Zobrazeno 1 - 10
of 34
pro vyhledávání: '"陳華總"'
Autor:
Chen, Hua-Tsung, 陳華總
98
The explosive proliferation of multimedia data in education, entertainment, sport and various applications necessitates the development of multimedia application systems and tools. As important multimedia content, sports video has been attrac
The explosive proliferation of multimedia data in education, entertainment, sport and various applications necessitates the development of multimedia application systems and tools. As important multimedia content, sports video has been attrac
Externí odkaz:
http://ndltd.ncl.edu.tw/handle/85296734603666522570
Autor:
Hua-Tsung Chen, 陳華總
91
News summarization provides a good starting point for users to efficiently navigate the news stories of interest in different levels of detail without the need to view the entire video through the structured table of video content that contai
News summarization provides a good starting point for users to efficiently navigate the news stories of interest in different levels of detail without the need to view the entire video through the structured table of video content that contai
Externí odkaz:
http://ndltd.ncl.edu.tw/handle/21309150489866087398
Autor:
Chiu, Mian-Jhong, 邱勉中
107
Obstacle avoidance and environment sensing are crucial applications in autonomous driving and robotics. Among all types of sensors, camera is widely used in these applications because it can offer rich visual contents with relatively low-cos
Obstacle avoidance and environment sensing are crucial applications in autonomous driving and robotics. Among all types of sensors, camera is widely used in these applications because it can offer rich visual contents with relatively low-cos
Externí odkaz:
http://ndltd.ncl.edu.tw/handle/4p2ddx
Autor:
Liu, Yu-Hsin, 劉昱鑫
107
Learning 3D geometry in a scene such as depth and optical flow can benefit robotics to perceive the environment and avoid obstacles. In recent years, many researchers develop deep neural networks and use supervised learning to learn 3D geome
Learning 3D geometry in a scene such as depth and optical flow can benefit robotics to perceive the environment and avoid obstacles. In recent years, many researchers develop deep neural networks and use supervised learning to learn 3D geome
Externí odkaz:
http://ndltd.ncl.edu.tw/handle/bf2cwb
108
Video frame interpolation is a common video processing technique. Given two consecutive frames in the same videos as inputs, it predicts single or multiple synthesized frames to smooth motions. The challenges in interpolation, like occlusion
Video frame interpolation is a common video processing technique. Given two consecutive frames in the same videos as inputs, it predicts single or multiple synthesized frames to smooth motions. The challenges in interpolation, like occlusion
Externí odkaz:
http://ndltd.ncl.edu.tw/handle/h2av6g
Autor:
Huang, Zih-Jie, 黃資捷
108
The accuracy of multiple object tracking relies strongly on the accuracy of object detection. Using Convolutional Neural Network in object tracking typically takes features of the current frame, while ignores the temporal correlation of the
The accuracy of multiple object tracking relies strongly on the accuracy of object detection. Using Convolutional Neural Network in object tracking typically takes features of the current frame, while ignores the temporal correlation of the
Externí odkaz:
http://ndltd.ncl.edu.tw/handle/7g46qj
Autor:
Jhuang, You-Ying, 莊侑穎
107
Over the last few years, human action recognition has been a popular issue since this task can be applied in multiple applications such as intelligent surveillance systems, autonomous vehicle control and robotics. Human action recognition us
Over the last few years, human action recognition has been a popular issue since this task can be applied in multiple applications such as intelligent surveillance systems, autonomous vehicle control and robotics. Human action recognition us
Externí odkaz:
http://ndltd.ncl.edu.tw/handle/52d4yz
Autor:
Su, Sheng-Ya, 蘇聖雅
107
In this work we introduce a new network architecture called “L3D” which is inspired by the question if a single network can focus on spatial features first then focus on temporal features, finally predict the result? Traditional 3D convo
In this work we introduce a new network architecture called “L3D” which is inspired by the question if a single network can focus on spatial features first then focus on temporal features, finally predict the result? Traditional 3D convo
Externí odkaz:
http://ndltd.ncl.edu.tw/handle/ass298
Autor:
Lu, Yan-Ting, 盧彥廷
108
In recent years, image segmentation has become an important issue, and been used in many fields like self-driving cars, computer vision, video tracking, medical use and so on. Therefore, there are many researchers devote themselves into this
In recent years, image segmentation has become an important issue, and been used in many fields like self-driving cars, computer vision, video tracking, medical use and so on. Therefore, there are many researchers devote themselves into this
Externí odkaz:
http://ndltd.ncl.edu.tw/handle/yyu3py
Autor:
Jen, Chia-Ching, 任佳靜
106
Three-dimensional (3D) object detection has become a popular research topic recently because it has many applications such as autonomous driving and robotics. 3D object detection typically utilizes point cloud or with the assistance of corre
Three-dimensional (3D) object detection has become a popular research topic recently because it has many applications such as autonomous driving and robotics. 3D object detection typically utilizes point cloud or with the assistance of corre
Externí odkaz:
http://ndltd.ncl.edu.tw/handle/2r5768