Browsing by Author "Tyan, Hsiao-Rong"

Now showing 1 - 3 of 3

Motion flow-based video retrieval
(2007-10-01)
Su, Chih-Wen
;
Liao, Hong-Yuan Mark
;
Tyan, Hsiao-Rong
;
Lin, Chia-Wen
;
Chen, Duan-Yu
In this paper, we propose the use of motion vectors embedded in MPEG bitstreams to generate so-called "motion flows", which are applied to perform video retrieval. By using the motion vectors directly, we do not need to consider the shape of a moving object and its corresponding trajectory. Instead, we simply "link" the local motion vectors across consecutive video frames to form motion flows, which are then recorded and stored in a video database. In the video retrieval phase, we propose a new matching strategy to execute the video retrieval task. Motions that do not belong to the mainstream motion flows are filtered out by our proposed algorithm. The retrieval process can be triggered by query-by-sketch or query-by-example. The experiment results show that our method is indeed superb in the video retrieval process.
Motion Manipulation for Characters in Videos
(2015)
Chu, Hung-Kuo
;
Yeh, Che-Hua
;
Tang, Nick C.
;
Tyan, Hsiao-Rong
;
Wang, Yu-Shuen
Multimedia content creation and manipulation have attracted great attention in recent years due to the popularity of mobile image and video capturing devices. In our daily life, the most common subject appearing in the captured content are people. Hence, to create images and videos by manipulating appearances or motions of the human character inside these media becomes an important research issue. In this paper, we propose a novel idea that requires the fusion of video and audio intelligence. We develop a system whose inputs are a monocular video captured by a stationary RGBD sensor and a music clip. In the context of a human character performing a music conducting motion, the output is a re-targeted video where the motion of performer is manipulated according to the emotional cues extracted from the music clip. To achieve this goal, our system is decomposed into three major stages. First, one needs to access to the geometric and appearance information pertaining to meaningful and representative targets in the video sequence. Second, a systematic way is needed to reliably classify and identify important emotions from the music. Third, to complete the emotion transfer, one has to manipulate the video targets based on the extracted music emotions.
On the Effectiveness of Scheduling Fuzz Testing
(2015-01-01)
Chen, Wei-Jun
;
Tyan, Hsiao-Rong
;
Huang, Shih-Kun
;
資訊工程學系
;
資訊技術服務中心
With the rapid development of software systems, exploiting software vulnerabilities to invade the system has largely increased. As a result, software security becomes vitally important. Since it is impossible to develop programs without bugs and it is inefficient to test program manually, we need a systematic software testing methods to verify if the software is with good quality. Black-box testing is a technique that can find bugs without the target program's source code, and normally copes with mutation fuzz testing. There are numerous fuzz testing tools freely available, but to find the maximum amount of unique bugs in limited interval of time is still a problem remained to be solved. In this paper we have used several scheduling algorithms to improve the fuzzer called FOE (Failure Observation Engine) to better improve the original fuzzing efficiency and produce maximum unique bugs in a given period of time.