.png){kind=icon}
返回
A novel learning-based frame pooling method for event detection
.png){kind=icon}
OA
AI
DOI：10.1016/j.sigpro.2017.05.005.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Detecting complex events in a large video collection crawled from video websites is a challenging task. When applying directly good image-based feature representation, e.g., HOG, SIFT, to videos, we have to face the problem of how to pool multiple frame feature representations into one feature representation. In this paper, we propose a novel learning-based frame pooling method. We formulate the pooling weight learning as an optimization problem and thus our method can automatically learn the best pooling weight configuration for each specific event category. Extensive experimental results conducted on TRECVID MED 2011 reveal that our method outperforms the commonly used average pooling and max pooling strategies on both high-level and low-level features. (C) 2017 Elsevier B.V. All rights reserved.
Keyword:
Optimal pooling
Event detection
Feature representation
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.6
论文数:
9.9K
被引数:
1.7W
机构
引用论文
Multi-task human action recognition via exploring super-category基于超类探索的多任务人体动作识别.png)
SIGNAL PROCESSING
SIGNAL PROCESSINGIF3.6
PREAI
分享收藏分享收藏Coupled hidden conditional random fields for RGB-D human action recognitionSIGNAL PROCESSING
SIGNAL PROCESSINGIF3.6
PREAI
分享收藏 没有更多内容
没有更多内容