Please use this identifier to cite or link to this item: https://doi.org/10.1109/TPAMI.2010.31
Title: A Hierarchical visual model for video object summarization
Authors: Liu D.
Hua G.
Chen T. 
Keywords: Multiple Instance Learning
object detection
probabilistic graphical model
semi-supervised learning
Topic model
video object summarization
Issue Date: 2010
Citation: Liu D., Hua G., Chen T. (2010). A Hierarchical visual model for video object summarization. IEEE Transactions on Pattern Analysis and Machine Intelligence 32 (12) : 2178-2190. ScholarBank@NUS Repository. https://doi.org/10.1109/TPAMI.2010.31
Abstract: We propose a novel method for removing irrelevant frames from a video given user-provided frame-level labeling for a very small number of frames. We first hypothesize a number of windows which possibly contain the object of interest, and then determine which window(s) truly contain the object of interest. Our method enjoys several favorable properties. First, compared to approaches where a single descriptor is used to describe a whole frame, each window's feature descriptor has the chance of genuinely describing the object of interest; hence it is less affected by background clutter. Second, by considering the temporal continuity of a video instead of treating frames as independent, we can hypothesize the location of the windows more accurately. Third, by infusing prior knowledge into the patch-level model, we can precisely follow the trajectory of the object of interest. This allows us to largely reduce the number of windows and hence reduce the chance of overfitting the data during learning. We demonstrate the effectiveness of the method by comparing it to several other semi-supervised learning approaches on challenging video clips.
Source Title: IEEE Transactions on Pattern Analysis and Machine Intelligence
URI: http://scholarbank.nus.edu.sg/handle/10635/146175
ISSN: 01628828
DOI: 10.1109/TPAMI.2010.31
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

88
checked on Oct 12, 2021

WEB OF SCIENCETM
Citations

44
checked on Dec 31, 2018

Page view(s)

38
checked on Oct 14, 2021

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.