http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
An Efficient Pedestrian Detection Approach Using a Novel Split Function of Hough Forests
Trung Dung Do,Thi Ly Vu,Van Huan Nguyen,Hakil Kim,Chongho Lee 한국정보과학회 2014 Journal of Computing Science and Engineering Vol.8 No.4
In pedestrian detection applications, one of the most popular frameworks that has received extensive attention in recent years is widely known as a ‘Hough forest’ (HF). To improve the accuracy of detection, this paper proposes a novel split function to exploit the statistical information of the training set stored in each node during the construction of the forest. The proposed split function makes the trees in the forest more robust to noise and illumination changes. Moreover, the errors of each stage in the training forest are minimized using a global loss function to support trees to track harder training samples. After having the forest trained, the standard HF detector follows up to search for and localize instances in the image. Experimental results showed that the detection performance of the proposed framework was improved significantly with respect to the standard HF and alternating decision forest (ADF) in some public datasets.
An Efficient Pedestrian Detection Approach Using a Novel Split Function of Hough Forests
Do, Trung Dung,Vu, Thi Ly,Nguyen, Van Huan,Kim, Hakil,Lee, Chongho Korean Institute of Information Scientists and Eng 2014 Journal of Computing Science and Engineering Vol.8 No.4
In pedestrian detection applications, one of the most popular frameworks that has received extensive attention in recent years is widely known as a 'Hough forest' (HF). To improve the accuracy of detection, this paper proposes a novel split function to exploit the statistical information of the training set stored in each node during the construction of the forest. The proposed split function makes the trees in the forest more robust to noise and illumination changes. Moreover, the errors of each stage in the training forest are minimized using a global loss function to support trees to track harder training samples. After having the forest trained, the standard HF detector follows up to search for and localize instances in the image. Experimental results showed that the detection performance of the proposed framework was improved significantly with respect to the standard HF and alternating decision forest (ADF) in some public datasets.
Cheng-Bin Jin(김성빈),Trung Dung Do,Mingjie Liu,Hakil Kim(김학일) 제어로봇시스템학회 2018 제어·로봇·시스템학회 논문지 Vol.24 No.3
When we say a person is texting, can you tell the person is walking or sitting? Emphatically, no. In order to solve this incomplete representation problem, this paper presents a sub-action descriptor for detailed action detection. The sub-action descriptor consists of three levels: posture, locomotion, and gestures. The three levels provide three sub-action categories for a single action in order to address the representation problem. The proposed action detection model simultaneously localizes and recognizes the actions of multiple individuals in video surveillance using appearance-based temporal features with multi-convolutional neural networks. The proposed approach achieved a mean average precision of 76.6% for frame-based measurement and 83.5% for video-based measurement of the ICVL video surveillance dataset. Extensive experiments on the benchmark KTH dataset demonstrate that the proposed approach achieved better performance, which in turn improves action recognition performance in comparison to the stateof-the-art methods. The action detection model can run at around 25 fps with the ICVL dataset and at more than 80 fps with the KTH dataset, which is suitable for real-time surveillance applications.
Thi Ly Vu,Trung Dung Do,Cheng-Bin Jin,Shengzhe Li,Van Huan Nguyen,Hakil Kim,Chongho Lee 한국정보과학회 2015 Journal of Computing Science and Engineering Vol.9 No.1
Human action recognition has become an important research topic in computer vision area recently due to many applications in the real world, such as video surveillance, video retrieval, video analysis, and human-computer interaction. The goal of this paper is to evaluate descriptors which have recently been used in action recognition, namely Histogram of Oriented Gradient (HOG) and Histogram of Optical Flow (HOF). This paper also proposes new descriptors to represent the change of points within each part of a human body, caused by actions named as Histogram of Changing Points (HCP) and so-called Average Speed (AS) which measures the average speed of actions. The descriptors are combined to build a strong descriptor to represent human actions by modeling the information about appearance, local motion, and changes on each part of the body, as well as motion speed. The effectiveness of these new descriptors is evaluated in the experiments on KTH and Hollywood datasets.
Vu, Thi Ly,Do, Trung Dung,Jin, Cheng-Bin,Li, Shengzhe,Nguyen, Van Huan,Kim, Hakil,Lee, Chongho Korean Institute of Information Scientists and Eng 2015 Journal of Computing Science and Engineering Vol.9 No.1
Human action recognition has become an important research topic in computer vision area recently due to many applications in the real world, such as video surveillance, video retrieval, video analysis, and human-computer interaction. The goal of this paper is to evaluate descriptors which have recently been used in action recognition, namely Histogram of Oriented Gradient (HOG) and Histogram of Optical Flow (HOF). This paper also proposes new descriptors to represent the change of points within each part of a human body, caused by actions named as Histogram of Changing Points (HCP) and so-called Average Speed (AS) which measures the average speed of actions. The descriptors are combined to build a strong descriptor to represent human actions by modeling the information about appearance, local motion, and changes on each part of the body, as well as motion speed. The effectiveness of these new descriptors is evaluated in the experiments on KTH and Hollywood datasets.
Outcomes of liver transplantation for hepatocellular carcinoma: Experiences from a Vietnamese center
Khai Viet Ninh,Dang Hai Do,Trung Duc Nguyen,Phuong Ha Tran,Tuan Hoang,Dung Thanh Le,Nghia Quang Nguyen 한국간담췌외과학회 2024 Annals of hepato-biliary-pancreatic surgery Vol.28 No.1
Backgrounds/Aims: Liver transplantation (LT) provides a favorable outcome for patients with hepatocellular carcinoma (HCC) and was launched in Vietnam in 2004. In this study, we evaluated the short-term and long-term outcomes of LT and its risk factors. Methods: This retrospective study analyzed HCC patients who underwent LT at Viet Duc University hospital, Vietnam, from 01/2012–03/2022. The following data were gathered: demographics, virus infection, tumor characteristics, alpha-fetoprotein (AFP) level, Child-Pugh and MELD scores, selection criteria, type of LT, complications, 30-day mortality, and disease-free and overall survival (DFS and OS). Results: Fifty four patients were included, the mean age was 55.39 ± 8.46 years. Nearly 90% had hepatitis B virus-related HCC. The median (interquartile range) AFP level was 16.2 (88.7) ng/mL. The average MELD score was 10.57 ± 5.95; the rate of Child-Pugh A and B were 70.4% and 18.5%, respectively. Nearly 40% of the patients were within Milan criteria, brain-dead donor was 83.3%. Hepatic and portal vein thrombosis occurred in 0% and 1.9%, respectively; hepatic artery thrombosis 1.9%, biliary leakage 5.6%, and postoperative hemorrhage 3.7%. Ninety-day mortality was 5.6%. Five-year DFS and OS were 79.3% and 81.4%, respectively. MELD score and Child- Pugh score were predictive factors for DFS and OS (p < 0.05). In multivariate analysis, Child-Pugh score was the only significant factor (p < 0.05). Conclusions: In Vietnam, LT is an effective therapy for HCC with an acceptable complication rate, mortality rate, and good survival outcomes, and should be further encouraged.