Search

Your search keyword '"Sun, Hang"' showing total 1,370 results
Start Over Author "Sun, Hang" Search Limiters Available in Library Collection
1,370 results on '"Sun, Hang"'

5. Precise Facial Landmark Detection by Reference Heatmap Transformer

Author

Wan, Jun, Liu, Jun, Zhou, Jie, Lai, Zhihui, Shen, Linlin, Sun, Hang, Xiong, Ping, and Min, Wenwen

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Most facial landmark detection methods predict landmarks by mapping the input facial appearance features to landmark heatmaps and have achieved promising results. However, when the face image is suffering from large poses, heavy occlusions and complicated illuminations, they cannot learn discriminative feature representations and effective facial shape constraints, nor can they accurately predict the value of each element in the landmark heatmap, limiting their detection accuracy. To address this problem, we propose a novel Reference Heatmap Transformer (RHT) by introducing reference heatmap information for more precise facial landmark detection. The proposed RHT consists of a Soft Transformation Module (STM) and a Hard Transformation Module (HTM), which can cooperate with each other to encourage the accurate transformation of the reference heatmap information and facial shape constraints. Then, a Multi-Scale Feature Fusion Module (MSFFM) is proposed to fuse the transformed heatmap features and the semantic features learned from the original face images to enhance feature representations for producing more accurate target heatmaps. To the best of our knowledge, this is the first study to explore how to enhance facial landmark detection by transforming the reference heatmap information. The experimental results from challenging benchmark datasets demonstrate that our proposed method outperforms the state-of-the-art methods in the literature., Comment: Accepted by IEEE Transactions on Image Processing, March 2023

Published
2023
Full Text
View/download PDF

15. Robust and Precise Facial Landmark Detection by Self-Calibrated Pose Attention Network

Author

Wan, Jun, Xi, Hui, Zhou, Jie, Lai, Zhihui, Pedrycz, Witold, Wang, Xu, and Sun, Hang

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Current fully-supervised facial landmark detection methods have progressed rapidly and achieved remarkable performance. However, they still suffer when coping with faces under large poses and heavy occlusions for inaccurate facial shape constraints and insufficient labeled training samples. In this paper, we propose a semi-supervised framework, i.e., a Self-Calibrated Pose Attention Network (SCPAN) to achieve more robust and precise facial landmark detection in challenging scenarios. To be specific, a Boundary-Aware Landmark Intensity (BALI) field is proposed to model more effective facial shape constraints by fusing boundary and landmark intensity field information. Moreover, a Self-Calibrated Pose Attention (SCPA) model is designed to provide a self-learned objective function that enforces intermediate supervision without label information by introducing a self-calibrated mechanism and a pose attention mask. We show that by integrating the BALI fields and SCPA model into a novel self-calibrated pose attention network, more facial prior knowledge can be learned and the detection accuracy and robustness of our method for faces with large poses and heavy occlusions have been improved. The experimental results obtained for challenging benchmark datasets demonstrate that our approach outperforms state-of-the-art methods in the literature., Comment: Accept by IEEE Transactions on Cybernetics, December 2021

Published
2021

18. Short-term Outcomes and Long-term Survival Outcomes of Elderly Patients (Over 80 Years of Age) with Colorectal Cancer Who Received Laparoscopic Versus Open Surgery

Author

MAO Zhengqiang, DU Botao, SUN Hang, GUO Dexing, ZHOU Li, LI Xinyu, and ZAI Shoufeng

Subjects
colorectal cancer, open surgery, laparoscopic surgery, short-term outcomes, prognosis, elderly patients, Neoplasms. Tumors. Oncology. Including cancer and carcinogens, RC254-282
Abstract

Objective To examine short-term outcomes and long-term survival of elderly patients (aged over 80 years) with colorectal cancer who received laparoscopic versus open surgery. Methods A total of 313 patients over 80 years old with colorectal cancer who underwent radical surgery were included.According to the surgical method, all patients were divided into open-surgery group (n=143) and laparoscopic surgery group (n=170).Baseline data were balanced between the two groups by using propensity score matching.Kaplan-Meier was used to draw the survival curve, and survival was compared by Log rank tests.Cox proportional risk model was used to analyze the effects of all factors on overall survival (OS) and disease-free survival (DFS). Results After matching, 93 patients were included in each group.The mean intraoperative blood loss, the incidence of overall postoperative complications and gradeⅠ-Ⅱ complications in the laparoscopic surgery group were significantly lower than those in the open surgery group (all P < 0.05).The time to first flatus, the time to oral feeding, and postoperative hospital stays in the laparoscopic surgery group were significantly shorter than those in the open surgery group (all P < 0.05).The mean number of lymph-node dissection was also significantly higher in the laparoscopic surgery group than in the open surgery group (P=0.030).Patients in both groups had similar 5-year OS (P=0.594) and DFS (P=0.295).Multivariate Cox prognostic analysis showed that CEA level > 5 ng/ml, pathological TNM stage Ⅲ, and perineural invasion were independent risk factors for poor OS and DFS. Conclusion Compared with open surgery, laparoscopic surgery can provide better short-term advantages and similar long-term outcomes for colorectal cancer patients over 80 years of age.

Published
2023
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results