Date / Time | 2022-07-20 13:30 -- 15:00 |
---|---|
Room | Estaque |
Conveners / Chairs |
|
Synopsis | In this session, the future sensors, imaging and display electronics will be discussed. The sensor, imaging and display systems are enabling us to access the information quickly, easily, and efficiently.
To share the operational principles of the sensor and imaging systems, several sensor systems will be introduced in various applications such as bio and automotive applications. In addition, the Visualization and device technology trends for hyper-realistic metaverse services will be introduced to give a display technology trend.
In this session, the experts having various backgrounds of systems are welcomed to share their experience.
|
Speakers |
|
Date / Time | 2022-07-21 11:00 -- 12:30 |
---|---|
Room | Estaque |
Conveners / Chairs |
|
Synopsis | Robot vision for human cognition often fails to work well in the real-world situation, despite the disruptive results achieved in Computer Vision and Artificial Intelligence. While most training data have been collected in well-conditioned, easy-to-isolate backgrounds, wild videos from the real-world may contain various environmental conditions such as lighting, background patterns, and, most notoriously, occlusions. The latter becomes the source of recurrent problems when it comes to human cognition by care-robots in the in-house situation. Large variations in body shapes, motions, clothes, and frequent interactions with objects also contribute to the difficulty. Finally, viewing dynamics by moving robots and humans is another source of the problem. Unfortunately, it is almost impossible to collect a large, annotated dataset that spans over all possible configurations of the real-world scene.
In this session, we will discuss a number of promising approaches to remedy such problems, a model-based learning framework being one of them. The main idea is to equip the robot with a photorealistic, physics-aware human model, so that the it can reconstruct the human and the world it is observing efficiently and robustly, over which the cognition task will be performed. Constituting the central idea of a binational project, it is under elaboration by researchers at ETRI, CNRS, and INRIA. Participanting members as well as invited researchers will present their on-going works around intelligent robot, human modeling, and physics-based simulation for health and medicine, grounded on their common interests in deep learning.
|
Speakers |
|
Date / Time | 2022-07-21 15:20 -- 16:50 |
---|---|
Room | Estaque |
Conveners / Chairs |
|
Synopsis | This session presents modern semiconductor device technologies (Si, InP, SiC, GaN) and circuits (low-noise, high-speed, multi-disciplinary) for industrial and consumer-electronics applications. For example, modern high-power devices using SiC or GaN will be discussed and their applications and market trends with respect to energy conversion and e-vehicles will be addressed. Also, novel low-noise circuits using CMOS will be presented. Details about a novel low-noise circuit design technique and impact on the emerging internet-of-things (IoT) will be provided. Higher-speed interconnection technologies and sub-THz with low-power consumption using S and III-V i technologies to enable higher internet access by users will be presented. Recent advancements will be available during talks. All presenters will also discuss the R&D collaboration interests between EU and Korea about each presentation topic. |
Speakers |
|