International Conference on Computational Photography最新文献

Keynote Lecture Towards Neuro-Symbolic AI 神经符号人工智能主题演讲

International Conference on Computational Photography Pub Date : 2022-09-22 DOI: 10.1109/iccp56966.2022.10053958

R. Grosu

引用次数: 0

Keynote Lecture Current Progresses in Natural Language Processing 自然语言处理的最新进展

International Conference on Computational Photography Pub Date : 2022-09-22 DOI: 10.1109/iccp56966.2022.10053984

Rada Mihalcea

引用次数: 0

Keynote Lecture - Building Knowledge For AI AgentsWith Reinforcement Learning 主题演讲-用强化学习为人工智能主体构建知识

International Conference on Computational Photography Pub Date : 2020-09-03 DOI: 10.1109/iccp51029.2020.9266153

Doina Precup

{"title":"Keynote Lecture - Building Knowledge For AI AgentsWith Reinforcement Learning","authors":"Doina Precup","doi":"10.1109/iccp51029.2020.9266153","DOIUrl":"https://doi.org/10.1109/iccp51029.2020.9266153","url":null,"abstract":"Reinforcement learning allows autonomous agents to learn how to act in a stochastic, unknown environment, with which they can interact. Deep reinforcement learning, in particular, has achieved great success in well-defined application domains, such as Go or chess, in which an agent has to learn how to act and there is a clear success criterion. In this talk, I will focus on the potential role of reinforcement learning as a tool for building knowledge representations in AI agents whose goal is to perform continual learning. I will examine a key concept in reinforcement learning, the value function, and discuss its generalization to support various forms of predictive knowledge. I will also discuss the role of temporally extended actions, and their associated predictive models, in learning procedural knowledge. In order to tame the possible complexity of learning knowledge representations, reinforcement learning agents can use the concepts of intents (ie intended consequences of courses of actions) and affordances (which capture knowlege about where actions can be applied). Finally, I will discuss the challenge of how to evaluate reinforcement learning agents whose goal is not just to control their environment, but also to build knowledge about their world.","PeriodicalId":414043,"journal":{"name":"International Conference on Computational Photography","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130067946","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Keynote Lecture - Robotics and AI: Promises and Challenges 主题演讲-机器人与人工智能:承诺与挑战

International Conference on Computational Photography Pub Date : 2020-09-03 DOI: 10.1109/iccp51029.2020.9266165

D. Rus

引用次数: 0

Keynote lecture: Automated driving at Volkswagen Group Research - Future challenges for environment perception 主题演讲:大众汽车集团自动驾驶研究中心——环境感知的未来挑战

International Conference on Computational Photography Pub Date : 2017-09-01 DOI: 10.1109/ICCP.2017.8116973

T. Bagdonat

{"title":"Keynote lecture: Automated driving at Volkswagen Group Research - Future challenges for environment perception","authors":"T. Bagdonat","doi":"10.1109/ICCP.2017.8116973","DOIUrl":"https://doi.org/10.1109/ICCP.2017.8116973","url":null,"abstract":"With the newly developed research vehicle “Sedric” — the first Volkswagen Group vehicle not associated to any brand — Volkswagen presents its vision for future mobility. Being fully electric and fully autonomous, Sedric will be the leading technology platform for automatic driving withing the Group. A brief overview of the recent projects within Volkswagen Group research regarding Level 2 and 3 automation for cars and trucks is given. These functions are based on a “classical” environment perception model including high level sensor data fusion for static and dynamic objects and the road. This model will be shortly discussed. With Sedric the next step towards level 4 and 5 in urban environments will be taken. For this, new technologies for environmental perception are needed, i.e. a redundant multi-modal sensor set, low level sensor data fusion, artificial intelligence for image processing, scene interpretation and prediction as well as a new, versatile path planner. The requirements for these new technologies will be presented alongside with an overview of current algorithms developed at Volkswagen Group research.","PeriodicalId":414043,"journal":{"name":"International Conference on Computational Photography","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124092501","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Keynote lecture: A functional architecture for the navigation of an autonomous vehicle 主题演讲:自动驾驶汽车导航的功能架构

International Conference on Computational Photography Pub Date : 2017-09-01 DOI: 10.1109/ICCP.2017.8116972

F. Nashashibi

引用次数: 0

Keynote speakers: Nature's gift: How the discovery of structural principles in a microbial protein helped illuminate the pathophysiology of psychiatry 主讲人:大自然的礼物:微生物蛋白结构原理的发现如何帮助阐明精神病学的病理生理学

International Conference on Computational Photography Pub Date : 2017-05-01 DOI: 10.1109/ICCPHOT.2017.7951477

K. Deisseroth

{"title":"Keynote speakers: Nature's gift: How the discovery of structural principles in a microbial protein helped illuminate the pathophysiology of psychiatry","authors":"K. Deisseroth","doi":"10.1109/ICCPHOT.2017.7951477","DOIUrl":"https://doi.org/10.1109/ICCPHOT.2017.7951477","url":null,"abstract":"Karl Deisseroth is the D.H. Chen Professor of Bioengineering and of Psychiatry and Behavioral Sciences at Stanford University, and Investigator of the Howard Hughes Medical Institute. He received his undergraduate degree from Harvard, his PhD from Stanford, and his MD from Stanford; he also completed postdoctoral training, medical internship, and adult psychiatry residency at Stanford, and he is board-certified by the American Board of Psychiatry and Neurology. He continues as a practicing psychiatrist at Stanford with specialization in affective disorders and autism-spectrum disease, employing medications along with neural stimulation. In the engineering school he developed and launched the undergraduate degree in Bioengineering at Stanford, and continues to serve as Director of Undergraduate Education in Bioengineering, while also teaching yearly medical physiology and optics courses. National-scale service has included the NIH BRAIN Initiative Working Group and nonprofit disease foundations including the Brain and Behavior Research Foundation (NARSAD) and the Michael J. Fox Foundation for Parkinsons Research. He was selected a Howard Hughes Medical Institute Investigator in 2013, began serving as a foreign adjunct professor at the Karolinska Institute in 2013, and was elected to the US National Academy of Medicine in 2010, to the US National Academy of Sciences in 2012, and to the German National Academy of Sciences (Leopoldina) in 2014.","PeriodicalId":414043,"journal":{"name":"International Conference on Computational Photography","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122140158","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Keynote speakers: Computational imaging: How much imaging - How much computation? 主讲人:计算成像:多少成像-多少计算?

International Conference on Computational Photography Pub Date : 2016-05-13 DOI: 10.1109/ICCPHOT.2016.7492865

G. Häusler, D. Forsyth, M. Walton, F. Halzen, Aydogan Ozcan

{"title":"Keynote speakers: Computational imaging: How much imaging - How much computation?","authors":"G. Häusler, D. Forsyth, M. Walton, F. Halzen, Aydogan Ozcan","doi":"10.1109/ICCPHOT.2016.7492865","DOIUrl":"https://doi.org/10.1109/ICCPHOT.2016.7492865","url":null,"abstract":"This talk will discuss (from the viewpoint of a physicist with background in optical engineering and information) how much imaging and how much computing is (or should be) in computational imaging, aiming for high information efficiency. For an opticist the order of the keywords “computational imaging” is inverted: imaging is the first operation in the sequence, as optics does the encoding for redundancy reduction, which has necessarily to be done before electronic noise is added in the channel. Before computers emerged, decoding was performed solely by optical \"hardware\" and the observer. As for today, it appears as if digital image processing evolved to a new quality: computational imaging, with much more imaging involved than during the times of digital imaging processing. Optics and computational imaging are not anymore in different faculties. Computational imaging will definitely have a great future — and it has a history: opticists do computational imaging for many years, without even knowing the term, as the author of this abstract had to notice to its own astonishment. As paradigms, we will discuss a few 3D-\"cameras\" which exploit different complexity of \"imaging = encoding\" and “computation = decoding”. Among others deflectometry, with a dynamic range of up to 106, SEM like images by pure optics, with large depth of field and very low noise and the 3D motion picture camera, with full 3D information in each camera frame.","PeriodicalId":414043,"journal":{"name":"International Conference on Computational Photography","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127253354","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Designing adaptive services: The case of energy efficiency 设计适应性服务:以能源效率为例

International Conference on Computational Photography Pub Date : 2011-10-20 DOI: 10.1109/ICCP.2011.6047834

B. Pernici

{"title":"Designing adaptive services: The case of energy efficiency","authors":"B. Pernici","doi":"10.1109/ICCP.2011.6047834","DOIUrl":"https://doi.org/10.1109/ICCP.2011.6047834","url":null,"abstract":"The advent of Web services, new network technologies, and new devices gives new opportunities and imposes new requirements for the design and the execution of adaptable information system. Processes can be composed using Web services, but their orchestration has to also consider users needs at runtime, where these needs are expressed as context information. Context information is formed by functional and not functional characteristics and Web services must be selected also considering non functional aspects. In this scenario, new approaches and new frameworks have to be studied in order to overcome the limitations of the current standards, such as WSDL and WS-BPEL, which only consider functional aspects of Web services. Adaptive information systems based on web services allows to select web services based on functional characteristics and QoS, to execute a context aware orchestration of processes composed of Web services. Considering the ever increasing of information technology usage in our everyday life and the huge concentration of computational resources at remote service centers, energy costs become one of the biggest challenging issues for IT managers. Mechanisms to improve energy efficiency in service centers are divided at different levels which range from single components to the whole facility, considering both equipment and application issues.","PeriodicalId":414043,"journal":{"name":"International Conference on Computational Photography","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127827456","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Combining human and computational intelligence for collaborative knowledge creation 结合人类和计算智能，协同创造知识

International Conference on Computational Photography Pub Date : 2011-08-01 DOI: 10.1109/ICCP.2011.6047835

E. Simperl

{"title":"Combining human and computational intelligence for collaborative knowledge creation","authors":"E. Simperl","doi":"10.1109/ICCP.2011.6047835","DOIUrl":"https://doi.org/10.1109/ICCP.2011.6047835","url":null,"abstract":"The Semantic Web is gaining momentum. As of today it has reached an order of magnitude of hundreds of billions of RDF triples, most of which being the result of the increasingly popular Linked Open Data community project, supported by related open access-motivated initiatives such as data.gov and its counterparts worldwide, and the solid theoretical and technical foundations of a decade of Semantic Web research and development. Despite these very encouraging statistics, the usage of this wealth of data in high-impact applications and services is currently not more than an exciting prospect. At the same time, it is already clear that the challenges related to purposefully exposing semantic data will require significant shares of human effort, going beyond the enthusiasm of the past couple of years. Motivating people to engage with the Semantic Web is still an art more than a science. In this talk we will look into fundamental design issues of semantic-content authoring technology - and of the applications deploying such technology - in order to find out which incentives speak to people to collaboratively create knowledge, and to determine the ways these incentives can be transferred into technology design. We will present case studies on the topics of enterprise knowledge management, media and entertainment, and IT ecosystems, in which combining human and computational intelligence has led to increased user participation in creating useful semantic descriptions of various types of digital resources - text documents, images, videos and Web services and APIs.","PeriodicalId":414043,"journal":{"name":"International Conference on Computational Photography","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130114681","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0