Yunan Ye
Zhejiang University
7 Papers
3 Citations
Yunan Ye is an academic researcher from Zhejiang University. The author has contributed to research in topics: Question answering & Computer science. The author has an hindex of 4, co-authored 7 publications.
Chat about Author
Papers
Reinforcement-learning based portfolio management with augmented asset movement prediction states
Yunan Ye,Hengzhi Pei,Boxin Wang,Pin-Yu Chen,Yada Zhu,Jun Xiao,Bo Li +6 more
- 03 Apr 2020
TL;DR: Li et al. as mentioned in this paper proposed a state-augmented RL framework for portfolio management, which augments the asset information with their price movement prediction as additional states, where the prediction can be solely based on financial data (e.g., asset prices) or derived from alternative sources such as news.
Video Question Answering via Attribute-Augmented Attention Network Learning
TL;DR: In this article, an attribute-augmented attention network learning framework is proposed to model the temporal dynamics of video content with frame-level attention mechanism. But the model is not suitable for video question answering.
87
Hierarchical Temporal Fusion of Multi-grained Attention Features for Video Question Answering
TL;DR: This work proposes the multi-granularity temporal attention network that enables to search for the specific frames in a video that are holistically and locally related to the answer.
9
Video question answering via multi-granularity temporal attention network learning
Shaoning Xiao,Yimeng Li,Yunan Ye,Zhou Zhao,Jun Xiao,Fei Wu,Jiang Zhu,Yueting Zhuang +7 more
- 17 Aug 2018
TL;DR: This work proposes the multi-granularity temporal attention network (MGTA-Net) that enables to search for the specific frames in a video that are holistically and locally related to the answer.
3
•Posted Content
Reinforcement-Learning based Portfolio Management with Augmented Asset Movement Prediction States
TL;DR: Experiments on two real-world datasets validate the effectiveness of SARL over existing PM approaches, both in terms of accumulated profits and risk-adjusted profits and extensive simulations are conducted to demonstrate the importance of the proposed state augmentation.