Zobrazeno 1 - 10
of 190
pro vyhledávání: '"Chee Sun Won"'
Autor:
Jun-Hwa Kim, Chee Sun Won
Publikováno v:
Applied Sciences, Vol 14, Iss 3, p 1190 (2024)
Our approach to action recognition is grounded in the intrinsic coexistence of and complementary relationship between audio and visual information in videos. Going beyond the traditional emphasis on visual features, we propose a transformer-based net
Externí odkaz:
https://doaj.org/article/b553acd97b924a7397508204bf976e2e
Publikováno v:
IEEE Access, Vol 9, Pp 123348-123357 (2021)
This paper provides a modular architecture with deep neural networks as a solution for real-time video analytics in an edge-computing environment. The modular architecture consists of two networks of Front-CNN (Convolutional Neural Network) and Back-
Externí odkaz:
https://doaj.org/article/b68cc1046391466a86e1d3a784410c39
Autor:
Jun-Hwa Kim, Chee Sun Won
Publikováno v:
IEEE Access, Vol 8, Pp 60179-60188 (2020)
A pre-trained 2D CNN (Convolutional Neural Network) can be used for the spatial stream in the two-stream CNN structure for videos, treating the representative frame selected from the video as an input. However, the CNN for the temporal stream in the
Externí odkaz:
https://doaj.org/article/b02a5074f90e4f158385bb1e8979b6ee
Autor:
Chee Sun Won
Publikováno v:
IEEE Access, Vol 8, Pp 116663-116674 (2020)
Most conventional fine-grained image recognitions are based on a two-stream model of object-level and part-level CNNs, where the part-level CNN is responsible for learning the object-parts and their spatial relationships. To train the part-level CNN,
Externí odkaz:
https://doaj.org/article/7e4c916e20b041c8a61db13f4e986321
Autor:
Trinh Thi Doan Pham, Chee Sun Won
Publikováno v:
IEEE Access, Vol 7, Pp 77816-77824 (2019)
This paper deals with the problem of training convolutional neural networks (CNNs) with facial action units (AUs). In particular, we focus on the imbalance problem of the training datasets for facial emotion classification. Since training a CNN with
Externí odkaz:
https://doaj.org/article/c18861fb93c344c5baf4992dcaf77f42
Publikováno v:
Journal of Marine Science and Engineering, Vol 10, Iss 3, p 377 (2022)
SMD (Singapore Maritime Dataset) is a public dataset with annotated videos, and it is almost unique in the training of deep neural networks (DNN) for the recognition of maritime objects. However, there are noisy labels and imprecisely located boundin
Externí odkaz:
https://doaj.org/article/ce2665e3f5764338a85280580363aae1
Autor:
Chee Sun Won
Publikováno v:
IEEE Access, Vol 6, Pp 54823-54833 (2018)
Conventional image resizing problems demand hard conditions on size and aspect ratio, which must be met with no tolerance. In this paper, a generalized optimization framework is presented, which can handle soft conditions as well as the hard ones. Th
Externí odkaz:
https://doaj.org/article/e8e71977a12e48dc80f14b80456b0f54
Publikováno v:
Sensors, Vol 14, Iss 7, Pp 11362-11378 (2014)
Depth maps taken by the low cost Kinect sensor are often noisy and incomplete. Thus, post-processing for obtaining reliable depth maps is necessary for advanced image and video applications such as object recognition and multi-view rendering. In this
Externí odkaz:
https://doaj.org/article/437d30980ee54d0d904eb5f66303be2f
Publikováno v:
Sensors, Vol 14, Iss 3, Pp 5333-5353 (2014)
Calibration between color camera and 3D Light Detection And Ranging (LIDAR) equipment is an essential process for data fusion. The goal of this paper is to improve the calibration accuracy between a camera and a 3D LIDAR. In particular, we are intere
Externí odkaz:
https://doaj.org/article/6eb06aeee12d4753a91385b33d25e5a5
Publikováno v:
Sensors, Vol 19, Iss 2, p 393 (2019)
Segmentation of human bodies in images is useful for a variety of applications, including background substitution, human activity recognition, security, and video surveillance applications. However, human body segmentation has been a challenging prob
Externí odkaz:
https://doaj.org/article/e6fe43564c0e4e5a8e7f210a4c1838c6