Modeling Video Evolution For Action Recognition

被引：0

作者：

Fernando, Basura ^{[1
]}

Gavves, Efstratios ^{[1
]}

Oramas, Jose M. ^{[1
]}

Ghodrati, Amir ^{[1
]}

Tuytelaars, Tinne ^{[1
]}

机构：

[1] Katholieke Univ Leuven, ESAT, PSI, iMinds, Leuven, Belgium

来源：

2015 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) | 2015年

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper we present a method to capture video-wide temporal information for action recognition. We postulate that a function capable of ordering the frames of a video temporally (based on the appearance) captures well the evolution of the appearance within the video. We learn such ranking functions per video via a ranking machine and use the parameters of these as a new video representation. The proposed method is easy to interpret and implement, fast to compute and effective in recognizing a wide variety of actions. We perform a large number of evaluations on datasets for generic action recognition (Hollywood2 and HMDB51), fine-grained actions (MPII-cooking activities) and gestures (Chalearn). Results show that the proposed method brings an absolute improvement of 7-10%, while being compatible with and complementary to further improvements in appearance and local motion based methods.

引用

页码：5378 / 5387

页数：10