{
  "id": 62398,
  "title": "ECCV 2018 Workshop Call for Participation!!",
  "url": "/competitions/cvpr-2018-autonomous-driving/discussion/62398",
  "author_name": "Xinyu Huang",
  "post_date": "2018-08-01T07:04:53.190000",
  "votes": 0,
  "comment_count": 0,
  "views": 0,
  "content": "<p>Dear Researcher: </p>\n\n<p>We are welcoming paper and challenge submission to ECCV 2018 workshop on vision based 3D perception for autonomous driving, targeting at low-cost perception system without LiDAR.  We accept all papers related to self-driving, robotic and 3D perception etc.  If you are interested, please check the following detailed information: </p>\n\n<p>Title:  ApolloScape: Vision-based Navigation for Autonomous Driving- ECCV 2018 Workshop</p>\n\n<ul>\n<li>A Workshop with invited speakers, challenge, and peer-reviewed papers.</li>\n</ul>\n\n<hr>\n\n<p>Date: 9th September 2018 (Full-day)</p>\n\n<p>Location: Munich, Germany</p>\n\n<p>Website: <a href=\"http://apolloscape.auto/ECCV/index.html\">http://apolloscape.auto/ECCV/index.html</a> </p>\n\n<p>Contact: Peng Wang (wangpeng54@baidu.com)</p>\n\n<hr>\n\n<hr>\n\n<p>IMPORTANT DATES:</p>\n\n<hr>\n\n<p>Submission of full papers and extended abstracts: AUG 22TH, 2018 - 23:59 (GMT)</p>\n\n<p>Submission of challenge results: AUG 31TH, 2018 - 23:59 (GMT)</p>\n\n<p>Notification of acceptance: AUG 27TH, 2018</p>\n\n<p>Camera-ready manuscripts: LATE SEPTEMBER, 2018 (after workshop)</p>\n\n<hr>\n\n<p>SUBMISSION SITE:</p>\n\n<hr>\n\n<p><a href=\"https://cmt3.research.microsoft.com/NVAD2018\">https://cmt3.research.microsoft.com/NVAD2018</a> </p>\n\n<hr>\n\n<p>Challenges:</p>\n\n<hr>\n\n<p>We provide challenges for three important tasks in navigation:</p>\n\n<ul>\n<li><p>Self-localization: 230k images from 7 sites in China with cm-level high accurate GPS/IMU </p></li>\n<li><p>Lanemark-segmentation: 160k images with dense pixel-level 35 semantic label. </p></li>\n<li><p>3D car instance understanding. 70k cars in street view with full 3D shape fitted.</p></li>\n</ul>\n\n<p>Please check <a href=\"http://apolloscape.auto/ECCV/challenge.html\">http://apolloscape.auto/ECCV/challenge.html</a> for details, data and\n<a href=\"https://github.com/ApolloScapeAuto/dataset-api\">https://github.com/ApolloScapeAuto/dataset-api</a> for toolkit.</p>\n\n<hr>\n\n<p>INVITED SPEAKERS</p>\n\n<hr>\n\n<p>Raquel Urtasun,  University of Toronto / UBER</p>\n\n<p>Marc Pollefeys, ETH Zurich, Switzerland / Microsoft, USA</p>\n\n<p>Andreas Geiger, ETH Zurich, Switzerland / UMPI</p>\n\n<p>Hao Su, University of San Diego</p>\n\n<p>We will also have speakers from companies like\nWaymo, Baidu, etc. </p>\n\n<hr>\n\n<p>SCOPE:</p>\n\n<hr>\n\n<p>Topics of interest for this workshop include, but are not limited to:</p>\n\n<ul>\n<li><p>Autonomous navigation and exploration</p></li>\n<li><p>Vision-based advanced driver assistance systems</p></li>\n<li><p>Vision-based underwater and unmanned aerial vehicles</p></li>\n<li><p>Visual driver monitoring and driver-vehicle interfaces</p></li>\n<li><p>On-board camera calibration</p></li>\n<li><p>Performance evaluation of vehicular applications</p></li>\n<li><p>Machine learning techniques for vehicle technology</p></li>\n<li><p>Vision based geo-localization</p></li>\n<li><p>Learning for 3D vision</p></li>\n<li><p>Datasets for self-driving</p></li>\n</ul>\n\n<p>We encourage both the submission of original work in the form of full\npapers and work in progress in the form of an extended abstract. Full\npapers will be peer-reviewed and broadcasted during the workshop. \nExtended abstracts will not be formally published, but we will collect the \nabstracts on the website of the workshop. </p>\n\n<p>Presentation of results on the challenge dataset is in all cases are most welcomed.</p>\n\n<hr>\n\n<p>ORGANIZERS:</p>\n\n<hr>\n\n<p>Peng Wang, Baidu Research Institution</p>\n\n<p>Ruigang Yang, Baidu Research /University of Kentucky</p>\n\n<p>Andreas Geiger, UMPI/ETH-Zurich</p>\n\n<p>Hongdong Li, Australian National University</p>\n\n<p>Alan Yuille, John Hopkins University</p>",
  "messages": [
    {
      "id": 364753,
      "postDate": "2018-08-01T07:04:53.190Z",
      "content": "<p>Dear Researcher: </p>\n\n<p>We are welcoming paper and challenge submission to ECCV 2018 workshop on vision based 3D perception for autonomous driving, targeting at low-cost perception system without LiDAR.  We accept all papers related to self-driving, robotic and 3D perception etc.  If you are interested, please check the following detailed information: </p>\n\n<p>Title:  ApolloScape: Vision-based Navigation for Autonomous Driving- ECCV 2018 Workshop</p>\n\n<ul>\n<li>A Workshop with invited speakers, challenge, and peer-reviewed papers.</li>\n</ul>\n\n<hr>\n\n<p>Date: 9th September 2018 (Full-day)</p>\n\n<p>Location: Munich, Germany</p>\n\n<p>Website: <a href=\"http://apolloscape.auto/ECCV/index.html\">http://apolloscape.auto/ECCV/index.html</a> </p>\n\n<p>Contact: Peng Wang (wangpeng54@baidu.com)</p>\n\n<hr>\n\n<hr>\n\n<p>IMPORTANT DATES:</p>\n\n<hr>\n\n<p>Submission of full papers and extended abstracts: AUG 22TH, 2018 - 23:59 (GMT)</p>\n\n<p>Submission of challenge results: AUG 31TH, 2018 - 23:59 (GMT)</p>\n\n<p>Notification of acceptance: AUG 27TH, 2018</p>\n\n<p>Camera-ready manuscripts: LATE SEPTEMBER, 2018 (after workshop)</p>\n\n<hr>\n\n<p>SUBMISSION SITE:</p>\n\n<hr>\n\n<p><a href=\"https://cmt3.research.microsoft.com/NVAD2018\">https://cmt3.research.microsoft.com/NVAD2018</a> </p>\n\n<hr>\n\n<p>Challenges:</p>\n\n<hr>\n\n<p>We provide challenges for three important tasks in navigation:</p>\n\n<ul>\n<li><p>Self-localization: 230k images from 7 sites in China with cm-level high accurate GPS/IMU </p></li>\n<li><p>Lanemark-segmentation: 160k images with dense pixel-level 35 semantic label. </p></li>\n<li><p>3D car instance understanding. 70k cars in street view with full 3D shape fitted.</p></li>\n</ul>\n\n<p>Please check <a href=\"http://apolloscape.auto/ECCV/challenge.html\">http://apolloscape.auto/ECCV/challenge.html</a> for details, data and\n<a href=\"https://github.com/ApolloScapeAuto/dataset-api\">https://github.com/ApolloScapeAuto/dataset-api</a> for toolkit.</p>\n\n<hr>\n\n<p>INVITED SPEAKERS</p>\n\n<hr>\n\n<p>Raquel Urtasun,  University of Toronto / UBER</p>\n\n<p>Marc Pollefeys, ETH Zurich, Switzerland / Microsoft, USA</p>\n\n<p>Andreas Geiger, ETH Zurich, Switzerland / UMPI</p>\n\n<p>Hao Su, University of San Diego</p>\n\n<p>We will also have speakers from companies like\nWaymo, Baidu, etc. </p>\n\n<hr>\n\n<p>SCOPE:</p>\n\n<hr>\n\n<p>Topics of interest for this workshop include, but are not limited to:</p>\n\n<ul>\n<li><p>Autonomous navigation and exploration</p></li>\n<li><p>Vision-based advanced driver assistance systems</p></li>\n<li><p>Vision-based underwater and unmanned aerial vehicles</p></li>\n<li><p>Visual driver monitoring and driver-vehicle interfaces</p></li>\n<li><p>On-board camera calibration</p></li>\n<li><p>Performance evaluation of vehicular applications</p></li>\n<li><p>Machine learning techniques for vehicle technology</p></li>\n<li><p>Vision based geo-localization</p></li>\n<li><p>Learning for 3D vision</p></li>\n<li><p>Datasets for self-driving</p></li>\n</ul>\n\n<p>We encourage both the submission of original work in the form of full\npapers and work in progress in the form of an extended abstract. Full\npapers will be peer-reviewed and broadcasted during the workshop. \nExtended abstracts will not be formally published, but we will collect the \nabstracts on the website of the workshop. </p>\n\n<p>Presentation of results on the challenge dataset is in all cases are most welcomed.</p>\n\n<hr>\n\n<p>ORGANIZERS:</p>\n\n<hr>\n\n<p>Peng Wang, Baidu Research Institution</p>\n\n<p>Ruigang Yang, Baidu Research /University of Kentucky</p>\n\n<p>Andreas Geiger, UMPI/ETH-Zurich</p>\n\n<p>Hongdong Li, Australian National University</p>\n\n<p>Alan Yuille, John Hopkins University</p>",
      "rawMarkdown": "Dear Researcher: \n \nWe are welcoming paper and challenge submission to ECCV 2018 workshop on vision based 3D perception for autonomous driving, targeting at low-cost perception system without LiDAR.  We accept all papers related to self-driving, robotic and 3D perception etc.  If you are interested, please check the following detailed information: \n \nTitle:  ApolloScape: Vision-based Navigation for Autonomous Driving- ECCV 2018 Workshop\n\n- A Workshop with invited speakers, challenge, and peer-reviewed papers.\n\n*******************************************************\nDate: 9th September 2018 (Full-day)\n\nLocation: Munich, Germany\n\nWebsite: http://apolloscape.auto/ECCV/index.html \n\nContact: Peng Wang (wangpeng54@baidu.com)\n*******************************************************\n\n*******************************************************\n IMPORTANT DATES:\n*******************************************************\nSubmission of full papers and extended abstracts: AUG 22TH, 2018 - 23:59 (GMT)\n\nSubmission of challenge results: AUG 31TH, 2018 - 23:59 (GMT)\n\nNotification of acceptance: AUG 27TH, 2018\n\nCamera-ready manuscripts: LATE SEPTEMBER, 2018 (after workshop)\n\n*******************************************************\n SUBMISSION SITE:\n*******************************************************\n https://cmt3.research.microsoft.com/NVAD2018 \n\n*******************************************************\n Challenges:\n*******************************************************\nWe provide challenges for three important tasks in navigation:\n\n - Self-localization: 230k images from 7 sites in China with cm-level high accurate GPS/IMU \n\n - Lanemark-segmentation: 160k images with dense pixel-level 35 semantic label. \n\n - 3D car instance understanding. 70k cars in street view with full 3D shape fitted.\n \nPlease check http://apolloscape.auto/ECCV/challenge.html for details, data and\nhttps://github.com/ApolloScapeAuto/dataset-api for toolkit.\n\n*******************************************************\n INVITED SPEAKERS\n*******************************************************\nRaquel Urtasun,  University of Toronto / UBER\n\nMarc Pollefeys, ETH Zurich, Switzerland / Microsoft, USA\n\nAndreas Geiger, ETH Zurich, Switzerland / UMPI\n\nHao Su, University of San Diego\n \nWe will also have speakers from companies like\nWaymo, Baidu, etc. \n\n*******************************************************\n SCOPE:\n*******************************************************\nTopics of interest for this workshop include, but are not limited to:\n\n - Autonomous navigation and exploration\n\n - Vision-based advanced driver assistance systems\n \n - Vision-based underwater and unmanned aerial vehicles\n \n - Visual driver monitoring and driver-vehicle interfaces\n \n - On-board camera calibration\n \n - Performance evaluation of vehicular applications\n \n - Machine learning techniques for vehicle technology\n \n - Vision based geo-localization\n \n - Learning for 3D vision\n \n - Datasets for self-driving\n \nWe encourage both the submission of original work in the form of full\npapers and work in progress in the form of an extended abstract. Full\npapers will be peer-reviewed and broadcasted during the workshop. \nExtended abstracts will not be formally published, but we will collect the \nabstracts on the website of the workshop. \n \nPresentation of results on the challenge dataset is in all cases are most welcomed.\n\n*******************************************************\n ORGANIZERS:\n*******************************************************\nPeng Wang, Baidu Research Institution\n\nRuigang Yang, Baidu Research /University of Kentucky\n\nAndreas Geiger, UMPI/ETH-Zurich\n\nHongdong Li, Australian National University\n\nAlan Yuille, John Hopkins University"
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "364753": "Dear Researcher: \n \nWe are welcoming paper and challenge submission to ECCV 2018 workshop on vision based 3D perception for autonomous driving, targeting at low-cost perception system without LiDAR.  We accept all papers related to self-driving, robotic and 3D perception etc.  If you are interested, please check the following detailed information: \n \nTitle:  ApolloScape: Vision-based Navigation for Autonomous Driving- ECCV 2018 Workshop\n\n- A Workshop with invited speakers, challenge, and peer-reviewed papers.\n\n*******************************************************\nDate: 9th September 2018 (Full-day)\n\nLocation: Munich, Germany\n\nWebsite: http://apolloscape.auto/ECCV/index.html \n\nContact: Peng Wang (wangpeng54@baidu.com)\n*******************************************************\n\n*******************************************************\n IMPORTANT DATES:\n*******************************************************\nSubmission of full papers and extended abstracts: AUG 22TH, 2018 - 23:59 (GMT)\n\nSubmission of challenge results: AUG 31TH, 2018 - 23:59 (GMT)\n\nNotification of acceptance: AUG 27TH, 2018\n\nCamera-ready manuscripts: LATE SEPTEMBER, 2018 (after workshop)\n\n*******************************************************\n SUBMISSION SITE:\n*******************************************************\n https://cmt3.research.microsoft.com/NVAD2018 \n\n*******************************************************\n Challenges:\n*******************************************************\nWe provide challenges for three important tasks in navigation:\n\n - Self-localization: 230k images from 7 sites in China with cm-level high accurate GPS/IMU \n\n - Lanemark-segmentation: 160k images with dense pixel-level 35 semantic label. \n\n - 3D car instance understanding. 70k cars in street view with full 3D shape fitted.\n \nPlease check http://apolloscape.auto/ECCV/challenge.html for details, data and\nhttps://github.com/ApolloScapeAuto/dataset-api for toolkit.\n\n*******************************************************\n INVITED SPEAKERS\n*******************************************************\nRaquel Urtasun,  University of Toronto / UBER\n\nMarc Pollefeys, ETH Zurich, Switzerland / Microsoft, USA\n\nAndreas Geiger, ETH Zurich, Switzerland / UMPI\n\nHao Su, University of San Diego\n \nWe will also have speakers from companies like\nWaymo, Baidu, etc. \n\n*******************************************************\n SCOPE:\n*******************************************************\nTopics of interest for this workshop include, but are not limited to:\n\n - Autonomous navigation and exploration\n\n - Vision-based advanced driver assistance systems\n \n - Vision-based underwater and unmanned aerial vehicles\n \n - Visual driver monitoring and driver-vehicle interfaces\n \n - On-board camera calibration\n \n - Performance evaluation of vehicular applications\n \n - Machine learning techniques for vehicle technology\n \n - Vision based geo-localization\n \n - Learning for 3D vision\n \n - Datasets for self-driving\n \nWe encourage both the submission of original work in the form of full\npapers and work in progress in the form of an extended abstract. Full\npapers will be peer-reviewed and broadcasted during the workshop. \nExtended abstracts will not be formally published, but we will collect the \nabstracts on the website of the workshop. \n \nPresentation of results on the challenge dataset is in all cases are most welcomed.\n\n*******************************************************\n ORGANIZERS:\n*******************************************************\nPeng Wang, Baidu Research Institution\n\nRuigang Yang, Baidu Research /University of Kentucky\n\nAndreas Geiger, UMPI/ETH-Zurich\n\nHongdong Li, Australian National University\n\nAlan Yuille, John Hopkins University"
  }
}