Visual knowledge guided intelligent generation of Chinese seal carving

We digitally reproduce the process of resource collaboration,design creation,and visual presentation of Chinese seal-carving art.We develop an intelligent seal-carving art-generation system(Zhejiang University Intelligent Seal-Carving System,http://www.next.zju.edu.cn/seal/;the website of the seal-carving search and layout system is http://www.next.zju.edu.cn/seal/search_app/)to deal with the difficulty in using a visual knowledge guided computational art approach.The knowledge base in this study is the Qiushi Seal-Carving Database,which consists of open datasets of images of seal characters and seal stamps.We propose a seal character generation method based on visual knowledge,guided by the database and expertise.Furthermore,to create the layout of the seal,we propose a deformation algorithm to adjust the seal characters and calculate layout parameters from the database and knowledge to achieve an intelligent structure.Experimental results show that this method and system can effectively deal with the difficulties in the generation of seal carving.Our work provides theoretical and applied references for the rebirth and innovation of seal-carving art.

基于精确扩散反演的生成式图像内生水印方法

扩散模型在图像生成方面取得了显著成就,但生成的图像真假难辨,因此滥用扩散模型将引发隐私安全、法律伦理等社会问题。对生成模型的输出添加水印可以追踪生成内容版权,防止人工智能生成内容造成潜在危害。对于去噪扩散模型,在初始噪声向量中添加水印的内生水印方法可直接生成含水印图像,版权验证时通过反向扩散重建初始向量以提取水印。但扩散模型中的采样过程并不是严格可逆,重建的噪声向量与原始噪声存在较大误差,很难保证水印的准确提取。通过引入基于耦合变换的精确反向扩散,可以更加准确地重建初始噪声向量,提升水印提取的准确性。通过实验验证了引入基于耦合变换的精确反向扩散对于生成式图像内生水印的性能提升,实验结果表明,内生水印可以在生成图像中嵌入不可见水印,嵌入的水印可通过精确反向扩散被准确提取,并具有一定的稳健性。

Cogeneration of Innovative Audio-visual Content: A New Challenge for Computing Art

In recent years,computing art has developed rapidly with the in-depth cross study of artificial intelligence generated con-tent(AIGC)and the main features of artworks.Audio-visual content generation has gradually been applied to various practical tasks,including video or game score,assisting artists in creation,art education and other aspects,which demonstrates a broad application pro-spect.In this paper,we introduce innovative achievements in audio-visual content generation from the perspective of visual art genera-tion and auditory art generation based on artificial intelligence(Al).We outline the development tendency of image and music datasets,visual and auditory content modelling,and related automatic generation systems.The objective and subjective evaluation of generated samples plays an important role in the measurement of algorithm performance.We provide a cogeneration mechanism of audio-visual content in multimodal tasks from image to music and display the construction of specific stylized datasets.There are still many new op-portunities and challenges in the field of audio-visual synesthesia generation,and we provide a comprehensive discussion on them.

Prompt learning in computer vision: a survey

Prompt learning has attracted broad attention in computer vision since the large pre-trained visionlanguagemodels (VLMs) exploded. Based on the close relationship between vision and language information builtby VLM, prompt learning becomes a crucial technique in many important applications such as artificial intelligencegenerated content (AIGC). In this survey, we provide a progressive and comprehensive review of visual promptlearning as related to AIGC. We begin by introducing VLM, the foundation of visual prompt learning. Then, wereview the vision prompt learning methods and prompt-guided generative models, and discuss how to improve theefficiency of adapting AIGC models to specific downstream tasks. Finally, we provide some promising researchdirections concerning prompt learning.

On Interdisciplinary Studies of a New Generation of Artificial Intelligence and Logic

A new generation of artificial intelligence(NGAI),currently based on big data and machine learning,follows a path of connectionism.Although this path achieves huge success in data-intensive applications under closed environments,there are some bottleneck problems,including a lack of explainability,the difficulty of ethical alignment,the weakness ofcognitive reasoning,etc.To address these problems inevitably involves thedepiction of information from an open,dynamic and real environment and the modeling of human reasoning and explanation mechanisms.Formal argumentation is a general formalism for modeling various types of knowledge representation and reasoning in a context of disagreement,and is flexible enough to incorporate other types of knowledge for decisionmaking,such as preferences,weights,and probabilities.Meanwhile,there are various approaches for efficient computation of argumentation semantics by exploiting the locality and modularity of argumentation,and for providing explanations based on arguments and dialogues.The organic combination of formal argumentation with existing big data and machine learning techniques can be expected to break through some existing technical bottlenecks and facilitate the sustainable development of NGAI.

AIGC challenges and opportunities related to public safety:A case study of ChatGPT

Artificial intelligence generated content(AIGC)is a production method based on artificial intelligence(AI)technology that finds rules through data and automatically generates content.In contrast to computational intelligence,generative AI,as exemplified by ChatGPT,exhibits characteristics that increasingly resemble human-level comprehension and creation processes.This paper provides a detailed technical framework and history of ChatGPT,followed by an examination of the challenges posed to political security,military security,economic security,cultural security,social security,ethical security,legal security,machine escape problems,and information leakage.Finally,this paper discusses the potential opportunities that AIGC presents in the realms of politics,military,cybersecurity,society,and public safety education.