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

90 篇 会议
58 篇 期刊文献
1 篇 学位论文

馆藏范围

149 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

137 篇 工学
- 114 篇 计算机科学与技术...
- 25 篇 电气工程
- 10 篇 软件工程
- 7 篇 生物医学工程（可授...
- 6 篇 信息与通信工程
- 6 篇 控制科学与工程
- 6 篇 测绘科学与技术
- 4 篇 仪器科学与技术
- 4 篇 电子科学与技术（可...
- 3 篇 机械工程
- 2 篇 材料科学与工程（可...
- 2 篇 交通运输工程
- 1 篇 航空宇航科学与技...
- 1 篇 环境科学与工程（可...
- 1 篇 生物工程
28 篇 医学
- 19 篇 临床医学
- 8 篇 特种医学
- 4 篇 基础医学(可授医学...
- 1 篇 中西医结合
- 1 篇 医学技术（可授医学...
18 篇 理学
- 7 篇 地球物理学
- 6 篇 物理学
- 5 篇 生物学
- 4 篇 化学
- 2 篇 地理学
- 1 篇 天文学
- 1 篇 地质学
4 篇 管理学
- 3 篇 管理科学与工程(可...
- 1 篇 图书情报与档案管...
1 篇 哲学
- 1 篇 哲学
1 篇 农学

主题

149 篇 vision-language ...
15 篇 large language m...
12 篇 prompt learning
10 篇 clip
9 篇 few-shot learnin...
6 篇 contrastive lear...
6 篇 foundation model...
6 篇 visualization
5 篇 deep learning
4 篇 object detection
4 篇 long-tailed reco...
4 篇 remote sensing
4 篇 image classifica...
4 篇 artificial intel...
4 篇 computer vision
4 篇 domain generaliz...
4 篇 prompt tuning
3 篇 multimodal learn...
3 篇 representation l...
3 篇 image captioning

机构

4 篇 carnegie mellon ...
4 篇 univ chinese aca...
3 篇 inesc tec porto
3 篇 sichuan univ col...
3 篇 univ chinese aca...
3 篇 chinese univ hon...
3 篇 chinese acad sci...
2 篇 shanghai ai lab ...
2 篇 ecole polytech f...
2 篇 tsinghua univ de...
2 篇 harbin inst tech...
2 篇 zhejiang univ pe...
2 篇 univ porto fac e...
2 篇 beijing univ pos...
2 篇 city univ hong k...
2 篇 sichuan univ col...
2 篇 tech univ munich...
2 篇 westlake univ sc...
2 篇 univ elect sci &...
2 篇 johns hopkins un...

作者

4 篇 banerjee biplab
4 篇 zhang yi
4 篇 jha ankit
3 篇 wang donglin
3 篇 singha mainak
3 篇 zhang ce
3 篇 tuia devis
2 篇 men aidong
2 篇 zhang min
2 篇 liu xuyang
2 篇 chen honggang
2 篇 guo miaotian
2 篇 yang yang
2 篇 ricci elisa
2 篇 ye mao
2 篇 tian liang
2 篇 patricio cristia...
2 篇 wang haiying
2 篇 teixeira luis f.
2 篇 mukhopadhyay sou...

语言

148 篇 英文
1 篇 其他

检索条件"主题词=Vision-Language Models"

共 149 条记录，以下是31-40 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：

Enhancing vision-language models with Scene Graphs for Traffic Accident Understanding

Enhancing Vision-Language Models with Scene Graphs for Traff...

引用

2024 International Automated Vehicle Validation Conference

作者： Lohner, Aaron Compagno, Francesco Francis, Jonathan Oltramari, Alessandro Carnegie Mellon Univ Sch Comp Sci Pittsburgh PA 15213 USA Univ Trento Dept Ind Innovat Trento Italy Bosch Ctr Artificial Intelligence Pittsburgh PA USA

ISBN: (纸本)9798350354089;9798350354072

Recognizing a traffic accident is an essential part of any autonomous driving or road monitoring system. An accident can appear in a wide variety of forms, and understanding what type of accident is taking place may be useful to prevent it from reoccurring. This work focuses on classifying traffic scenes into specific accident types. We approach the problem by representing a traffic scene as a graph, where objects such as cars can be represented as nodes, and relative distances and directions between them as edges. This representation of a traffic scene is referred to as a scene graph, and can be used as input for an accident classifier. Better results are obtained with a classifier that fuses the scene graph input with visual and textual representations. This work introduces a multi-stage, multimodal pipeline that pre-processes videos of traffic accidents, encodes them as scene graphs, and aligns this representation with vision and language modalities before executing the classification task. When trained on 4 classes, our method achieves a balanced accuracy score of 57.77% on an (unbalanced) subset of the popular Detection of Traffic Anomaly (DoTA) benchmark, representing an increase of close to 5 percentage points from the case where scene graph information is not taken into account.

关键词： Neuro-symbolism vision-language models Foundation models Autonomous Driving Perception

来源：评论

学校读者我要写书评

暂无评论

CLIPping the Deception: Adapting vision-language models for Universal Deepfake Detection 24

CLIPping the Deception: Adapting Vision-Language Models for ...

引用

4th Annual International Conference on Multimedia Retrieval (ICMR)

作者： Khan, Sohail Ahmed Duc-Tien Dang-Nguyen Univ Bergen Bergen Norway

ISBN: (纸本)9798400706028

The recent advancements in Generative Adversarial Networks (GANs) and the emergence of Diffusion models have significantly streamlined the production of highly realistic and widely accessible synthetic content. As a result, there is a pressing need for effective general purpose detection mechanisms to mitigate the potential risks posed by deepfakes. In this paper, we explore the effectiveness of pre-trained vision-language models (VLMs) when paired with recent adaptation methods for universal deepfake detection. Following previous studies in this domain, we employ only a single dataset (ProGAN) in order to adapt CLIP for deepfake detection. However, in contrast to prior research, which rely solely on the visual part of CLIP while ignoring its textual component, our analysis reveals that retaining the text part is crucial. Consequently, the simple and lightweight Prompt Tuning based adaptation strategy that we employ outperforms the previous SOTA approach by 5.01% mAP and 6.61% accuracy while utilizing less than one third of the training data (200k images as compared to 720k). To assess the real-world applicability of our proposed models, we conduct a comprehensive evaluation across various scenarios. This involves rigorous testing on images sourced from 21 distinct datasets, including those generated by GANs-based, diffusion-based and commercial tools. Code and pre-trained models: https://***/sohailahmedkhan/CLIPping-the-Deception

关键词： deepfake detection transfer learning vision-language models

来源：评论

学校读者我要写书评

暂无评论

MoPE-CLIP: Structured Pruning for Efficient vision-language models with Module-wise Pruning Error Metric

MoPE-CLIP: Structured Pruning for Efficient Vision-Language ...

引用

IEEE/CVF Conference on Computer vision and Pattern Recognition (CVPR)

作者： Lin, Haokun Bai, Haoli Liu, Zhili Hou, Lu Sung, Muyi Song, Linqi Wei, Ying Sun, Zhenan Univ Chinese Acad Sci Sch Artificial Intelligence Beijing Peoples R China Chinese Acad Sci CRIPAC Beijing Peoples R China Chinese Acad Sci MAIS Inst Automat Beijing Peoples R China Huawei Noahs Ark Lab Hong Kong Peoples R China City Univ Hong Kong Hong Kong Peoples R China City Univ Hong Kong Shenzhen Res Inst Hong Kong Peoples R China Nanyang Technol Univ Singapore Singapore

ISBN: (纸本)9798350353006

vision-language pre-trained models have achieved impressive performance on various downstream tasks. However, their large model sizes hinder their utilization on platforms with limited computational resources. We find that directly using smaller pre-trained models and applying magnitude-based pruning on CLIP models leads to inflexibility and inferior performance. Recent efforts for VLP compression either adopt uni-modal compression metrics resulting in limited performance or involve costly mask-search processes with learnable masks. In this paper, we first propose the Module-wise Pruning Error (MoPE) metric, accurately assessing CLIP module importance by performance decline on cross-modal tasks. Using the MoPE metric, we introduce a unified pruning framework applicable to both pre-training and task-specific fine-tuning compression stages. For pre-training, MoPE-CLIP effectively leverages knowledge from the teacher model, significantly reducing pre-training costs while maintaining strong zero-shot capabilities. For fine-tuning, consecutive pruning from width to depth yields highly competitive task-specific models. Extensive experiments in two stages demonstrate the effectiveness of the MoPE metric, and MoPE-CLIP outperforms previous state-of-the-art VLP compression methods.

关键词： CLIP Model Compression Structured Pruning vision-language models

来源：评论

学校读者我要写书评

暂无评论

MMA: Multi-Modal Adapter for vision-language models

MMA: Multi-Modal Adapter for Vision-Language Models

引用

IEEE/CVF Conference on Computer vision and Pattern Recognition (CVPR)

作者： Yang, Lingxiao Zhang, Ru-Yuan Wang, Yanchen Xie, Xiaohua Sun Yat Sen Univ Guangzhou Peoples R China Shanghai Jiao Tong Univ Shanghai Peoples R China Stanford Univ Stanford CA USA

ISBN: (纸本)9798350353006

Pre-trained vision-language models (VLMs) have served as excellent foundation models for transfer learning in diverse downstream tasks. However, tuning VLMs for few-shot generalization tasks faces a discrimination - generalization dilemma, i.e., general knowledge should be preserved and task-specific knowledge should be fine-tuned. How to precisely identify these two types of representations remains a challenge. In this paper, we propose a Multi-Modal Adapter (MMA) for VLMs to improve the alignment between representations from text and vision branches. MMA aggregates features from different branches into a shared feature space so that gradients can be communicated across branches. To determine how to incorporate MMA, we systematically analyze the discriminability and generalizability of features across diverse datasets in both the vision and language branches, and find that (1) higher layers contain discriminable dataset-specific knowledge, while lower layers contain more generalizable knowledge, and (2) language features are more discriminable than visual features, and there are large semantic gaps between the features of the two modalities, especially in the lower layers. Therefore, we only incorporate MMA to a few higher layers of transformers to achieve an optimal balance between discrimination and generalization. We evaluate the effectiveness of our approach on three tasks: generalization to novel classes, novel target datasets, and domain generalization. Compared to many state-of-the-art methods, our MMA achieves leading performance in all evaluations. Code is at https://***/ZjjConan/Multi-Modal-Adapter

关键词： Adapter Multi-Modal vision-language models

来源：评论

学校读者我要写书评

暂无评论

The Neglected Tails in vision-language models

The Neglected Tails in Vision-Language Models

引用

IEEE/CVF Conference on Computer vision and Pattern Recognition (CVPR)

作者： Parashar, Shubham Lin, Zhiqiu Liu, Tian Dong, Xiangjue Li, Yanan Ramanan, Deva Caverlee, James Kong, Shu Texas A&M Univ College Stn TX 77840 USA Carnegie Mellon Univ Pittsburgh PA 15213 USA Zhejiang Lab Hangzhou Peoples R China Univ Macau Taipa Macao Peoples R China

ISBN: (纸本)9798350353006

vision-language models (VLMs) excel in zero-shot recognition but their performance varies greatly across different visual concepts. For example, although CLIP achieves impressive accuracy on ImageNet (60-80%), its performance drops below 10% for more than ten concepts like night snake, presumably due to their limited presence in the pretraining data. However, measuring the frequency of concepts in VLMs' large-scale datasets is challenging. We address this by using large language models (LLMs) to count the number of pretraining texts that contain synonyms of these concepts. Our analysis confirms that popular datasets, such as LAION, exhibit a long-tailed concept distribution, yielding biased performance in VLMs. We also find that downstream applications of VLMs, including visual chatbots (e.g., GPT-4V) and text-to-image models (e.g., Stable Diffusion), often fail to recognize or generate images of rare concepts identified by our method. To mitigate the imbalanced performance of zero-shot VLMs, we propose REtrieval-Augmented Learning (REAL). First, instead of prompting VLMs using the original class names, REAL uses their most frequent synonyms found in pretraining texts. This simple change already outperforms costly human-engineered and LLM-enriched prompts over nine benchmark datasets. Second, REAL trains a linear classifier on a small yet balanced set of pretraining data re-trieved using concept synonyms. REAL surpasses the previous zero-shot SOTA, using 400x less storage and 10,000x less training time!

关键词： Long tailed recognition vision-language models Zero-Shot Recognition

来源：评论

学校读者我要写书评

暂无评论

On the use of vision-language models for Visual Sentiment Analysis: a study on CLIP 11

On the use of Vision-Language models for Visual Sentiment An...

引用

11th International Conference on Affective Computing and Intelligent Interaction (ACIIW)

作者： Bustos, Cristina Civit, Carles Du, Brian Sole-Ribalta, Albert Lapedriza, Agata Univ Oberta Catalunya Barcelona Spain Northeastern Univ Boston MA 02115 USA

ISBN: (纸本)9798350327434

This work presents a study on how to exploit the CLIP embedding space to perform Visual Sentiment Analysis. We experiment with two architectures built on top of the CLIP embedding space, which we denote by CLIP-E. We train the CLIP-E models with WEBEmo, the largest publicly available and manually labeled benchmark for Visual Sentiment Analysis, and perform two sets of experiments. First, we test on WEBEmo and compare the CLIP-E architectures with state-of-the-art (SOTA) models and with CLIP Zero-Shot. Second, we perform cross dataset evaluation, and test the CLIP-E architectures trained with WEBEmo on other Visual Sentiment Analysis benchmarks. Our results show that the CLIP-E approaches outperform SOTA models in WEBEmo fine grained categorization, and they also generalize better when tested on datasets that have not been seen during training. Interestingly, we observed that for the FI dataset, CLIP Zero-Shot produces better accuracies than SOTA models and CLIP-E trained on WEBEmo. These results motivate several questions that we discuss in this paper, such as how we should design new benchmarks and evaluate Visual Sentiment Analysis, and whether we should keep designing tailored Deep Learning models for Visual Sentiment Analysis or focus our efforts on better using the knowledge encoded in large vision-language models such as CLIP for this task. Our code is available at https://***/cristinabustos16/CLIP-E.

关键词： visual sentiment analysis vision-language models zero-shot classification

来源：评论

学校读者我要写书评

暂无评论

PromptKD: Unsupervised Prompt Distillation for vision-language models

PromptKD: Unsupervised Prompt Distillation for Vision-Langua...

引用

IEEE/CVF Conference on Computer vision and Pattern Recognition (CVPR)

作者： Li, Zheng Li, Xiang Fu, Xinyi Zhang, Xin Wang, Weiqiang Chen, Shuo Yang, Jian Nankai Univ Coll Comp Sci PCA Lab VCIP Tianjin Peoples R China NKIARI Shenzhen Futian Peoples R China Ant Grp Tiansuan Lab Hangzhou Peoples R China RIKEN Wako Saitama Japan

ISBN: (纸本)9798350353006

Prompt learning has emerged as a valuable technique in enhancing vision-language models (VLMs) such as CLIP for downstream tasks in specific domains. Existing work mainly focuses on designing various learning forms of prompts, neglecting the potential of prompts as effective distillers for learning from larger teacher models. In this paper, we introduce an unsupervised domain prompt distillation framework, which aims to transfer the knowledge of a larger teacher model to a lightweight target model through prompt-driven imitation using unlabeled domain images. Specifically, our framework consists of two distinct stages. In the initial stage, we pre-train a large CLIP teacher model using domain (few-shot) labels. After pre-training, we leverage the unique decoupled-modality characteristics of CLIP by pre-computing and storing the text features as class vectors only once through the teacher text encoder. In the subsequent stage, the stored class vectors are shared across teacher and student image encoders for calculating the predicted logits. Further, we align the logits of both the teacher and student models via KL divergence, encouraging the student image encoder to generate similar probability distributions to the teacher through the learnable prompts. The proposed prompt distillation process eliminates the reliance on labeled data, enabling the algorithm to leverage a vast amount of unlabeled images within the domain. Finally, the well-trained student image encoders and pre-stored text features (class vectors) are utilized for inference. To our best knowledge, we are the first to (1) perform unsupervised domain-specific prompt-driven knowledge distillation for CLIP, and (2) establish a practical pre-storing mechanism of text features as shared class vectors between teacher and student. Extensive experiments on 11 datasets demonstrate the effectiveness of our method. Code is publicly available at https://***/zhengli97/PromptKD.

关键词： knowledge distillation prompt learning vision-language models zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

ENvisionING MEDCLIP: A DEEP DIVE INTO EXPLAINABILITY FOR MEDICAL vision-language models 21

ENVISIONING MEDCLIP: A DEEP DIVE INTO EXPLAINABILITY FOR MED...

引用

21st IEEE International Symposium on Biomedical Imaging (ISBI)

作者： Hashmi, Anees Ur Rehman Mahapatra, Dwarikanath Yaqub, Mohammad Mohamed bin Zayed Univ Artificial Intelligence Abu Dhabi U Arab Emirates Incept Inst Artificial Intelligence Abu Dhabi U Arab Emirates

ISBN: (纸本)9798350313345;9798350313338

Explaining Deep Learning models is becoming increasingly important in the face of daily emerging multimodal models, particularly in safety-critical domains like medical imaging. However, the lack of detailed investigations into the performance of explainability methods on these models is widening the gap between their development and safe deployment. In this work, we analyze the performance of various explainable AI methods on a vision-language model, MedCLIP, to demystify its inner workings. We also provide a simple methodology to overcome the shortcomings of these methods. Our work offers a different new perspective on the explainability of a recent well-known VLM in the medical domain and our assessment method is generalizable to other current and possible future VLMs.

关键词： Explainable AI vision-language models Multimodal models

来源：评论

学校读者我要写书评

暂无评论

Fine-Grained Visual Prompt Learning of vision-language models for Image Recognition 23

Fine-Grained Visual Prompt Learning of Vision-Language Model...

引用

31st ACM International Conference on Multimedia (MM)

作者： Sun, Hongbo He, Xiangteng Zhou, Jiahuan Peng, Yuxin Peking Univ Wangxuan Inst Comp Technol Beijing Peoples R China Peking Univ Natl Key Lab Multimedia Informat Proc Beijing Peoples R China

ISBN: (纸本)9798400701085

Large-scale pre-trained vision-language (VL) models have shown powerful generic representation capabilities for adapting to down-stream tasks with limited training data, which are data-efficient solutions to various applications such as image recognition. In order to enhance the adaption performance, most existing methods attempt to introduce learnable vectors into the text prompt to generate adaptive classification weights for the class in the downstream task. However, they generally focus on the text side while neglecting adaptive visual feature generation on the image side, which is insufficient to fit the downstream task data. In this paper, we propose fine-grained visual prompt learning (FG-VPL) of vision-language models for image recognition with few training samples, and the main contributions are: (1) Fine-grained visual prompt is introduced into the image encoder of the vision-language model for focusing on the target object and conducting information interaction within the object, which facilitates generating discriminative visual features for image recognition. (2) A two-pathway adaptive recognition module is proposed to narrow the domain gap and utilize both the cross-modal knowledge of the vision-language model and the visual information of the few-sample training set for classifying images with the help of feature adapters. We conduct extensive experiments on 11 image recognition benchmark datasets under the few training samples setting, which demonstrate that our proposed approach can achieve state-of-the-art performance. The code is available at https://***/PKU-ICST-MIPL/FG-VPL_ACMMM2023.

关键词： Fine-Grained visual prompt learning vision-language models Image recognition with few training samples

来源：评论

学校读者我要写书评

暂无评论

Food-500 Cap: A Fine-Grained Food Caption Benchmark for Evaluating vision-language models 23

Food-500 Cap: A Fine-Grained Food Caption Benchmark for Eval...

引用

31st ACM International Conference on Multimedia (MM)

作者： Ma, Zheng Pan, Mianzhi Wu, Wenhan Cheng, Kanzhi Zhang, Jianbing Huang, Shujian Chen, Jiajun Nanjing Univ Natl Key Lab Novel Software Technol Nanjing Peoples R China

ISBN: (纸本)9798400701085

vision-language models (VLMs) have shown impressive performance in substantial downstream multi-modal tasks. However, only comparing the fine-tuned performance on downstream tasks leads to the poor interpretability of VLMs, which is adverse to their future improvement. Several prior works have identified this issue and used various probing methods under a zero-shot setting to detect VLMs' limitations, but they all examine VLMs using general datasets instead of specialized ones. In practical applications, VLMs are usually applied to specific scenarios, such as e-commerce and news fields, so the generalization of VLMs in specific domains should be given more attention. In this paper, we comprehensively investigate the capabilities of popular VLMs in a specific field, the food domain. To this end, we build a food caption dataset, Food-500 Cap, which contains 24,700 food images with 494 categories. Each image is accompanied by a detailed caption, including fine-grained attributes of food, such as the ingredient, shape, and color. We also provide a culinary culture taxonomy that classifies each food category based on its geographic origin in order to better analyze the performance differences of VLM in different regions. Experiments on our proposed datasets demonstrate that popular VLMs underperform in the food domain compared with their performance in the general domain. Furthermore, our research reveals severe bias in VLMs' ability to handle food items from different geographic regions. We adopt diverse probing methods and evaluate nine VLMs belonging to different architectures to verify the aforementioned observations. We hope that our study will bring researchers' attention to VLM's limitations when applying them to the domain of food or culinary cultures, and spur further investigations to address this issue.

关键词： vision-language models Food Benchmark Evaluation

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15页 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：