Join Kitware’s Computer Vision Team at this year’s International Conference on Computer Vision 2019, taking place October 27-November 2 in Seoul, Korea!
Details:
On Monday, October 28, Kitware’s Assistant Director of Computer Vision, Dr. Arslan Basharat, will speak at the Moving Camera’s 2019 Workshop: From Body Cameras to Drones. Dr. Basharat will give an invited talk titled “The View from Above: Challenges and Capabilities in Overhead Video Understanding.” He has performed research in various areas of computer vision, including object detection and tracking, anomaly detection, activity recognition, dynamical systems in videos, imagery forensics, and imagery retrieval. He will discuss Kitware’s extensive expertise and knowledge of the challenges that overhead video brings and what capabilities and methods to better understand that video can be derived. According to the event organizers, the goal of the workshop is to bring together researchers from the area of intelligent video analytics from moving cameras (body cams, dash cams, drones and other UAVs), in order to discuss emerging technology at the intersection of these areas, as well as their societal implications. Dr. Basharat is one of four invited speakers in the workshop, which takes place in conjunction with the ICCV Conference.
Also on Monday, October 28, Dr. Basharat will also be participating in the Workshop on Video Retrieval Methods and Their Limits, where he has been invited to participate in the panel discussion on “What’s Next for Video Retrieval: Directions and Future Challenges.” On the same day, Dr. Basharat will also be attending the Deep Fake Detection Challenge Luncheon organized by Facebook AI. This event will provide a forum to solicit feedback from the research community on the forthcoming Deep Fake Detection Challenge, one of the largest known public challenges on the detection of deep fakes, manipulated media, and visual misinformation.
Kitware will also have a presence during the main conference. On Friday, November 1 at 3:30 p.m. (15:30), Senior R&D Engineer Dr. Chengjiang Long will present the poster “ARGAN: Attentive Recurrent Generative Adversarial Network for Shadow Detection and Removal.” The purpose is to propose an attentive recurrent generative adversarial network (ARGAN) to detect and remove shadows in an image. The generator consists of multiple progressive steps, which Dr. Long will detail. ARGAN is suitable to be trained with a semi-supervised strategy to make full use of sufficient unsupervised data, which can be very challenging. Come learn more about this robust model and where this work will extend to for future development and implementation addressing shadow detection and removal.
Contact:
Please reach out to computervision@kitware.com to schedule meetings throughout this event. Find out about Kitware’s computer vision research and capability development supporting academia, defense, environmental monitoring, and commercial domains.
About the event:
ICCV is the premier international computer vision event combining high quality tutorials, workshops, and the main exhibition in order to fuel collaboration amongst students, academics, and industry researchers worldwide. The value in attending is exponential as it provides international perspectives on vision techniques, research & development, open-source software, and their current and potential contributions to various domains.
Physical Event
COEX Convention Center
513, Yeongdong-daero, Gangnam-gu Seoul 06164 Republic of Korea