Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

A REAL-TIME MULTI-LABEL CLASSIFICATION SYSTEM FOR SHORT VIDEOS

Abstract: 

Efficient classification of short videos is of a great challenge in industry due to their large amounts and diverse semantics. In this paper, we present a real-time multi-label classification system to attain it. Specifically, a frame-level preprocessing strategy is first proposed to efficiently decode the videos for useful information. Then an image-based model is developed to achieve the final video-level classification. For the multi-label classification case, three modules are proposed to enhance the model's classification capability, relieve the label-imbalance issue and exploit the label correlation respectively. Our system achieves an accuracy of 86% on both private test sets of the challenge ``Short Video Real-time Classification'' in AI Challenger 2018, and on its open validation set it achieves an accuracy of 89.2% with a speed of 28ms per video on a workstation with an Intel Xeon CPU E5-2650 and a NVIDIA GPU TITAN Xp.

up
0 users have voted:

Paper Details

Authors:
Bo Jiang, Lei Zhou, Li Lin, Binbin Xu, Jiahong Yu, Xuping Zheng, Kailin Wu
Submitted On:
18 September 2019 - 2:02am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Jiahong Yu, Kailin Wu
Paper Code:
1312
Document Year:
2019
Cite

Document Files

a real-time multi-label classification system for short videos

(13)

Subscribe

[1] Bo Jiang, Lei Zhou, Li Lin, Binbin Xu, Jiahong Yu, Xuping Zheng, Kailin Wu, "A REAL-TIME MULTI-LABEL CLASSIFICATION SYSTEM FOR SHORT VIDEOS", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4664. Accessed: Oct. 20, 2019.
@article{4664-19,
url = {http://sigport.org/4664},
author = {Bo Jiang; Lei Zhou; Li Lin; Binbin Xu; Jiahong Yu; Xuping Zheng; Kailin Wu },
publisher = {IEEE SigPort},
title = {A REAL-TIME MULTI-LABEL CLASSIFICATION SYSTEM FOR SHORT VIDEOS},
year = {2019} }
TY - EJOUR
T1 - A REAL-TIME MULTI-LABEL CLASSIFICATION SYSTEM FOR SHORT VIDEOS
AU - Bo Jiang; Lei Zhou; Li Lin; Binbin Xu; Jiahong Yu; Xuping Zheng; Kailin Wu
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4664
ER -
Bo Jiang, Lei Zhou, Li Lin, Binbin Xu, Jiahong Yu, Xuping Zheng, Kailin Wu. (2019). A REAL-TIME MULTI-LABEL CLASSIFICATION SYSTEM FOR SHORT VIDEOS. IEEE SigPort. http://sigport.org/4664
Bo Jiang, Lei Zhou, Li Lin, Binbin Xu, Jiahong Yu, Xuping Zheng, Kailin Wu, 2019. A REAL-TIME MULTI-LABEL CLASSIFICATION SYSTEM FOR SHORT VIDEOS. Available at: http://sigport.org/4664.
Bo Jiang, Lei Zhou, Li Lin, Binbin Xu, Jiahong Yu, Xuping Zheng, Kailin Wu. (2019). "A REAL-TIME MULTI-LABEL CLASSIFICATION SYSTEM FOR SHORT VIDEOS." Web.
1. Bo Jiang, Lei Zhou, Li Lin, Binbin Xu, Jiahong Yu, Xuping Zheng, Kailin Wu. A REAL-TIME MULTI-LABEL CLASSIFICATION SYSTEM FOR SHORT VIDEOS [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4664