallucination" and show that it stems from an excessive reliance on the language prior. In particular, we show that as more tokens are generated, the reliance on the visual prompt decreases, and this behavior strongly correlates with the emergence of hallucinations. To reduce hallucinations, we introduce Multi-Modal Mutual-Information Decoding (M3ID), a new sampling method for prompt amplification. M3ID amplifies the influence of the reference image over the language prior, hence favoring the generation of tokens with higher mutual information with the visual prompt. M3ID can be applied to any pre-trained autoregressive VLM at inference time without necessitating further training and with minimal computational overhead. If training is an option, we show that M3ID can be paired with Direct Preference Optimization ( DPO) to improve the model's reliance on the prompt image without requiring any labels. Our empirical findings show that our algorithms maintain the fluency and linguistic capabilities of pre-trained VLMs while reducing hallucinations by mitigating visually ungrounded answers. Specifically, for the LLaVA 13B model, M3ID and M3ID+DPO reduce the percentage of hallucinated objects in captioning tasks by 25% and 28%, respectively, and improve the accuracy on VQA benchmarks such as POPE by 21% and 24%.

关键词： language reasoning vision

来源：评论

学校读者我要写书评

暂无评论

CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attention

CAD-SIGNet: CAD Language Inference from Point Clouds using L...

引用

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

作者： Khan, Mohammad Sadil Dupont, Elona Ali, Sk Aziz Cherenkova, Kseniya Kacem, Anis Aouada, Djamila Univ Luxembourg SnT Luxembourg Luxembourg German Res Ctr Artificial Intelligence Berlin Germany Artec3D Luxembourg Luxembourg

ISBN: (纸本)9798350353013;9798350353006

Reverse engineering in the realm of computer-Aided Design (CAD) has been a longstanding aspiration, though not yet entirely realized. Its primary aim is to uncover the CAD process behind a physical object given its 3D scan. We propose CAD- SIGNet, an end-to-end trainable and aeto-regressive architecture to recover the design history of a CAD model represented as a sequence of sketch-and-extrusion from an input point cloud. Our model learns CAD visual-language representations by layer-wise cross-attention between point cloud and CAD language embedding. In particular, a new Sketch instance Guided Attention (SGA) module is proposed in order to reconstruct the fine-grained details of the sketches. Thanks to its auto-regressive nature, CAD-SIGNet not only reconstructs a unique full design history of the corresponding CAD model given an input point cloud but also provides multiple plausible design choices. This allows for an interactive reverse engineering scenario by providing designers with multiple next step choices along with the design process. Extensive experiments on publicly available CAD datasets showcase the effectiveness of our approach against existing baseline models in two settings, namely, full design history recovery and conditional autocompletion from point clouds.

关键词： 3D Point Clouds computer-Aided Design (CAD) Reverse Engineering 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466页 << < 33 34 35 36 37 38 39 40 41 42 > >>

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：