检索结果-内蒙古大学图书馆

6th Chinese Conference on Pattern Recognition and Computer Vision (PRCV)

作者： Jia, Junhua Xin, Xiaowei Gao, Xiaoyan Ding, Xiangqian Pang, Shunpeng Ocean Univ China Fac Informat Sci & Engn Shandong 266000 Peoples R China Weifang Univ Sch Comp Engn Shandong 261061 Peoples R China

ISBN: (纸本)9789819984343;9789819984350

The current image captioning (IC) methods achieve good results within a single domain primarily due to training on a large amount of annotated data. However, the performance of single-domain image captioning methods suffers when extended to new domains. To address this, we propose a cross-domain image captioning framework, called SGCDIC, which achieves cross-domain generalization of image captioning models by simultaneously optimizing two coupled tasks, i.e., image captioning and text-to-image synthesis (TIS). Specifically, we propose a scene-graph-based approach SGAT for image captioning tasks. The image synthesis task employs a GAN variant (DFGAN) to synthesize plausible images based on the generated text descriptions by SGAT. We compare the generated images with the real images to enhance the image captioning performance in new domains. We conduct extensive experiments to evaluate the performance of SGCDIC by using the MSCOCO as the source domain data, and using Flickr30k and Oxford-102 as the new domain data. Sufficient comparative experiments and ablation studies demonstrate that SGCDIC achieves substantially better performance than the strong competitors for the cross-domain image captioning task.

关键词： image Captioning Scene Graph text-to-image synthesis Dual Learning

来源：评论

学校读者我要写书评

暂无评论

Seeing is No Longer Believing: A Survey on the State of Deepfakes, AI-Generated Humans, and Other Nonveridical Media 40th

Seeing is No Longer Believing: A Survey on the State of Deep...

引用

40th Computer Graphics International Conference (CGI)

作者： Pocol, Andreea Istead, Lesley Siu, Sherman Mokhtari, Sabrina Kodeiri, Sara Univ Waterloo Waterloo ON Canada Carleton Univ Ottawa ON Canada

ISBN: (纸本)9783031500718;9783031500725

Did you see that crazy photo of Chris Hemsworth wearing a gorgeous, blue ballgown? What about the leaked photo of Bernie Sanders dancing with Sarah Palin? If these don't sound familiar, it's because these events never happened-but with text-to-image generators and deepfake AI technologies, it is effortless for anyone to produce such images. Over the last decade, there has been an explosive rise in research papers, as well as tool development and usage, dedicated to deepfakes, text-to-image generation, and image synthesis. These tools provide users with great creative power, but with that power comes "great responsibility;" it is just as easy to produce nefarious and misleading content as it is to produce comedic or artistic content. Therefore, given the recent advances in the field, it is important to assess the impact they may have. In this paper, we conduct meta-research on deepfakes to visualize the evolution of these tools and paper publications. We also identify key authors, research institutions, and papers based on bibliometric data. Finally, we conduct a survey that tests the ability of participants to distinguish photos of real people from fake, AI-generated images of people. Based on our meta-research, survey, and background study, we conclude that humans are falling behind in the race to keep up with AI, and we must be conscious of the societal impact.

关键词： deepfakes AI image synthesis text-to-image synthesis

来源：评论

学校读者我要写书评

暂无评论

text-to-image Generation with Multiscale Semantic Context-Aware Generative Adversarial Networks 20th

Text-to-Image Generation with Multiscale Semantic Context-Aw...

引用

20th International Conference on Intelligent Computing (ICIC)

作者： Dong, Pei Wu, Lei Meng, Lei Meng, Xiangxu Shandong Univ 1500 Shunhua Rd Jinan Shandong Peoples R China

ISBN: (纸本)9789819756148;9789819756155

Synthesizing complex images from textual descriptions presents a significant challenge. Relying on tremendous training data and model size, recent Diffusion, Autoregressive and GAN models have made significant progress in synthesizing photo-realistic images. However, the high computing budget and hardware requirements due to the large data and model size hinder the flexibility of employing these models. This paper introduces Multiscale Semantic Context-Aware Generative Adversarial Networks (MSCA-GAN), which achieves strong text alignment with limited data while balancing generation quality and efficiency. The proposed MSCA-GAN incorporates innovative modules for textual semantic injection, delivery, and validation. Specifically, the Semantic Adaptive Affine Fusion (SAAF) module dynamically adjusts expression weights of textual semantic information to align with the feature generation process, encompassing global to detailed aspects. Furthermore, the CrossBlock Context Aware Encoding (CCAE) module explicitly establishes semantic context across different synthesis blocks during the local feature delivery. Finally, MSCA-GAN introduces an additional CLIP guidance term to verify the semantic consistency of local features at various scales. MSCA-GAN is pre-trained on the CC3M and CC12M datasets, which only contain limited data. Extensive experiments confirm that the MSCA-GAN performs competitively in terms of image quality and generation efficiency, both quantitatively and qualitatively.

关键词： text-to-image synthesis Generative Adversarial Networks text-image Semantic Consistency Limited Data

来源：评论

学校读者我要写书评

暂无评论

Pipeline for text-to-image Panoramic Road Scene Generation and Evaluation 16

Pipeline for Text-to-Image Panoramic Road Scene Generation a...

引用

16th International Conference on Automotive User Interfaces and Interactive Vehicular Applications (AutomotiveUI)

作者： Sim, Ryan Y. H. Chen, Kan Ng, Pai Chet Lee, Jeannie S. A. Singapore Inst Technol Singapore Singapore Singapore Inst Technol Ctr Immersificat Singapore Singapore

ISBN: (纸本)9798400705205

The Panoramic Road Scene Generation (PRSG) pipeline is a framework designed to generate realistic and contextually accurate panoramic road scenes from textual descriptions. This approach leverages a combination of a stable diffusion model and super-resolution techniques to produce panoramic images for autonomous vehicle (AV) simulations and VR/AR applications. By generating detailed panoramic road scenes viewable in a VR HMD, an additional avenue for easily creating and simulating vehicular scenarios is possible. The pipeline utilizes a customized dataset with specifically tailored captions to fine-tune the generation process, ensuring both visual fidelity and contextual relevance. The evaluation framework includes both subjective and objective metrics to assess to the quality and applicability of the generated images. A pilot study determined the generated road scenes to be relatively realistic and acceptable for viewing. Potential applications include the creation of new synthetic scenes for simulating AV scenarios, or training and validation of autonomous systems.

关键词： text-to-image synthesis Generative Panoramic Autonomous Vehicle Road Scene

来源：评论

学校读者我要写书评

暂无评论

DualG-GAN, a Dual-channel Generator based Generative Adversarial Network for text-to-face synthesis

引用

NEURAL NETWORKS 2022年 155卷 155-167页

作者： Luo, Xiaodong He, Xiaohai Chen, Xiang Qing, Linbo Zhang, Jin Sichuan Univ Coll Elect & Informat Engn Chengdu 610065 Sichuan Peoples R China Univ Leeds Fac Engn & Phys Sci Sch Comp Leeds England Sichuan Post & Telecommun Coll Chengdu 610065 Sichuan Peoples R China

text-to-image synthesis is a fundamental and challenging task in computer vision, which aims to synthesize realistic images from given descriptions. Recently, text-to-image synthesis methods have achieved great improvements in the quality of synthesized images. However, very few works have explored its application in the scenario of face synthesis, which is of great potentials in face-related applications and the public safety domain. On the other side, the faces generated by existing methods are generally of poor quality and have low consistency to the given text. To tackle this issue, in this paper, we build a novel end-to-end dual-channel generator based generative adversarial network, named DualG-GAN, to improve the quality of the generated images and the consistency to the text description. In DualG-GAN, to improve the consistency between the synthesized image and the input description, a dual-channel generator block is introduced, and a novel loss is designed to improve the similarity between the generated image and the ground-truth in three different semantic levels. Extensive experiments demonstrate that DualG-GAN achieves state-of-the-art results on SCU-text2face dataset. To further verify the performance of DualG-GAN, we compare it with the current optimal methods on text-to-image synthesis tasks, where quantitative and qualitative results show that the proposed DualG-GAN achieves optimal performance in both Frechet inception distance (FID) and R -precision metrics. As only a few works are focusing on text-to-face synthesis, this work can be seen as a baseline for future research. (c) 2022 Elsevier Ltd. All rights reserved.

关键词： Conditional GAN Face synthesis text -to -face synthesis text-to-image synthesis DualG-GAN

来源：评论

学校读者我要写书评

暂无评论

image Hallucination From Attribute Pairs

引用

IEEE TRANSACTIONS ON CYBERNETICS 2022年第1期52卷 568-581页

作者： Wu, Fuxiang Cheng, Jun Wang, Xinchao Wang, Lei Tao, Dapeng Chinese Acad Sci Shenzhen Inst Adv Technol CAS Key Lab Human Machine Intelligence Synergy Sy Shenzhen 518055 Peoples R China Chinese Univ Hong Kong Dept Mech & Automat Engn Hong Kong Peoples R China Stevens Inst Technol Dept Comp Sci Hoboken NJ 07030 USA Yunnan Univ Sch Informat Sci & Engn Kunming 650106 Yunnan Peoples R China

Recent image-generation methods have demonstrated that realistic images can be produced from captions. Despite the promising results achieved, existing caption-based generation methods confront a dilemma. On the one hand, the image generator should be provided with sufficient details for realistic hallucination, meaning that longer sentences with rich content are preferred, but on the other hand, the generator is meanwhile fragile to long sentences due to their complex semantics and syntax like long-range dependencies and the combinatorial explosion of object visual features. Toward alleviating this dilemma, a novel approach is proposed in this article to hallucinate images from attribute pairs, which can be extracted from natural language processing (NLP) toolsets in the presence of complex semantics and syntax. Attribute pairs, therefore, enable our image generator to tackle long sentences handily and alleviate the combinatorial explosion, and at the same time, allow us to enlarge the training dataset and to produce hallucinations from randomly combined attribute pairs at ease. Experiments on widely used datasets demonstrate that the proposed approach yields results superior to the state of the art.

关键词： Gallium nitride Semantics Visualization Generators Syntactics Training Natural language processing Attentional generative adversarial network (GAN) attribute pair text-to-image synthesis

来源：评论

学校读者我要写书评

暂无评论

Aberrant AI creations: co-creating surrealist body horror using the DALL-E Mini text-to-image generator

引用

CONVERGENCE-THE INTERNATIONAL JOURNAL OF RESEARCH INTO NEW MEDIA TECHNOLOGIES 2023年第4期29卷 1070-1096页

作者： O'Meara, Jennifer Murphy, Cait Trinity Coll Dublin Dept Film Dublin Ireland

The emergence in 2022 of surreal and grotesque image sets created using the free online AI text-to-image generator DALL-E Mini (Craiyon) prompts our analysis of their aesthetic content and connections to preexisting media forms and trends in digital culture. DALL-E Mini uses an unfiltered database of images from the internet to create new images based on a user's text prompt, often resulting in misshapen bodies and impossible scenarios. Despite its technological limitations, DALL-E Mini's popularity as a meme-making tool is visible on social media platforms, where crowd-sourced images are shared and experimentation with the tool is encouraged. Through comparison with existing artistic practices and formats (creative automata, surrealism, body horror, celebrity memes), we argue that DALL-E Mini creations can be understood as human-AI co-creations and forms of aesthetic mimicry. Building on the ideas of surrealists such as Andr ' e Breton, we propose that DALL-E Mini's images, prompts and the grid interface adhere to surrealism's historical interests in the unconscious, the uncanny, and the collaborative 'exquisite corpse' parlour game. We also consider DALL-E Mini's relevance to the category of 'AI Arts', PatriciaDe Vries's call for more research that relates algorithms to the broader artistic and cultural contexts in which they are embedded (2020), and the 'authoring' of celebrity bodies as data (Kanai, 2016). Our theorisation of DALL-E Mini is supported by examples drawn from social media and personal experiments with the generator. Overall, we propose that internet users' experimentation with DALL-E Mini corresponds with a cultural moment in which AI imaging technologies are eliciting excitement and anxiety. The outputs are revealed to be reliant on users' pop cultural knowledge, with DALL-E Mini allowing for a playful, co-creative algorithmic practice, wherein contemporary anxieties about digital labour, (post)digital culture, biopolitics, and global issues are r

关键词： DALL-E Mini algorithmic culture text-to-image synthesis screen media visual culture media archaeology storyboards storytelling pop culture digital culture social media surrealism body horror memes algorithmic anxiety

来源：评论

学校读者我要写书评

暂无评论

text-to-image Diffusion Models can be Easily Backdoored through Multimodal Data Poisoning 23

Text-to-Image Diffusion Models can be Easily Backdoored thro...

引用

31st ACM International Conference on Multimedia (MM)

作者： Zhai, Shengfang Dong, Yinpeng Shen, Qingni Pu, Shi Fang, Yuejian Su, Hang Peking Univ Sch Software & Microelect Beijing Peoples R China Tsinghua Univ Dept Comp Sci & Technol Beijing Peoples R China ShengShu Beijing Peoples R China Peking Univ Sch Software & Microelect Natl Engn Res Ctr Software Engn PKU OCTA Lab Blockchain & Privacy Comp Beijing 100871 Peoples R China Tsinghua Univ Inst AI THBI Lab Tsinghua Bosch Joint ML CtrDept Comp Sci & Tech Beijing 100084 Peoples R China

ISBN: (纸本)9798400701085

With the help of conditioning mechanisms, the state-of-the-art diffusion models have achieved tremendous success in guided image generation, particularly in text-to-image synthesis. To gain a better understanding of the training process and potential risks of text-to-image synthesis, we perform a systematic investigation of backdoor attack on text-to-image diffusion models and propose BadT2I, a general multimodal backdoor attack framework that tampers with image synthesis in diverse semantic levels. Specifically, we perform backdoor attacks on three levels of the vision semantics: Pixel-Backdoor, Object-Backdoor and Style-Backdoor. By utilizing a regularization loss, our methods efficiently inject backdoors into a large-scale text-to-image diffusion model while preserving its utility with benign inputs. We conduct empirical experiments on Stable Diffusion, the widely-used text-to-image diffusion model, demonstrating that the large-scale diffusion model can be easily backdoored within a few fine-tuning steps. We conduct additional experiments to explore the impact of different types of textual triggers, as well as the backdoor persistence during further training, providing insights for the development of backdoor defense methods. Besides, our investigation may contribute to the copyright protection of text-to-image models in the future. Our Code: https://***/sf-zhai/BadT2I.

关键词： text-to-image synthesis Backdoor attack Diffusion model

来源：评论

学校读者我要写书评

暂无评论

Vastr-GAN: Versatile Apparel synthesised from text using a Robust Generative Adversarial Network 2022

Vastr-GAN: Versatile Apparel Synthesised from Text using a R...

引用

5th ACM India Joint International Conference on Data Science and Management of Data (CoDS-COMAD) / 9th ACM IKDD CODS Conference / 26th COMAD Conference

作者： Shastri, Hetvi Lodhavia, Dhruvi Purohit, Palak Kaoshik, Ronak Batra, Nipun IIT Gandhinagar Palaj India

ISBN: (纸本)9781450385824

The development of the fashion industry has increased the demand for customised and meticulously designed clothes. This poses a challenge to fashion designers who need to create novel clothing designs based on the requirements specified by the customers. This work presents a generative adversarial network (GAN) based text-to-image synthesis model for fabricating intricate Indian apparel designs. We introduce an architecture that strategically combines multiple trained GAN models for a streamlined text-to-image generation. Existing fashion datasets with elaborate image descriptions cater to western fashion only. We have extracted traditional Indian images like kurtis, kurtas, etc., and then combined with an existing dataset to create an Indian Fashion dataset of around 16000 images with their corresponding text descriptions. On carrying out elaborate testing on our dataset we have achieved good visual results that can capture the details given in the text descriptions.

关键词： text-to-image synthesis Indian Fashion GAN text encoder,Classifier

来源：评论

学校读者我要写书评

暂无评论

image Generation from text and Segmentation 10

Image Generation from Text and Segmentation

引用

10th International Symposium on Computing and Networking (CANDAR)

作者： Osugi, Masato Vargas, Danilo Vasconcellos Kyushu Univ Grad Sch Informat Sci & Elect Engn Fukuoka Japan Kyushu Univ ISEE Fuculty Fukuoka Japan

ISBN: (纸本)9781665475327

Although text-to-image tasks have been developing in recent years, the controlled generation of images that represent the layout of multiple complex objects remains a challenging problem. Specifically, challenges for the GLIDE model of image generation from text are: controlling the number of objects, scale conversion, instability of generation (objects indicated in the text do not appear in the image), and unnatural object structure. In addition, the task of generating images from textual information alone is so flexible that it is difficult to derive the relevance and requires a large number of data for training. In fact, the training of current generative models often uses hundreds of millions of text-image pairs. The large scale of the generative model itself makes the training cost enormous. In this study, we propose and validate a new image generation method that uses segmentation and text as input. That is, image generation from text is assisted by segmentation information. This should solve issues that GLIDE had difficulty with, such as controlling the number of objects, scale conversion, unstable generation, and unnatural object structure. Furthermore, the goal is to reduce the number of data needed for training by making it easier to find the relationship between textual information and image generation. As a result of the verification, our model achieved FID-10k score of 17.12 after training with only about 120,000 training data, and it was confirmed that it is capable of handling complex layouts and maintaining natural object structure even with a large number of objects.

关键词： image Generation text-to-image synthesis Diffusion Models Multimodal

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：