• 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:

EI Scopus SCIE

Abstract:

Action prediction based on partially observed videos is challenging as the information provided by partial videos is not discriminative enough for classification. 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 whole framework performs as a teacher-student network, where the teacher network supports the complete video feature supervision to the student network to capture the salient differences between partial videos and their corresponding complete videos based on the residual feature learning. The teacher and student network are trained simultaneously, and the technique called partial feature detach is employed to prevent the teacher network from disturbing by the student network. We also design a novel weighted loss function to give less penalization to partial videos that have small observation ratios. Extensive evaluations on the challenging UCF101 and HMDB51 datasets demonstrate that the proposed method outperforms state-of-the-art results without knowing the observation ratios of testing videos. The code will be publicly available soon.

Keyword:

Action recognition Action prediction Teacher-student network Deep residual feature learning

Author Community:

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

Reprint Author's Address:

  • 段立娟

    [Duan, Lijuan]Beijing Univ Technol, Fac Informat Technol, Beijing, Peoples R China

Show more details

Related Keywords:

Related Article:

Source :

MULTIMEDIA TOOLS AND APPLICATIONS

ISSN: 1380-7501

Year: 2020

Issue: 7-8

Volume: 79

Page: 4713-4727

3 . 6 0 0

JCR@2022

ESI Discipline: COMPUTER SCIENCE;

ESI HC Threshold:132

Cited Count:

WoS CC Cited Count: 3

SCOPUS Cited Count: 3

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 1

Affiliated Colleges:

Online/Total:847/5323956
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.