[UAI] [CfP] Now running: IEEE FG 2020 Chalearn LAP Challenge: Identity-preserved Human Detection (IPHD)
*** Please accept our apologies if you receive multiple copies of this CfP *** This is a message regarding a change of status of our competition *IEEE FG 2020 Chalearn Looking at People Challenge on Identity-preserved Human Detection (IPHD)* at http://chalearnlap.cvc.uab.es/challenge /34/description. *The competition is now up and running!* *CONTEST DESCRIPTION* For the competition, we ask the participants to perform human detection in depth and/or thermal images. Human detection in images/video is a challenging computer vision problem with applications in human-computer interaction, patient monitoring, surveillance, and autonomous driving, just to mention a few. In some applications, however, keeping people's privacy is a big concern for both users and companies/institutions involved. Most notably, unintended identity revelation of subjects is perhaps the greatest peril. While video data from RGB cameras are massively available to train powerful detection models, the nature of these data may also allow unpermitted third parties to access such data to try to identify observed subjects. We argue that moving away from visual sensors that capture identity information in the first place is the safest bet. However, the lack of these more privacy-safe data affects the ability to train big deep-learning models, thus affecting negatively the popularity of these sensors. For this competition, we offer a freshly-recorded multimodal image dataset consisting of over 100K spatiotemporally aligned depth-thermal images of different people recorded in public and private spaces: street, university (cloister, hallways, and rooms), a research center, libraries, and private houses. In particular, we used RealSense D435 for depth and FLIR Lepton v3 for thermal. Given the noisy nature of such commercial depth camera and the thermal image resolution, the subjects are hardly identifiable. The dataset contains a mix of close-range in-the-wild pedestrian scenes and indoor ones with people performing in scripted scenarios, thus covering a larger space of poses, clothing, illumination, background clutter, and occlusions. The scripted scenarios include basic actions such as: sit on the sofa, lay on the floor, interacting with kitchen appliances, cooking, eating, working on the computer, talking on the phone, and so on. The camera position is not necessarily static, but sometimes held by a person. The data were originally collected as videos from different duration (from seconds to hours) but skipping frames where no movement was observed. The ordering of frames is removed to make it an image dataset (the only information provided will be the video ID). There are *three tracks* associated to this contest: 1. *Depth track*. Given the provided depth frames (and bounding box groundtruth annotations), the participants will be asked to develop their depth-based human detection method. Depth cameras are cost-effective devices that provide geometric information of the scene at a resolution and frame acquisition speed that is comparable to RGB cameras. The downside is their noisiness at large real distances. The method developed by the participants will need to output a list of bounding boxes (and their confidence scores) per frame containing each person in it. The performance on depth image-based human detection will be evaluated. 2. *Thermal track*. Given the provided thermal frames (and bounding box groundtruth annotations), the participants will be asked to develop their thermal-based human detection method. Thermal cameras provide temperature readings from the scene. They are less noisy than depth cameras, but at a comparable price they offer a much lower image resolution. The method developed by the participants will need to output a list of bounding boxes (and their confidence scores) per frame containing each person in it. The performance on depth image-based human detection will be evaluated. 3. *Depth-Thermal Fusion track*. Given the provided aligned depth-thermal frames (and bounding box groundtruth annotations), the participants will be asked to develop their multimodal (depth and thermal) human detection method. Both modalities have been temporally and spatially aligned and, hence, so they will try to exploit their potential complementarity with a proper fusion strategy. The participants will need to output a list of bounding boxes per frame (and their confidence scores) containing each person in it. The performance on depth image-based human detection will be evaluated. The competition will be run in the CodaLab platform. The participants will register through the platform, where they will be able to access to the different tracks (corresponding data, evaluation scripts, leaderboard, etc). The CodaLab can be found at: http://chalearnlap.cvc.uab.es/challenge/34/description. *ASSOCIATED EVENTS* The participants will be invited to submit their papers to the associated event: *IEEE FG 2020 Workshop on Privacy-aware Comp
[UAI] [Percom 2020] Work-in-Progress (WiP) Call for Papers
The Percom 2020 Work-in-Progress (WiP) Call for Papers The Work-in-Progress (WiP) session provides an opportunity to present and discuss new challenges and visions, showcase early research results, and explore novel research directions. The specific aim of the WiP session is to provide a forum for timely presentation, discussion and feedback for novel, controversial, and thought-provoking ideas. All selected papers will be presented as posters in a special conference session and published as part of the PerCom Workshops proceedings to be published by IEEE and included in the IEEE Xplore digital library. Contributions are solicited in all areas of pervasive computing research and applications. Papers are expected to report on early or ongoing research on any aspect of pervasive computing and communications. Preliminary experimental results are appreciated. Submission Guidelines Authors are requested to submit original, unpublished manuscripts in standard IEEE proceedings format (two-column format with a 4-page limit including figures, tables, and references) in PDF format that include contact information of all the authors. All manuscripts must be registered and submitted through the EDAS submission site. New this year! The WiP Chairs and the WiP Program Committee will also select up to three finalists for best WiP contribution. Each best WiP candidate will be given an additional 10 minute presentation as part of the main conference in addition to their poster presentations. The committee will select a best WiP contribution from among these finalists, with the award to be presented at the conference. Important Dates Submission deadline: November 24, 2019 Notification of acceptance: December 23, 2019 Camera ready deadline: January 31, 2020 For further information about the Work In Progress portion of the program, please see http://www.percom.org/call-for-wip or contact the WiP Co-Chairs Petteri Nurmi (ptnu...@cs.helsinki.fi) and James Xi Zheng (james.zh...@mq.edu.au). ___ uai mailing list uai@ENGR.ORST.EDU https://secure.engr.oregonstate.edu/mailman/listinfo/uai
[UAI] [journals] Final Reminder (due 15 Dec): Special Issue on "Robotics in Extreme Environments"
Dear Colleagues, Robotics is currently running a Special Issue entitled "Robotics in Extreme Environments". Prof. Rustam Stolkin, from Royal Society Industry Fellow for Nuclear Robotics, University of Birmingham, is serving as Guest Editor for this issue. We are pleased to invite you to submit your papers to this Special Issue of Robotics, "Robotics in Extreme Environments". Extreme environments can be defined as those that are so hazardous that it would be undesirable or impossible to send a human worker into the environment. Such applications are of special importance to the robotics research community, because they demand the use of robots and often cannot be done at all without major new advances in robotics. In contrast, while research on, e.g., household helper robots is certainly interesting, such jobs can still be done by human workers if needed at the present time... For further reading, please follow the link to the Special Issue Website at: https://www.mdpi.com/journal/robotics/special_issues/REE. The submission deadline is 15 December 2019. You may send your manuscript now or up until the deadline. Submitted papers should not be under consideration for publication elsewhere. We also encourage authors to send a short abstract or tentative title to the Editorial Office in advance (robot...@mdpi.com). The Robotics is an online open access journal dedicated to both the foundations of artificial intelligence, bio-mechanics and mechatronics, and the real-world applications of robotic perception, cognition and actions. The journal is presently covered by the following indexing: Scopus(citescore 1.53), Emerging Sources Citation Index (ESCI - Web of Science),Directory of Open Access Journals (DOAJ), INSPEC (IET) and DBLP Computer Science Bibliography. For further details on the submission process, please see the instructions for authors at the journal website (http://www.mdpi.com/journal/robotics/instructions). We look forward to hearing from you. Best regards, Linda Wang Managing Editor To submit to the journal click here: http://susy.mdpi.com/user/manuscripts/upload?journal=robotics Unsubscribe: http://www.mdpi.com/unsub/unsubscribe/mail/Um9ib3RpY3NAbWRwaS5jb20=/8795b601147e7dee2ad869265e01dc6bf1bad227048e5558d1cfb6a3136b52d5 Manage your subscriptions: http://www.mdpi.com/unsub/managesubscriptions/mail/Um9ib3RpY3NAbWRwaS5jb20=/8795b601147e7dee2ad869265e01dc6bf1bad227048e5558d1cfb6a3136b52d5 MDPI - Multidisciplinary Digital Publishing Institute www.mdpi.com St. Alban-Anlage 66 4052 Basel Switzerland Tel. +41 61 683 77 34 Fax +41 61 302 89 18 ___ uai mailing list uai@ENGR.ORST.EDU https://secure.engr.oregonstate.edu/mailman/listinfo/uai
