Korean Institute of Smart Media

The 11th International Conference on Smart Media & Applications

Prof. In So Kweon
(KAIST, School of EE, Professor)

▪   

Abstract : In recent years, the performance of Deep Learning based approaches for object recognition has improved dramatically and even surpassed human performance in some benchmarking datasets. Specifically, Deep attention models have been very effective to improve recognition performance. In this talk, we present two convolutional attention models inspired by human visual systems, in which the object is defined by the presence or absence of “Local Visual Properties” and by “object parts” with their “Contextual Relations”. We also present a simple and effective video mask transformer model that is widely applicable to multiple video segmentation tasks. TubeFormer-DeepLab directly predicts video tubes with task-specific labels (either pure semantic categories, or both semantic categories and instance identities), which not only significantly simplifies video segmentation models, but also advances state-of-the-art results on multiple video segmentation benchmarks.

▪   

Biography : Professor In So Kweon received the B.S. and the M.S. degrees in Mechanical Design and Production Engineering from Seoul National University, Korea, in 1981 and 1983, respectively, and the Ph.D. degree in Robotics from the Robotics Institute at Carnegie Mellon University in 1990. He worked for Toshiba R&D Center and joined KAIST in 1992. He is a KEPCO Chair professor of the School of Electrical Engineering and had been the director for the National Core Research Center – P3 DigiCar Center at KAIST (2010~2017). His research focuses on Computer Vision and Robotics. He has published 3 research books, and more than 500 papers in leading journals and conference proceedings, including 100+ in prestigious CVPR, ICCV, and ECCV. He is also active in professional service. Currently, he is the President of the Asia Federation of Computer Vision (AFCV). He served on the Editorial Board of the International Journal of Computer Vision for ten years since 2005. He has also organized 5 international conferences either as a general chair or a program chair, including IEEE-CVF ICCV 2019. He was awarded “2016 Faculty Research Excellence Award”, “2020 Grand Prize for Academic Excellence”, and “2021 Hyung-Gyu Im LINKGENESIS Best Teacher Award” by KAIST and conferred a Prime Minister Award by the Korean Government for his contribution to DRC-HUBO+ to win the DARPA Robotics Challenge in 2015. He also received several awards from international conferences, including "The Best Paper Award of the IEEE Transaction on CSVT 2014" and "The Best Student Paper Runnerup Award in the IEEE-CVPR 2009".

Dr. Kiho Lim
(Department of Computer Science, William Paterson University of New Jersey)

▪   

Abstract : Advancement of autonomous driving and vehicular ad-hoc networks (VANETs) have demanded many applications requiring vehicle-to-vehicle (V2V) communications as vehicles cooperatively share their traffic information (collected by sensors) with each other to improve driving safety, traffic efficiency and convenience. In order to secure V2V communications, authentication has been carried out in the presence of the central trusted authority and infrastructures. However, the scenarios where the infrastructures are not available have not been addressed well. In this presentation, we introduce an advanced V2V Authentication scheme for roadside infrastructure-less vehicular networks to authenticate vehicles locally without involvement of a trusted authority and infrastructures. Our protocol utilizes the sensors installed in vehicles to verify the shared surrounding objects. The proposed scheme is robust against possible security threats (e.g., location spoofing attack and man-in-the-middle attack). An extensive simulation was also conducted in an autonomous driving environment to evaluate our scheme.

▪   

Biography : Dr. Kiho Lim is currently an Assistant Professor in the Department of Computer Science at William Paterson University of New Jersey, USA. He received his M.S. and Ph.D. degrees in Computer Science from the University of Kentucky in 2012 and 2016, respectively. His research interests include cybersecurity, network security, vehicular networks, wireless communications, fog/edge computing, and IoT.

Janet S. Choi
(Fellow Physician – Neurotology, University of Minnesota Department of Otolaryngology)

▪   

Abstract : Ears are vital organs of the body that provide special functions including hearing and balance. The basic anatomy of ear-related structures will be reviewed to understand the pathophysiology of common ear diseases including hearing loss, tinnitus, infection, dizziness, and vertigo. This presentation will then take a deeper dive into understanding the global burden of hearing loss especially among the aging population. Hearing loss affects one-quarter of people over 50 years and nearly two-thirds of people over 70 years in the United States. Prior epidemiological studies have demonstrated negative health outcomes associated with hearing loss including depression, anxiety, social isolation, poorer quality of life, decreased physical functioning, and dementia. Hearing loss has been recently identified as the number one modifiable risk factor for dementia. This presentation will review the evidence behind the link between hearing loss and negative health consequences including dementia. It will further discuss the barriers to hearing health care leading to the significantly low rates of hearing loss awareness and hearing aid/cochlear implantation use. Finally, ways to improve access to hearing health care based on multidisciplinary efforts from medicine, engineering, and public health will be discussed. The presentation will introduce innovative hearing technologies incorporating artificial intelligence and computer vision that are currently available and under development.

▪   

Biography : Janet S. Choi, MD MPH is a fellow physician in Otology, Neurotology, and Lateral Skullbase Surgery in the Department of Otolaryngology—Head and Neck Surgery at the University of Minnesota. She earned her bachelor’s degree in bioengineering at the University of California San Diego, her medical degree and master’s in public health from Johns Hopkins School of Medicine and Johns Hopkins Bloomberg School of Public Health. She completed her otolaryngology residency training at the University of Southern California.

Her research work has focused on addressing the problem of low awareness and poor utilization of hearing healthcare. Her research seeks to tackle this problem by 1) establishing hearing care specific databases to further elucidate the impact of hearing and 2) developing artificial intelligence-based platforms that summarize aural rehabilitation options and their outcomes for patients with hearing loss. She led multiple research projects and co-authored numerous epidemiology studies involving otolaryngological diseases and focus group studies integrating qualitative research methods. These projects were sponsored by the National Institute of Health, the Alpha Omega Alpha Honor Society, the American Academy of Otolaryngology, and the Lions Hearing Foundation. Dr.
Dr. Choi is a member of the American Academy of Otolaryngology, board certified by the American Board of Otolaryngology—Head and Neck Surgery. She is an active member of otolaryngology professional associations and serve on their committees.