scholarly journals Video Summarization via Label Distributions Dual-Reward

2021 ◽  
Author(s):  
Yongbiao Gao ◽  
Ning Xu ◽  
Xin Geng
Keyword(s):  
Reinforcement Learning ◽  
Video Summarization ◽  
Experimental Results ◽  
Average Score ◽  
State Representation ◽  
Benchmark Datasets ◽  
Video Summaries ◽  
Paper Label ◽  
Reward Mechanism ◽  
Score Distributions

Reinforcement learning maps from perceived state representation to actions, which is adopted to solve the video summarization problem. The reward is crucial for deal with the video summarization task via reinforcement learning, since the reward signal defines the goal of video summarization. However, existing reward mechanism in reinforcement learning cannot handle the ambiguity which appears frequently in video summarization, i.e., the diverse consciousness by different people on the same video. To solve this problem, in this paper label distributions are mapped from the CNN and LSTM-based state representation to capture the subjectiveness of video summaries. The dual-reward is designed by measuring the similarity between user score distributions and the generated label distributions. Not only the average score but also the the variance of the subjective opinions are considered in summary generation. Experimental results on several benchmark datasets show that our proposed method outperforms other approaches under various settings.

scholarly journals Deep Reinforcement Learning for Query-Conditioned Video Summarization

2019 ◽  
Vol 9 (4) ◽  
pp. 750 ◽  
Author(s):  
Yujia Zhang ◽  
Michael Kampffmeyer ◽  
Xiaoguang Zhao ◽  
Min Tan
Keyword(s):  
Reinforcement Learning ◽  
Visual Information ◽  
Video Summarization ◽  
Experimental Results ◽  
Learning Approach ◽  
Video Content ◽  
User Interests ◽  
User Query ◽  
Mapping Mechanism

Query-conditioned video summarization requires to (1) find a diverse set of video shots/frames that are representative for the whole video, and that (2) the selected shots/frames are related to a given query. Thus it can be tailored to different user interests leading to a better personalized summary and differs from the generic video summarization which only focuses on video content. Our work targets this query-conditioned video summarization task, by first proposing a Mapping Network (MapNet) in order to express how related a shot is to a given query. MapNet helps establish the relation between the two different modalities (videos and query), which allows mapping of visual information to query space. After that, a deep reinforcement learning-based summarization network (SummNet) is developed to provide personalized summaries by integrating relatedness, representativeness and diversity rewards. These rewards jointly guide the agent to select the most representative and diversity video shots that are most related to the user query. Experimental results on a query-conditioned video summarization benchmark demonstrate the effectiveness of our proposed method, indicating the usefulness of the proposed mapping mechanism as well as the reinforcement learning approach.

Reinforcement Learning for Cloud Computing Digital Library

2014 ◽  
Vol 571-572 ◽  
pp. 105-108
Author(s):  
Lin Xu
Keyword(s):  
Artificial Intelligence ◽  
Cloud Computing ◽  
Reinforcement Learning ◽  
Digital Library ◽  
Learning Algorithms ◽  
Experimental Results ◽  
Current Status ◽  
Self Learning ◽  
New Framework

This paper proposes a new framework of combining reinforcement learning with cloud computing digital library. Unified self-learning algorithms, which includes reinforcement learning, artificial intelligence and etc, have led to many essential advances. Given the current status of highly-available models, analysts urgently desire the deployment of write-ahead logging. In this paper we examine how DNS can be applied to the investigation of superblocks, and introduce the reinforcement learning to improve the quality of current cloud computing digital library. The experimental results show that the method works more efficiency.

scholarly journals Towards High-Level Intrinsic Exploration in Reinforcement Learning

2020 ◽  
Author(s):  
Nicolas Bougie ◽  
Ryutaro Ichise
Keyword(s):  
Reinforcement Learning ◽  
Time Horizon ◽  
State Of The Art ◽  
Experimental Results ◽  
Prior Work ◽  
Extrinsic Rewards ◽  
Intrinsic Reward ◽  
Long Time ◽  
End To End ◽  
High Level

Deep reinforcement learning (DRL) methods traditionally struggle with tasks where environment rewards are sparse or delayed, which entails that exploration remains one of the key challenges of DRL. Instead of solely relying on extrinsic rewards, many state-of-the-art methods use intrinsic curiosity as exploration signal. While they hold promise of better local exploration, discovering global exploration strategies is beyond the reach of current methods. We propose a novel end-to-end intrinsic reward formulation that introduces high-level exploration in reinforcement learning. Our curiosity signal is driven by a fast reward that deals with local exploration and a slow reward that incentivizes long-time horizon exploration strategies. We formulate curiosity as the error in an agent’s ability to reconstruct the observations given their contexts. Experimental results show that this high-level exploration enables our agents to outperform prior work in several Atari games.

Design of diversified teaching platform of college aerobics course based on artificial intelligence

2021 ◽  
pp. 1-13
Author(s):  
Fengping Huang
Keyword(s):  
Artificial Intelligence ◽  
Design Process ◽  
Experimental Results ◽  
Average Score ◽  
Network Teaching ◽  
Teaching Platform ◽  
Student Grouping ◽  
Function Module ◽  
And Function

In order to improve the diversified teaching effect of a college aerobics course, effectively improve the accuracy of student grouping on the teaching platform, a diversified teaching platform of college aerobics course based on artificial intelligence is designed. First of all, it puts forward the construction idea and design process of the network teaching platform, then designs the interface and function module of the teaching platform, and finally designs the grouping function of teaching objects, so as to complete the design of the diversified teaching platform of a college aerobics course based on artificial intelligence. The experimental results show that the grouping accuracy of students on the diversified teaching platform of college aerobics course based on artificial intelligence is greater than 75%, and the average score of students studying on the platform is 74.66. This explains why the designed platform can effectively provide the accuracy of grouping and the students’ performance.

scholarly journals Mobile Robot Wall-Following Control Using Fuzzy Logic Controller with Improved Differential Search and Reinforcement Learning

Mathematics ◽  
2020 ◽  
Vol 8 (8) ◽  
pp. 1254 ◽  
Author(s):  
Cheng-Hung Chen ◽  
Shiou-Yun Jeng ◽  
Cheng-Jian Lin
Keyword(s):  
Fuzzy Logic ◽  
Reinforcement Learning ◽  
Mobile Robot ◽  
Fuzzy Logic Controller ◽  
Search Algorithm ◽  
Experimental Results ◽  
Average Error ◽  
Stopover Site ◽  
Accumulated Reward ◽  
Wall Following

In this study, a fuzzy logic controller with the reinforcement improved differential search algorithm (FLC_R-IDS) is proposed for solving a mobile robot wall-following control problem. This study uses the reward and punishment mechanisms of reinforcement learning to train the mobile robot wall-following control. The proposed improved differential search algorithm uses parameter adaptation to adjust the control parameters. To improve the exploration of the algorithm, a change in the number of superorganisms is required as it involves a stopover site. This study uses reinforcement learning to guide the behavior of the robot. When the mobile robot satisfies three reward conditions, it gets reward +1. The accumulated reward value is used to evaluate the controller and to replace the next controller training. Experimental results show that, compared with the traditional differential search algorithm and the chaos differential search algorithm, the average error value of the proposed FLC_R-IDS in the three experimental environments is reduced by 12.44%, 22.54% and 25.98%, respectively. Final, the experimental results also show that the real mobile robot using the proposed method can effectively implement the wall-following control.

Sign in / Sign up

Export Citation Format

Share Document