Rebuilding Visual Vocabulary via Spatial-temporal Context Similarity for Video Retrieval

Author(s):  
Lei Wang ◽  
Eyad Elyan ◽  
Dawei Song
2021 ◽  
Author(s):  
Lynn J Lohnas ◽  
Karl Healey ◽  
Lila Davachi

Although life unfolds continuously, experiences are generally perceived and remembered as discrete events. Accumulating evidence suggests that event boundaries disrupt temporal representations and weaken memory associations. However, less is known about the consequences of event boundaries on temporal representations during retrieval, especially when temporal information is not tested explicitly. Using a neural measure of temporal context extracted from scalp electroencephalography, we found reduced temporal context similarity between studied items separated by an event boundary when compared to items from the same event. Further, while participants free recalled list items, neural activity reflected reinstatement of temporal context representations from study, including temporal disruption. A computational model of episodic memory, the Context Maintenance and Retrieval model (CMR; Polyn, Norman & Kahana, 2009), predicted these results, and made novel predictions regarding the influence of temporal disruption on recall order. These findings implicate the impact of event structure on memory organization via temporal representations.


2008 ◽  
pp. 527-546
Author(s):  
A. Mittal ◽  
Cheong Loong Fah ◽  
Ashraf Kassim ◽  
Krishnan V. Pagalthivarthi

Most of the video retrieval systems work with a single shot without considering the temporal context in which the shot appears. However, the meaning of a shot depends on the context in which it is situated and a change in the order of the shots within a scene changes the meaning of the shot. Recently, it has been shown that to find higher-level interpretations of a collection of shots (i.e., a sequence), intershot analysis is at least as important as intrashot analysis. Several such interpretations would be impossible without a context. Contextual characterization of video data involves extracting patterns in the temporal behavior of features of video and mapping these patterns to a high-level interpretation. A Dynamic Bayesian Network (DBN) framework is designed with the temporal context of a segment of a video considered at different granularity depending on the desired application. The novel applications of the system include classifying a group of shots called sequence and parsing a video program into individual segments by building a model of the video program.


2017 ◽  
Vol 77 (2) ◽  
pp. 2057-2081 ◽  
Author(s):  
Lelin Zhang ◽  
Zhiyong Wang ◽  
Tingting Yao ◽  
Shin’ichi Staoh ◽  
Tao Mei ◽  
...  

Author(s):  
Ankush Mittal ◽  
Cheong Loong Fah ◽  
Ashraf Kassim ◽  
Krishnan V. Pagalthivarthi

Most of the video retrieval systems work with a single shot without considering the temporal context in which the shot appears. However, the meaning of a shot depends on the context in which it is situated and a change in the order of the shots within a scene changes the meaning of the shot. Recently, it has been shown that to find higher-level interpretations of a collection of shots (i.e., a sequence), intershot analysis is at least as important as intrashot analysis. Several such interpretations would be impossible without a context. Contextual characterization of video data involves extracting patterns in the temporal behavior of features of video and mapping these patterns to a high-level interpretation. A Dynamic Bayesian Network (DBN) framework is designed with the temporal context of a segment of a video considered at different granularity depending on the desired application. The novel applications of the system include classifying a group of shots called sequence and parsing a video program into individual segments by building a model of the video program.


Author(s):  
Daragh Byrne ◽  
Peter Wilkins ◽  
Gareth J.F. Jones ◽  
Alan F. Smeaton ◽  
Noel E. O'Connor

2007 ◽  
Author(s):  
Sean M. Polyn ◽  
Kenneth A. Norman ◽  
Michael J. Kahana

2013 ◽  
Author(s):  
Jeffrey D. Karpicke ◽  
Melissa Lehman
Keyword(s):  

Sign in / Sign up

Export Citation Format

Share Document