期刊论文、会议论文

Qiao, Yu

英文

Lecture Notes in Computer Science

0302-9743

2014

8693 LNCS

PART 5

581-595

13th European Conference on Computer Vision, ECCV 2014

Lecture Notes in Computer Science

6 September 2014 through 12 September 2014

Zurich

[Peng, Xiaojiang;Zou, Changqing;Qiao, Yu] Chinese Acad Sci, Shenzhen Inst Adv Technol, Shenzhen Key Lab CVPR, Shenzhen, Peoples R China.^[Peng, Xiaojiang] Southwest Jiaotong Univ, Chengdu, Peoples R China.^[Peng, Xiaojiang;Zou, Changqing] Hengyang Normal Univ, Dept Comp Sci, Hengyang, Peoples R China.^[Qiao, Yu] Chinese Univ Hong Kong, Hong Kong, Hong Kong, Peoples R China.

Fleet, D Pajdla, T Schiele, B Tuytelaars, T

GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND

Springer Verlag

978-3-319-10602-1; 978-3-319-10601-4

10.1007/978-3-319-10602-1_38

Natural Science Foundation of ChinaNational Natural Science Foundation of China (NSFC) [91320101, 61036008, 60972111]; Shenzhen Basic Research Program [JC201005270350A, JCYJ20120903092050890, JCYJ20120617114614438]; Talents Program of CAS, Guangdong Innovative Research Team Program [201001D0104648280]

本校为其他机构

Representation of video is a vital problem in action recognition. This paper proposes Stacked Fisher Vectors (SFV), a new representation with multi-layer nested Fisher vector encoding, for action recognition. In the first layer, we densely sample large subvolumes from input videos, extract local features, and encode them using Fisher vectors (FVs). The second layer compresses the FVs of subvolumes obtained in previous layer, and then encodes them again with Fisher vectors. Compared with standard FV, SFV allows refining the representation and ab...