Modelling perceptions on the evaluation of video summarization

被引：2

作者：

Abdalla, Kalyf ^{[1
,2
]}

Menezes, Igor ^{[3
]}

Oliveira, Luciano ^{[1
]}

机构：

[1] Univ Fed Bahia, Intelligent Vis Res Lab, Salvador, BA, Brazil

[2] Fed Inst Bahia, Salvador, BA, Brazil

[3] Univ Hull, Kingston Upon Hull, N Humberside, England

来源：

EXPERT SYSTEMS WITH APPLICATIONS | 2019年 / 131卷

关键词：

Video summarization; Subjective evaluation; Evaluation metric; SHOT-BOUNDARY DETECTION; RETRIEVAL;

D O I：

10.1016/j.eswa.2019.04.065

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Hours of video are uploaded to streaming platforms every minute, with recommender systems suggesting popular and relevant videos that can help users save time in the searching process. Recommender systems regularly require video summarization as an expert system to automatically identify suitable video entities and events. Since there is no well-established methodology to evaluate the relevance of summarized videos, some studies have made use of user annotations to gather evidence about the effectiveness of summarization methods. Aimed at modelling the user's perceptions, which ultimately form the basis for testing video summarization systems, this paper seeks to propose: (i) A guideline to collect unrestricted user annotations, (ii) a novel metric called compression level of user annotation (CLUSA) to gauge the performance of video summarization methods, and (iii) a study on the quality of annotated video summaries collected from different assessment scales. These contributions lead to benchmarking video summarization methods with no constraints, even if user annotations are collected from different assessment scales for each method. Our experiments showed that CLUSA is less susceptible to unbalanced compression data sets in comparison to other metrics, hence achieving higher reliability estimates. CLUSA also allows to compare results from different video summarizing approaches. (C) 2019 Elsevier Ltd. All rights reserved.

引用

页码：254 / 265

页数：12

共 40 条

[11]

Gygli M, 2015, PROC CVPR IEEE, P3090, DOI 10.1109/CVPR.2015.7298928

[12] Creating Summaries from User Videos [J].

Gygli, Michael ;

Grabner, Helmut ;

Riemenschneider, Hayko ;

Van Gool, Luc .

COMPUTER VISION - ECCV 2014, PT VII, 2014, 8695 :505-520

[13] Shot-boundary detection: Unraveled and resolved? [J].

Hanjalic, A .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2002, 12 (02) :90-105

[14] Auto-summarization of audio-video presentations [J].

He, LW ;

Sanocki, E ;

Gupta, A ;

Grudin, J .

ACM MULTIMEDIA 99, PROCEEDINGS, 1999, :489-498

[15] Joint Summarization of Large-scale Collections of Web Images and Videos for Storyline Reconstruction [J].

Kim, Gunhee ;

Sigal, Leonid ;

Xing, Eric P. .

2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2014, :4225-4232

[16]

Lee YJ, 2012, PROC CVPR IEEE, P1346, DOI 10.1109/CVPR.2012.6247820

[17] An efficient error-minimizing algorithm for variable-rate temporal video sampling [J].

Liu, T ;

Kender, JR .

IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, VOL I AND II, PROCEEDINGS, 2002, :413-416

[18] A novel video key-frame-extraction algorithm based on perceived motion energy model [J].

Liu, TM ;

Zhang, HJ ;

Qi, FH .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2003, 13 (10) :1006-1013

[19]

Liu W, 2015, PROC CVPR IEEE, P3707, DOI 10.1109/CVPR.2015.7298994

[20] Automatic video summarization by graph modeling [J].

Ngo, CW ;

Ma, YF ;

Zhang, HJ .

NINTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOLS I AND II, PROCEEDINGS, 2003, :104-109

← 1 2 3 4 →