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

11,273 篇 英文
7 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251-260 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：

Boosting Continual Learning of vision-Language Models via Mixture-of-Experts Adapters

Boosting Continual Learning of Vision-Language Models via Mi...

引用

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

作者： Yu, Jiazuo Zhuge, Yunzhi Zhang, Lu Hu, Ping Wang, Dong Lu, Huchuan He, You Dalian Univ Technol Dalian Peoples R China Univ Elect Sci & Technol China Chengdu Peoples R China Tsinghua Univ Beijing Peoples R China

ISBN: (纸本)9798350353006

Continual learning can empower vision-language models to continuously acquire new knowledge, without the need for access to the entire historical dataset. However, mitigating the performance degradation in large-scale models is non-trivial due to (i) parameter shifts throughout life-long learning and (ii) significant computational burdens associated with full-model tuning. In this work, we present a parameter-efficient continual learning framework to alleviate long-term forgetting in incremental learning with vision-language models. Our approach involves the dynamic expansion of a pre-trained CLIP model, through the integration of Mixture-of-Experts (MoE) adapters in response to new tasks. To preserve the zero-shot recognition capability of vision-language models, we further introduce a Distribution Discriminative Auto-Selector (DDAS) that automatically routes in-distribution and out-of-distribution inputs to the MoE Adapter and the original CLIP, respectively. Through extensive experiments across various settings, our proposed method consistently outperforms previous state-of-the-art approaches while concurrently reducing parameter training burdens by 60%. Our code locates at https://***/JiazuoYu/MoE-Adapters4CL

关键词： class incremental learning continual learning task incremental learning vision-Language Model

来源：评论

学校读者我要写书评

暂无评论

Unravelling Robustness of Deep Face recognition Networks Against Illicit Drug Abuse Images

Unravelling Robustness of Deep Face Recognition Networks Aga...

引用

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

作者： Dhake, Hruturaj Agarwal, Akshay IISER Bhopal Data Sci & Engn Bhopal India

ISBN: (纸本)9798350365474

Alteration in facial features can lead to a significant drop in recognition performance. These alterations can be due to several factors: one such prominent and less explored factor is illicit drug abuse. To advance the understanding of how drug abuse faces affect the performance of state-of-the-art deep face recognition (DFR) networks, in this study, we have utilized clean and illicit drug abuse faces. Extensive studies are performed on deep face recognition and soft biometric identification, such as gender, ethnicity, and expression recognition. It is observed that illicit drug abuse not only impacts the identity recognition performance but also degrades the soft biometrics identification accuracy. Therefore, to advance the integrity of DFR, we have performed the detection of illicit drug abuse as a potential solution to its mitigation. In the end, the robustness of the drug abuse face detector is evaluated under the prominent use of social-media filters on face images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning

Troika: Multi-Path Cross-Modal Traction for Compositional Ze...

引用

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

作者： Hu, Siteng Gong, Biao Feng, Yutong Zhang, Min Lv, Yiliang Wang, Donglin Zhejiang Univ Hangzhou Peoples R China Alibaba Grp Hangzhou Peoples R China Westlake Univ Sch Engn AI Div Machine Intelligence Lab MiLAB Hangzhou Peoples R China

ISBN: (纸本)9798350353006

Recent compositional zero-shot learning (CZSL) methods adapt pre-trained vision-language models (VLMs) by constructing trainable prompts only for composed state-object pairs. Relying on learning the joint representation of seen compositions, these methods ignore the explicit modeling of the state and object, thus limiting the exploitation of pre-trained knowledge and generalization to unseen compositions. With a particular focus on the universality of the solution, in this work, we propose a novel paradigm for CZSL models that establishes three identification branches (i.e., Multi-Path) to jointly model the state, object, and composition. The presented Troika is an outstanding implementation that aligns the branch-specific prompt representations with decomposed visual features. To calibrate the bias between semantically similar multi-modal representations, we further devise a Cross-Modal Traction module into Troika that shifts the prompt representation towards the current visual content. We conduct extensive experiments on three popular benchmarks, where our method significantly outperforms existing methods in both closed-world and open-world settings. The code will be available at https://***/bighuang624/Troika.

关键词： compositional zero-shot learning parameter-efficient transfer learning Troika vision-language models

来源：评论

学校读者我要写书评

暂无评论

ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts

ViP-LLaVA: Making Large Multimodal Models Understand Arbitra...

引用

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

作者： Cai, Mu Liu, Haotian Mustikovela, Siva Karthik Meyer, Gregory P. Chai, Yuning Park, Dennis Lee, Yong Jae Univ Wisconsin Madison WI 53706 USA Cruise LLC San Francisco CA USA

ISBN: (纸本)9798350353006

While existing large vision-language multimodal models focus on whole image understanding, there is a prominent gap in achieving region-specific comprehension. Current approaches that use textual coordinates or spatial encodings often fail to provide a user-friendly interface for visual prompting. To address this challenge, we introduce a novel multimodal model capable of decoding arbitrary (free-form) visual prompts. This allows users to intuitively mark images and interact with the model using natural cues like a "red bounding box" or "pointed arrow". Our simple design directly overlays visual markers onto the RGB image, eliminating the need for complex region encodings, yet achieves state-of-the-art performance on region-understanding tasks like Visual7W, PointQA, and Visual Commonsense Reasoning benchmark. Furthermore, we present ViP-Bench, a comprehensive benchmark to assess the capability of models in understanding visual prompts across multiple dimensions, enabling future research in this domain. Code, data, and model are publicly available.

关键词： Large Language Models Large Multimodal Models Multimodal Benchmark Region-level Understanding vision-language models Visual Commonsense Reasoning Visual Prompts

来源：评论

学校读者我要写书评

暂无评论

Generating Enhanced Negatives for Training Language-Based Object Detectors

Generating Enhanced Negatives for Training Language-Based Ob...

引用

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

作者： Zhao, Shiyu Zhao, Long Kumar, Vijay B. G. Suh, Yumin Metaxas, Dimitris N. Chandraker, Manmohan Schulter, Samuel Rutgers State Univ New Brunswick NJ 08901 USA NEC Labs Amer Princeton NJ USA Google Res Mountain View CA USA Univ Calif San Diego La Jolla CA USA

ISBN: (纸本)9798350353006

The recent progress in language-based open-vocabulary object detection can be largely attributed to finding better ways of leveraging large-scale data with free-form text annotations. Training such models with a discriminative objective function has proven successful, but requires good positive and negative samples. However, the free-form nature and the open vocabulary of object descriptions make the space of negatives extremely large. Prior works randomly sample negatives or use rule-based techniques to build them. In contrast, we propose to leverage the vast knowledge built into modern generative models to automatically build negatives that are more relevant to the original data. Specifically, we use large-Language-models to generate negative text descriptions, and text-to-image diffusion models to also generate corresponding negative images. Our experimental analysis confirms the relevance of the generated negative data, and its use in language-based detectors improves performance on two complex benchmarks. Code is available at https://***/xiaofeng94/Gen-Enhanced-Negs.

关键词： large language model negative example mining open-vocabulary object detection vision and language

来源：评论

学校读者我要写书评

暂无评论

TAMM: TriAdapter Multi-Modal Learning for 3D Shape Understanding

TAMM: TriAdapter Multi-Modal Learning for 3D Shape Understan...

引用

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

作者： Zhang, Zhihao Cao, Shengcao Wang, Yu-Xiong Xi An Jiao Tong Univ Xian Peoples R China Univ Illinois Champaign IL USA

ISBN: (纸本)9798350353006

The limited scale of current 3D shape datasets hinders the advancements in 3D shape understanding, and motivates multi-modal learning approaches which transfer learned knowledge from data-abundant 2D image and language modalities to 3D shapes. However, even though the image and language representations have been aligned by cross-modal models like CLIP, we find that the image modality fails to contribute as much as the language in existing multi-modal 3D representation learning methods. This is attributed to the domain shift in the 2D images and the distinct focus of each modality. To more effectively leverage both modalities in the pre-training, we introduce TriAdapter Multi-Modal Learning (TAMM) - a novel two-stage learning approach based on three synergistic adapters. First, our CLIP Image Adapter mitigates the domain gap between 3D-rendered images and natural images, by adapting the visual representations of CLIP for synthetic image-text pairs. Subsequently, our Dual Adapters decouple the 3D shape representation space into two complementary sub-spaces: one focusing on visual attributes and the other for semantic understanding, which ensure a more comprehensive and effective multi-modal pre-training. Extensive experiments demonstrate that TAMM consistently enhances 3D representations for a wide range of 3D encoder architectures, pre-training datasets, and downstream tasks. Notably, we boost the zero-shot classification accuracy on Objaverse-LVIS from 46.8% to 50.7%, and improve the 5-way 10-shot linear probing classification accuracy on ModelNet40 from 96.1% to 99.0%. Project page: https://***/tamm-page.

关键词： 3D shape classification 3D vision multi-modal learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Online Multi-Camera Tracking with Memory-Efficient Accumulated Appearance Features and Trajectory Validation

Efficient Online Multi-Camera Tracking with Memory-Efficient...

引用

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

作者： Lap Quoc Tran Huan Duc Vi Asilla Tokyo Japan

ISBN: (纸本)9798350365474

Multi-camera tracking (MCT) plays a crucial role in various computer vision applications. However, accurate tracking of individuals across multiple cameras faces challenges, particularly with identity switches. In this paper, we present an efficient online MCT system that tackles these challenges through online processing. Our system leverages memory-efficient accumulated appearance features to provide stable representations of individuals across cameras and time. By incorporating trajectory validation using hierarchical agglomerative clustering (HAC) in overlapping regions, ID transfers are identified and rectified. Evaluation on the 2024 AI City Challenge Track 1 dataset [39] demonstrates the competitive performance of our system, achieving accurate tracking in both overlapping and non-overlapping camera networks. With a 40.3% HOTA score [29], our system ranked 9th in the challenge. The integration of trajectory validation enhances performance by 8% over the baseline, and the accumulated appearance features further contribute to a 17% improvement.

关键词： computer vision

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

Collaborating Foundation Models for Domain Generalized Semantic Segmentation

Collaborating Foundation Models for Domain Generalized Seman...

引用

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

作者： Benigmim, Yasser Roy, Subhankar Essid, Slim Kalogeiton, Vicky Lathuiliere, Stephane Inst Polytech Paris Telecom Paris LTCI Palaiseau France Inst Polytech Paris CNRS Ecole Polytech LIX Palaiseau France Univ Aberdeen Aberdeen Scotland

ISBN: (纸本)9798350353013;9798350353006

Domain Generalized Semantic Segmentation (DGSS) deals with training a model on a labeled source domain with the aim of generalizing to unseen domains during inference. Existing DGSS methods typically effectuate robust features by means of Domain Randomization (DR). Such an approach is often limited as it can only account for style diversification and not content. In this work, we take an orthogonal approach to DGSS and propose to use an assembly of CoLlaborative FOUndation models for Domain Generalized Semantic Segmentation (CLOUDS). In detail, CLOUDS is a framework that integrates Foundation Models of various kinds: (i) CLIP backbone for its robust feature representation, (ii) Diffusion Model to diversify the content, thereby covering various modes of the possible target distribution, and (iii) Segment Anything Model (SAM) for iteratively refining the predictions of the segmentation model. Extensive experiments show that our CLOUDS excels in adapting from synthetic to real DGSS benchmarks and under varying weather conditions, notably outperforming prior methods by 5.6% and 6.7% on averaged mIoU, respectively. Our code is available at https://***/yasserben/CLOUDS

关键词： computer vision Deep Learning Domain Adaptation Domain Generalization Foundation Models Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Multiscale vision Transformers meet Bipartite Matching for efficient single-stage Action Localization

Multiscale Vision Transformers meet Bipartite Matching for e...

引用

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

作者： Ntinou, Ioanna Sanchez, Enrique Tzimiropoulos, Georgios Queen Mary Univ London London England Samsung AI Ctr Cambridge Cambridge England

ISBN: (纸本)9798350353006

Action Localization is a challenging problem that combines detection and recognition tasks, which are often addressed separately. State-of-the-art methods rely on off-the-shelf bounding box detections pre-computed at high resolution, and propose transformer models that focus on the classification task alone. Such two-stage solutions are prohibitive for real-time deployment. On the other hand, single-stage methods target both tasks by devoting part of the network (generally the backbone) to sharing the majority of the workload, compromising performance for speed. These methods build on adding a DETR head with learnable queries that after cross- and self-attention can be sent to corresponding MLPs for detecting a person's bounding box and action. However, DETR-like architectures are challenging to train and can incur in big complexity. In this paper, we observe that a straight bipartite matching loss can be applied to the output tokens of a vision transformer. This results in a backbone + MLP architecture that can do both tasks without the need of an extra encoder-decoder head and learnable queries. We show that a single MViTv2-S architecture trained with bipartite matching to perform both tasks surpasses the same MViTv2-S when trained with RoI align on pre-computed bounding boxes. With a careful design of token pooling and the proposed training pipeline, our Bipartite-Matching vision Transformer model, BMViT, achieves +3 mAP on AVA2.2. w.r.t. the two-stage MViTv2-S counterpart. Code is available at https://***/IoannaNti/BMViT

关键词： Signal encoding

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 << < 22 23 24 25 26 27 28 29 30 31 > >>

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：