• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
搜索

Author:

Guo, Shuangshuang (Guo, Shuangshuang.) | Qing, Laiyun (Qing, Laiyun.) | Miao, Jun (Miao, Jun.) | Duan, Lijuan (Duan, Lijuan.) (Scholars:段立娟)

Indexed by:

CPCI-S

Abstract:

Though action recognition based on complete videos has achieved great success recently, action prediction remains a challenging task as the information provided by partial videos is not discriminative enough for classifying actions. In this paper, we propose a Deep Residual Feature Learning (DeepRFL) framework to explore more discriminative information from partial videos, achieving similar representations as those of complete videos. The proposed method is based on residual learning, which captures the salient differences between partial videos and their corresponding full videos. The partial videos can attain the missing information by learning from features of complete videos and thus improve the discriminative power. Moreover, our model can be trained efficiently in an end-to-end fashion. Extensive evaluations on the challenging UCF101 and HMDB51 datasets demonstrate that the proposed method outperforms state-of-the-art results.

Keyword:

Action Recognition Deep Residual Feature Learning Action Prediction

Author Community:

  • [ 1 ] [Guo, Shuangshuang]Univ Chinese Acad Sci, Sch Comp & Control Engn, Beijing, Peoples R China
  • [ 2 ] [Qing, Laiyun]Univ Chinese Acad Sci, Sch Comp & Control Engn, Beijing, Peoples R China
  • [ 3 ] [Miao, Jun]Beijing Informat Sci & Technol Univ, Beijing Key Lab Internet Culture & Digital Dissem, Sch Comp Sci, Beijing, Peoples R China
  • [ 4 ] [Duan, Lijuan]Beijing Univ Technol, Fac Informat Technol, Beijing, Peoples R China

Reprint Author's Address:

  • [Guo, Shuangshuang]Univ Chinese Acad Sci, Sch Comp & Control Engn, Beijing, Peoples R China

Show more details

Related Keywords:

Related Article:

Source :

2018 IEEE FOURTH INTERNATIONAL CONFERENCE ON MULTIMEDIA BIG DATA (BIGMM)

Year: 2018

Language: English

Cited Count:

WoS CC Cited Count: 0

SCOPUS Cited Count:

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 1

Affiliated Colleges:

Online/Total:689/5336075
Address:BJUT Library(100 Pingleyuan,Chaoyang District,Beijing 100124, China Post Code:100124) Contact Us:010-67392185
Copyright:BJUT Library Technical Support:Beijing Aegean Software Co., Ltd.