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

83 篇 会议
62 篇 期刊文献

馆藏范围

145 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

137 篇 工学
- 123 篇 计算机科学与技术...
- 34 篇 电气工程
- 21 篇 软件工程
- 12 篇 信息与通信工程
- 5 篇 控制科学与工程
- 4 篇 电子科学与技术（可...
- 3 篇 机械工程
- 3 篇 建筑学
- 3 篇 土木工程
- 2 篇 仪器科学与技术
- 2 篇 材料科学与工程（可...
- 1 篇 动力工程及工程热...
- 1 篇 石油与天然气工程
- 1 篇 交通运输工程
- 1 篇 农业工程
- 1 篇 生物医学工程（可授...
- 1 篇 城乡规划学
13 篇 医学
- 12 篇 临床医学
12 篇 理学
- 7 篇 物理学
- 3 篇 化学
- 2 篇 数学
- 2 篇 科学技术史(分学科...
6 篇 管理学
- 6 篇 管理科学与工程(可...
3 篇 法学
- 3 篇 社会学
2 篇 哲学
- 1 篇 哲学
2 篇 历史学
- 2 篇 考古学
2 篇 艺术学
1 篇 经济学
- 1 篇 应用经济学
1 篇 教育学
- 1 篇 心理学(可授教育学...
1 篇 文学
- 1 篇 外国语言文学
1 篇 农学
- 1 篇 作物学

主题

145 篇 text-to-image ge...
23 篇 diffusion model
17 篇 diffusion models
11 篇 generative adver...
9 篇 generative ai
8 篇 prompt engineeri...
8 篇 generative adver...
7 篇 large language m...
7 篇 image synthesis
6 篇 deep learning
6 篇 task analysis
6 篇 generative model...
5 篇 generative model
5 篇 stable diffusion
5 篇 real image editi...
5 篇 feature extracti...
5 篇 aigc
5 篇 training
4 篇 natural language...
4 篇 image generation

机构

5 篇 univ sci & techn...
4 篇 zhejiang univ pe...
4 篇 alibaba grp peop...
4 篇 shandong normal ...
2 篇 univ michigan an...
2 篇 univ chinese aca...
2 篇 sidi mohamed ben...
2 篇 hong kong univ s...
2 篇 osaka univ osaka
2 篇 chinese acad sci...
2 篇 harbin inst tech...
2 篇 university of ch...
2 篇 sidi mohamed ben...
2 篇 univ jyvaskyla f...
2 篇 zhejiang univ co...
2 篇 tianjin univ peo...
2 篇 sun yat sen univ...
2 篇 southern univ sc...
2 篇 chinese academy ...
2 篇 univ calif san d...

作者

5 篇 huang jiancheng
4 篇 bahani mourad
4 篇 wu yankun
4 篇 liu li
4 篇 garcia noa
4 篇 el ouaazizi aziz...
4 篇 oppenlaender jon...
4 篇 maalmi khalil
4 篇 zhang huaxiang
4 篇 nakashima yuta
3 篇 liu yifan
3 篇 liu dongmei
3 篇 mao zhendong
3 篇 chen shifeng
2 篇 gong biao
2 篇 yang yi
2 篇 silvennoinen joh...
2 篇 visuri aku
2 篇 chen songyan
2 篇 ma yue

语言

143 篇 英文
2 篇 其他
1 篇 法文

检索条件"主题词=Text-to-Image Generation"

共 145 条记录，以下是21-30 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：

LayoutLLM-T2I: Eliciting Layout Guidance from LLM for text-to-image generation 23

LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-t...

引用

31st ACM International Conference on Multimedia (MM)

作者： Qu, Leigang Wu, Shengqiong Fei, Hao Nie, Liqiang Chua, Tat-Seng Natl Univ Singapore NExT Res Ctr Singapore Singapore Harbin Inst Technol Shenzhen Shenzhen Peoples R China

ISBN: (纸本)9798400701085

In the text-to-image generation field, recent remarkable progress in Stable Diffusion makes it possible to generate rich kinds of novel photorealistic images. However, current models still face misalignment issues (e.g., problematic spatial relation understanding and numeration failure) in complex natural scenes, which impedes the high-faithfulness text-to-image generation. Although recent efforts have been made to improve controllability by giving fine-grained guidance (e.g., sketch and scribbles), this issue has not been fundamentally tackled since users have to provide such guidance information manually. In this work, we strive to synthesize high-fidelity images that are semantically aligned with a given textual prompt without any guidance. Toward this end, we propose a coarse-to-fine paradigm to achieve layout planning and image generation. Concretely, we first generate the coarse-grained layout conditioned on a given textual prompt via in-context learning based on Large Language Models. Afterward, we propose a fine-grained object-interaction diffusion method to synthesize high-faithfulness images conditioned on the prompt and the automatically generated layout. Extensive experiments demonstrate that our proposed method outperforms the state-of-the-art models in terms of layout and image generation. Our code and settings are available at https://***/.

关键词： text-to-image generation Diffusion Model Large Language Model

来源：评论

学校读者我要写书评

暂无评论

MAGAN: Multi-attention Generative Adversarial Networks for text-to-image generation 4th

MAGAN: Multi-attention Generative Adversarial Networks for T...

引用

4th Chinese Conference on Pattern Recognition and Computer Vision (PRCV)

作者： Jia, Xibin Mi, Qing Dai, Qi Beijing Univ Technol Beijing 100124 Peoples R China

ISBN: (纸本)9783030880132;9783030880125

Although generative adversarial networks are commonly used in textto-image generation tasks and have made great progress, there are still some problems. The convolution operation used in these GANs-based methods works on local regions, but not disjoint regions of the image, leading to structural anomalies in the generated image. Moreover, the semantic consistency of generated images and corresponding text descriptions still needs to be improved. In this paper, we propose a multi-attention generative adversarial networks (MAGAN) for text-toimage generation. We use self-attention mechanism to improve the overall quality of images, so that the target image with a certain structure can also be generated well. We use multi-head attentionmechanism to improve the semantic consistency of generated images and text descriptions. We conducted extensive experiments on three datasets: Oxford-102 Flowers dataset, Caltech-UCSD Birds dataset and COCO dataset. Our MAGAN has better results than representative methods such as AttnGAN, MirrorGAN and ControlGAN.

关键词： text-to-image generation Generative adversarial networks Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Background Layout generation and Object Knowledge Transfer for text-to-image generation 22

Background Layout Generation and Object Knowledge Transfer f...

引用

30th ACM International Conference on Multimedia (MM)

作者： Chen, Zhuowei Mao, Zhendong Fang, Shancheng Hu, Bo Univ Sci & Technol China Hefei Peoples R China

ISBN: (纸本)9781450392037

text-to-image generation (T2I) aims to generate realistic and semantically consistent images according to the natural language descriptions. Built upon the recent advances in generative adversarial networks (GANs), existing T2I models have made great process. However, a close inspection of their generated images shows two major limitations: 1) the background (e.g., fence, lake) of the generated image with the complicated, real-world scene tends to be unrealistic;2) the object (e.g., elephant, zebra) in the generated image often presents highly distorted shape or key parts missing. To address these limitations, we propose a two-stage T2I approach, where the first stage redesigns the text-to-layout process to incorporate the background layout with the existing object layout, the second stage transfers the object knowledge from an existing class-to-image model to the layout-to-image process to improve the object fidelity. Specifically, a transformer-based architecture is introduced as the layout generator to learn the mapping from text to layout of object and background, and a text-attended Layout-aware feature Normalization (TL-Norm) is proposed to adaptively transfer the object knowledge to the image generation. Benefitting from the background layout and transferred object knowledge, the proposed approach significantly surpasses previous state-of-the-art methods in the image quality metric and achieves superior image-text alignment performance.

关键词： text-to-image generation Layout generation

来源：评论

学校读者我要写书评

暂无评论

Learning Prompt-Level Quality Variance for Cost-Effective text-to-image generation 24

Learning Prompt-Level Quality Variance for Cost-Effective Te...

引用

33rd ACM International Conference on Information and Knowledge Management (CIKM)

作者： Lee, Dongkeun Lee, Wonjun Korea Univ Seoul South Korea

ISBN: (纸本)9798400704369

text-to-image generation is a multivariable process in which the resulting quality is determined by both the generative model and the input prompt. While previous efforts rely on a single model either by enhancing its capability or by reformulating prompts, we point out that no single model excels at handling all types of tasks, as there exist inter-model and intra-model quality variance induced by the difference in types of prompts. This paper explores the relationship between the generation quality of text-to-image models and the linguistic features of input prompts by measuring the performance of state-of-the-art models using five different prompt datasets each with its distinctive features. Motivated by our empirical observations, we propose a novel approach that assigns each prompt to its best-performing model based on quality prediction. This enables utilizing a diverse set of models each with its expertise and cost, thereby enhancing cost-effectiveness. Evaluation results show that our approach can reduce the total generation cost by 29.25% with comparable or even higher generation quality than using only the single best model.

关键词： generative models text-to-image generation cost-effectiveness

来源：评论

学校读者我要写书评

暂无评论

Learning Disentangled Identifiers for Action-Customized text-to-image generation

Learning Disentangled Identifiers for Action-Customized Text...

引用

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

作者： Huang, Siteng Gong, Biao Feng, Yutong Chen, Xi Fu, Yuqian Liu, Yu Wang, Donglin Zhejiang Univ Hangzhou Peoples R China Alibaba Grp Hangzhou Peoples R China Swiss Fed Inst Technol Zurich Switzerland Westlake Univ Sch Engn AI Div Machine Intelligence Lab MiLAB Hangzhou Peoples R China

ISBN: (纸本)9798350353013;9798350353006

This study focuses on a novel task in text-to-image (T2I) generation, namely action customization. The objective of this task is to learn the co-existing action from limited data and generalize it to unseen humans or even animals. Experimental results show that existing subject-driven customization methods fail to learn the representative characteristics of actions and struggle in decoupling actions from context features, including appearance. To overcome the preference for low-level features and the entanglement of high-level features, we propose an inversion-based method Action-Disentangled Identifier (ADI) to learn action-specific identifiers from the exemplar images. ADI first expands the semantic conditioning space by introducing layer-wise identifier tokens, thereby increasing the representational richness while distributing the inversion across different features. Then, to block the inversion of action-agnostic features, ADI extracts the gradient invariance from the constructed sample triples and masks the updates of irrelevant channels. To comprehensively evaluate the task, we present an Action-Bench that includes a variety of actions, each accompanied by meticulously selected samples. Both quantitative and qualitative results show that our ADI outperforms existing baselines in action-customized T2I generation. Our project page is at https://***/ADI.

关键词： action customization Action-Disentangled Identifier text-to-image generation

来源：评论

学校读者我要写书评

暂无评论

Check, Locate, Rectify: A Training-Free Layout Calibration System for text-to-image generation

Check, Locate, Rectify: A Training-Free Layout Calibration S...

引用

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

作者： Gong, Biao Huang, Siteng Feng, Yutong Zhang, Shiwei Li, Yuyuan Liu, Yu Alibaba Grp Hangzhou Peoples R China Zhejiang Univ Hangzhou Peoples R China

ISBN: (纸本)9798350353013;9798350353006

Diffusion models have recently achieved remarkable progress in generating realistic images. However, challenges remain in accurately understanding and synthesizing the layout requirements in the textual prompts. To align the generated image with layout instructions, we present a training-free layout calibration system SimM that intervenes in the generative process on the fly during inference time. Specifically, following a "check-locate-rectify" pipeline, the system first analyses the prompt to generate the target layout and compares it with the intermediate outputs to automatically detect errors. Then, by moving the located activations and making intra- and inter-map adjustments, the rectification process can be performed with negligible computational overhead. To evaluate SimM over a range of layout requirements, we present a benchmark SimMBench that compensates for the lack of superlative spatial relations in existing datasets. And both quantitative and qualitative results demonstrate the effectiveness of the proposed SimM in calibrating the layout inconsistencies. Our project page is at https://***/SimM.

关键词： layout calibration text-to-image generation training-free

来源：评论

学校读者我要写书评

暂无评论

Rich Human Feedback for text-to-image generation

Rich Human Feedback for Text-to-Image Generation

引用

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

作者： Liang, Youwei He, Junfeng Li, Gang Li, Peizhao Klimovskiy, Arseniy Carolan, Nicholas Sun, Jiao Pont-Tuset, Jordi Young, Sarah Yang, Feng Ke, Junjie Dvijotham, Krishnamurthy Di Collins, Katherine M. Luo, Yiwen Li, Yang Kohlhoff, Kai J. Ramachandran, Deepak Navalpakkam, Vidhya Univ Calif San Diego San Diego CA USA Google Res Mountain View CA 94043 USA Univ Southern Calif Los Angeles CA USA Univ Cambridge Cambridge England Brandeis Univ Waltham MA USA Google Mountain View CA USA Google Gemini Team Mountain View CA USA

ISBN: (纸本)9798350353006

Recent text-to-image (T2I) generation models such as Stable Diffusion and imagen have made significant progress in generating high-resolution images based on text descriptions. However, many generated images still suffer from issues such as artifacts/implausibility, misalignment with text descriptions, and low aesthetic quality. Inspired by the success of Reinforcement Learning with Human Feedback (RLHF) for large language models, prior works collected human-provided scores as feedback on generated images and trained a reward model to improve the T2I generation. In this paper, we enrich the feedback signal by (i) marking image regions that are implausible or misaligned with the text, and (ii) annotating which words in the text prompt are misrepresented or missing on the image. We collect such rich human feedback on 18K generated images (RichHF-18K) and train a multimodal transformer to predict the rich feedback automatically. We show that the predicted rich human feedback can be leveraged to improve image generation, for example, by selecting high-quality training data to finetune and improve the generative models, or by creating masks with predicted heatmaps to inpaint the problematic regions. Notably, the improvements generalize to models (Muse) beyond those used to generate the images on which human feedback data were collected (Stable Diffusion variants). The RichHF-18K data set will be released in our GitHub repository: https://***/google-research/google-research/tree/master/richhf_18k.

关键词： dataset rich human feedback text-to-image generation

来源：评论

学校读者我要写书评

暂无评论

A 28.6 mJ/iter Stable Diffusion Processor for text-to-image generation with Patch Similarity-based Sparsity Augmentation and text-based Mixed-Precision

A 28.6 mJ/iter Stable Diffusion Processor for Text-to-Image ...

引用

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： Choi, Jiwon Jo, Wooyoung Hong, Seongyon Kwon, Beomseok Park, Wonhoon Yoo, Hoi-Jun Korea Adv Inst Sci & Technol KAIST Sch Elect Engn Daejeon South Korea

ISBN: (纸本)9798350330991;9798350331004

This paper presents an energy-efficient stable diffusion processor for text-to-image generation. While stable diffusion attained attention for high-quality image synthesis results, its inherent characteristics hinder its deployment on mobile platforms. The proposed processor achieves high throughput and energy efficiency with three key features as solutions: 1) Patch similarity-based sparsity augmentation (PSSA) to reduce external memory access (EMA) energy of self-attention score by 60.3 %, leading to 37.8 % total EMA energy reduction. 2) text-based important pixel spotting (TIPS) to allow 44.8 % of the FFN layer workload to be processed with low-precision activation. 3) Dual-mode bit-slice core (DBSC) architecture to enhance energy efficiency in FFN layers by 43.0 %. The proposed processor is implemented in 28 nm CMOS technology and achieves 3.84 TOPS peak throughput with 225.6 mW average power consumption. In sum, 28.6 mJ/iteration highly energy-efficient text-to-image generation processor can be achieved at MS-COCO dataset.

关键词： Generative AI stable diffusion text-to-image generation sparsity mixed-precision energy-efficient

来源：评论

学校读者我要写书评

暂无评论

PromptPaint: Steering text-to-image generation Through Paint Medium-like Interactions 23

PromptPaint: Steering Text-to-Image Generation Through Paint...

引用

36th Annual ACM Symposium on User Interface Software and Technology (UIST)

作者： Chung, John Joon Young Adar, Eytan SpaceCraft Inc Los Angeles CA 90046 USA Univ Michigan Ann Arbor MI 48109 USA

ISBN: (纸本)9798400701320

While difusion-based text-to-image (T2I) models provide a simple and powerful way to generate images, guiding this generation remains a challenge. For concepts that are difcult to describe through language, users may struggle to create prompts. Moreover, many of these models are built as end-to-end systems, lacking support for iterative shaping of the image. In response, we introduce PromptPaint, which combines T2I generation with interactions that model how we use colored paints. PromptPaint allows users to go beyond language to mix prompts that express challenging concepts. Just as we iteratively tune colors through layered placements of paint on a physical canvas, PromptPaint similarly allows users to apply diferent prompts to diferent canvas areas and times of the generative process. Through a set of studies, we characterize diferent approaches for mixing prompts, design trade-ofs, and socio-technical challenges for generative models. With PromptPaint we provide insight into future steerable generative tools.

关键词： generative model text-to-image generation painting interactions

来源：评论

学校读者我要写书评

暂无评论

Adma-GAN: Attribute-Driven Memory Augmented GANs for text-to-image generation. 22

Adma-GAN: Attribute-Driven Memory Augmented GANs for Text-to...

引用

30th ACM International Conference on Multimedia (MM)

作者： Wu, Xintian Zhao, Hanbin Zheng, Liangli Ding, Shouhong Li, Xi Zhejiang Univ Hangzhou Peoples R China Tencent Youtu Lab Shanghai Peoples R China Shanghai AI Lab Shanghai Peoples R China

ISBN: (纸本)9781450392037

As a challenging task, text-to-image generation aims to generate photo-realistic and semantically consistent images according to the given text descriptions. Existing methods mainly extract the text information from only one sentence to represent an image and the text representation effects the quality of the generated image well. However, directly utilizing the limited information in one sentence misses some key attribute descriptions, which are the crucial factors to describe an image accurately. To alleviate the above problem, we propose an effective text representation method with the complements of attribute information. Firstly, we construct an attribute memory to jointly control the text-to-image generation with sentence input. Secondly, we explore two update mechanisms, sample-aware and sample-joint mechanisms, to dynamically optimize a generalized attribute memory. Furthermore, we design an attribute-sentence-joint conditional generator learning scheme to align the feature embeddings among multiple representations, which promotes the cross-modal network training. Experimental results illustrate that the proposed method obtains substantial performance improvements on both the CUB (FID from 14.81 to 8.57) and COCO (FID from 21.42 to 12.39) datasets.

关键词： text-to-image generation attribute memory sample-aware sample-joint cross-modal alignment

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：