Zobrazeno 1 - 10
of 17
pro vyhledávání: '"Kyoung Mu Lee"'
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 44:9615-9628
Video frame interpolation is a challenging problem that involves various scenarios depending on the variety of foreground and background motions, frame rate, and occlusion. Therefore, generalizing across different scenes is difficult for a single net
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 44:7718-7730
Few-shot learning is an emerging yet challenging problem in which the goal is to achieve generalization from only few examples. Meta-learning tackles few-shot learning via the learning of prior knowledge shared across tasks and using it to learn new
Autor:
Kyoung Mu Lee
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 44:11-12
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 40:2374-2387
State-of-the-art video deblurring methods cannot handle blurry videos recorded in dynamic scenes since they are built under a strong assumption that the captured scenes are static. Contrary to the existing methods, we propose a new video deblurring a
Autor:
Kyoung Mu Lee, Junseok Kwon
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 39:18-31
A novel tracking algorithm is proposed, which robustly tracks a target by finding the state that minimizes the likelihood uncertainty. Likelihood uncertainty is estimated by determining the gap between the lower and upper bounds of likelihood. By min
Autor:
Kyoung Mu Lee, Junseok Kwon
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 37:1737-1750
A novel approach for event summarization and rare event detection is proposed. Unlike conventional methods that deal with event summarization and rare event detection independently, our method solves them in a single framework by transforming them in
Publikováno v:
IEEE transactions on pattern analysis and machine intelligence. 40(10)
Depth estimation is essential in many light field applications. Numerous algorithms have been developed using a range of light field properties. However, conventional data costs fail when handling noisy scenes in which occlusion is present. To addres
Autor:
Kyoung Mu Lee, Junseok Kwon
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 36:1428-1441
We propose the visual tracker sampler, a novel tracking algorithm that can work robustly in challenging scenarios, where several kinds of appearance and motion changes of an object can occur simultaneously. The proposed tracking algorithm accurately
Autor:
Kyoung Mu Lee, Junseok Kwon
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 35:2427-2441
A novel tracking algorithm is proposed for targets with drastically changing geometric appearances over time. To track such objects, we develop a local patch-based appearance model and provide an efficient online updating scheme that adaptively chang
Publikováno v:
IEEE transactions on pattern analysis and machine intelligence. 36(4)
Existing approaches to template-based visual tracking, in which the objective is to continuously estimate the spatial transformation parameters of an object template over video frames, have primarily been based on deterministic optimization, which as