Search

Your search keyword '"Chen, Yiyan"' showing total 236 results
Start Over Author "Chen, Yiyan"
236 results on '"Chen, Yiyan"'

9. Weakly Supervised Video Summarization by Hierarchical Reinforcement Learning

Author

Chen, Yiyan, Tao, Li, Wang, Xueting, and Yamasaki, Toshihiko

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning, Computer Science - Multimedia
Abstract

Conventional video summarization approaches based on reinforcement learning have the problem that the reward can only be received after the whole summary is generated. Such kind of reward is sparse and it makes reinforcement learning hard to converge. Another problem is that labelling each frame is tedious and costly, which usually prohibits the construction of large-scale datasets. To solve these problems, we propose a weakly supervised hierarchical reinforcement learning framework, which decomposes the whole task into several subtasks to enhance the summarization quality. This framework consists of a manager network and a worker network. For each subtask, the manager is trained to set a subgoal only by a task-level binary label, which requires much fewer labels than conventional approaches. With the guide of the subgoal, the worker predicts the importance scores for video frames in the subtask by policy gradient according to both global reward and innovative defined sub-rewards to overcome the sparse problem. Experiments on two benchmark datasets show that our proposal has achieved the best performance, even better than supervised approaches., Comment: mmasia 2019 accepted

Published
2020

16. Conclusion

Author

Chen, Yiyan, primary, Hooi Lean, Hooi, additional, and Li, Ye, additional

Published
2023
Full Text
View/download PDF

22. Influence of Oil Injection Lubrication Parameters of High-Speed Internal Meshing Gear Based on the Computational Fluid Dynamics.

Author

Tang, Peixun, Li, Zhengminqing, Hou, Xiangying, Li, Letian, Xi, Rongsheng, and Chen, Yiyan

Subjects
COMPUTATIONAL fluid dynamics, MODEL airplanes, DYNAMICAL systems, GEARBOXES, PETROLEUM
Abstract

High-speed gears are crucial transmission components found in airplanes and other systems, and they are maintained primarily through oil injection. However, due to their high operating speeds and the influence of oil injection settings, gear surface lubrication efficacy is frequently insufficient, compromising the transmission system's precision, durability, and safety. Currently, the parameter choices for oil injection in high-speed gears mostly rely on empirical judgment, which results in significant time and resource expenses. This study focuses on one pair of internal meshing gears within a specific aircraft gearbox, establishing an oil injection lubrication model for high-speed internal meshing gears using the computational fluid dynamics (CFD) approach. This research provides insights and references for optimizing oil injection parameters and improving lubrication efficiency in high-speed internal meshing gear systems by examining the dynamic characteristics of internal meshing wind resistance in addition to the effects of injection tube position, angle, and speed on lubrication performance. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

23. Static Scheduling of Weight Programming for DNN Acceleration with Resource Constrained PIM.

Author

Gao, Xin, Wang, Hongyue, Chen, Yiyan, Zhang, Yuhao, Shen, Zhaoyan, and Ju, Lei

Subjects
SCHEDULING, COST
Abstract

Most existing architectural studies on ReRAM-based processing-in-memory (PIM) DNN accelerators assume that all weights of the DNN can be mapped to the crossbar at once. However, these studies are over-idealized. ReRAM crossbar resources for calculation are limited because of technological limitations, so multiple weight mapping procedures are required during the inference process. In this article, we propose a static scheduling framework which generates the mapping between DNN weights and ReRAM cells with minimum runtime weight programming cost. We first build a ReRAM crossbar programming latency model by simultaneously considering the DNN weight patterns, ReRAM programming operations, and PIM architecture characteristics. Then, the model is used in the searching process to obtain an optimized weight-to-OU mapping table with minimum online programming latency. Finally, an OU scheduler is used to coordinate the activation sequences of OUs in the crossbars to perform the inference computation correctly. Evaluation results show the proposed framework significantly reduces the weight programming overhead and the overall inference latency for various DNN models with different input datasets. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

24. Study on Key Elements of Shopping App Design for the Elderly

Author

Liu, Wenfeng, Wang, Fenghong, Chen, Yiyan, Kacprzyk, Janusz, Series Editor, Pal, Nikhil R., Advisory Editor, Bello Perez, Rafael, Advisory Editor, Corchado, Emilio S., Advisory Editor, Hagras, Hani, Advisory Editor, Kóczy, László T., Advisory Editor, Kreinovich, Vladik, Advisory Editor, Lin, Chin-Teng, Advisory Editor, Lu, Jie, Advisory Editor, Melin, Patricia, Advisory Editor, Nedjah, Nadia, Advisory Editor, Nguyen, Ngoc Thanh, Advisory Editor, Wang, Jun, Advisory Editor, Ahram, Tareq, editor, Karwowski, Waldemar, editor, Vergnano, Alberto, editor, Leali, Francesco, editor, and Taiar, Redha, editor

Published
2020
Full Text
View/download PDF

38. Syntactic and Semantic Features Based Relation Extraction in Agriculture Domain

Author

Liu, Zhanghui, Chen, Yiyan, Dai, Yuanfei, Guo, Chenhao, Zhang, Zuwen, Chen, Xing, Hutchison, David, Series Editor, Kanade, Takeo, Series Editor, Kittler, Josef, Series Editor, Kleinberg, Jon M., Series Editor, Mattern, Friedemann, Series Editor, Mitchell, John C., Series Editor, Naor, Moni, Series Editor, Pandu Rangan, C., Series Editor, Steffen, Bernhard, Series Editor, Terzopoulos, Demetri, Series Editor, Tygar, Doug, Series Editor, Meng, Xiaofeng, editor, Li, Ruixuan, editor, Wang, Kanliang, editor, Niu, Baoning, editor, Wang, Xin, editor, and Zhao, Gansen, editor

Published
2018
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results