A Unified Framework for Event Summarization and Rare Event Detection from Multiple Views

A novel approach for event summarization and rare event detection is proposed. Unlike conventional methods that deal with event summarization and rare event detection independently, our method solves them in a single framework by transforming them into a graph editing problem. In our approach, a vid...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 37(2015), 9 vom: 14. Sept., Seite 1737-50
1. Verfasser: Kwon, Junseok (VerfasserIn)
Weitere Verfasser: Lee, Kyoung Mu
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2015
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article Research Support, Non-U.S. Gov't
LEADER 01000naa a22002652 4500
001 NLM252590015
003 DE-627
005 20231224164431.0
007 cr uuu---uuuuu
008 231224s2015 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2014.2385695  |2 doi 
028 5 2 |a pubmed24n0842.xml 
035 |a (DE-627)NLM252590015 
035 |a (NLM)26353123 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Kwon, Junseok  |e verfasserin  |4 aut 
245 1 2 |a A Unified Framework for Event Summarization and Rare Event Detection from Multiple Views 
264 1 |c 2015 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Completed 24.11.2015 
500 |a Date Revised 10.09.2015 
500 |a published: Print 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a A novel approach for event summarization and rare event detection is proposed. Unlike conventional methods that deal with event summarization and rare event detection independently, our method solves them in a single framework by transforming them into a graph editing problem. In our approach, a video is represented by a graph, each node of which indicates an event obtained by segmenting the video spatially and temporally. The edges between nodes describe the relationship between events. Based on the degree of relations, edges have different weights. After learning the graph structure, our method finds subgraphs that represent event summarization and rare events in the video by editing the graph, that is, merging its subgraphs or pruning its edges. The graph is edited to minimize a predefined energy model with the Markov Chain Monte Carlo (MCMC) method. The energy model consists of several parameters that represent the causality, frequency, and significance of events. We design a specific energy model that uses these parameters to satisfy each objective of event summarization and rare event detection. The proposed method is extended to obtain event summarization and rare event detection results across multiple videos captured from multiple views. For this purpose, the proposed method independently learns and edits each graph of individual videos for event summarization or rare event detection. Then, the method matches the extracted multiple graphs to each other, and constructs a single composite graph that represents event summarization or rare events from multiple views. Experimental results show that the proposed approach accurately summarizes multiple videos in a fully unsupervised manner. Moreover, the experiments demonstrate that the approach is advantageous in detecting rare transition of events 
650 4 |a Journal Article 
650 4 |a Research Support, Non-U.S. Gov't 
700 1 |a Lee, Kyoung Mu  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 37(2015), 9 vom: 14. Sept., Seite 1737-50  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:37  |g year:2015  |g number:9  |g day:14  |g month:09  |g pages:1737-50 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2014.2385695  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 37  |j 2015  |e 9  |b 14  |c 09  |h 1737-50