Due to the technological advances in hardware and compute power nowadays the visual data is collected in huge amounts practically by everyone. The digital cameras are pervasive. Most of the smart devices include camera sensors and are capable of capturing stills and videos. With these large amounts of visual data there is a pressing need to automatically process, organize, interpret the data and refine the information in ways that humans are capable. Computer Vision is asked to provide such solutions. How to achieve such goals? What are the challenges? What are the solutions? What is state-of-the-art? What are the benefits? What is the societal impact? How can we further improve the state-of-the-art? In this seminar, we review, explore and debate such questions based on the recent research at the intersection of Machine Learning, Computer Vision, Robotics and Artificial Intelligence. Each participant will be assigned one topic from a range of computer vision topics, including but not limited to those listed below. Each participant is expected to prepare a written review report covering the state-of-the-art on the particular topic (compiled from at least two research papers) and a corresponding oral presentation. At the same time, each participant is expected to interact, read and comment on the reports provided and presented by the other participants. Each participant will get skills on critical analysis, scientific discourse, and preparation, writing, and presentation on a research topic. Moreover, the participants will get acquainted with state-of-the-art computer vision.
- Dozent: Radu Timofte