Proceedings Article10.1109/ICIP.2007.4379128
A Generalized Multiple Instance Learning Algorithm for Iterative Distillation and Cross-Granular Propagation of Video Annotations
Feng Kang,Milind Naphade +1 more
- 12 Nov 2007
- Vol. 2, pp 205-208
TL;DR: A new generalized multiple instance learning algorithm that can work with any underlying density modeling techniques, and help propagate semantic concepts provided at the coarse granularity of video key-frames to finer grained regions.
read more
Abstract: Video annotation is an expensive but necessary task for most vision and learning problems that require building models of visual semantics. This annotation gets prohibitively expensive especially when annotation has to happen at finer grained levels of regions in the videos. One way around the finer grained annotation dilemma is to support annotation at coarser granularity and then propagate this annotation to the finer granularity in a concept-dependent way. In this paper we propose a new generalized multiple instance learning algorithm that can work with any underlying density modeling techniques, and help propagate semantic concepts provided at the coarse granularity of video key-frames to finer grained regions. Our experiments on the NIST TRECVID common annotation corpus reveal improvement in annotation propagation accuracy between 3% to a dramatic 161%.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
A Mechanism for Propagation of Semantic Annotations of Multimedia Content
TL;DR: Techniques for structuring and propagating annotations, in parallel to the data transformation processes, thereby alleviating the overhead and decreasing the errors introduced by manual annotation are introduced.
10
References
Bagging predictors
Leo Breiman
- 01 Aug 1996
TL;DR: Tests on real and simulated data sets using classification and regression trees and subset selection in linear regression show that bagging can give substantial gains in accuracy.
•Proceedings Article
Multiple-Instance Learning for Natural Scene Classification
Oded Maron,Aparna Lakshmi Ratan +1 more
- 24 Jul 1998
TL;DR: It is shown that very simple templates are suu-cient, and that performance improves with more user interaction, and the Diverse Density algorithm which is a method of learning from ambiguous examples is discussed.
673
Pruning training sets for learning of object categories
Anelia Angelova,Y. Abu-Mostafam,Pietro Perona +2 more
- 20 Jun 2005
TL;DR: This work proposes a fully automatic mechanism for noise cleaning, called 'data pruning', and demonstrates its success on learning of human faces and shows that data pruning can improve on generalization performance for algorithms with various robustness to noise.
A framework for learning query concepts in image classification
A.L. Ratan,Oded Maron,W.E.L. Grimson,Tomás Lozano-Pérez +3 more
- 23 Jun 1999
TL;DR: The bag generator is extended to generate more complex instances using multiple cues on segmented high resolution images and it is shown that this method can be used to learn certain object class concepts in addition, to natural scenes.
A generalized multiple instance learning algorithm for large scale modeling of multimedia semantics
Milind Naphade,John R. Smith +1 more
- 18 Mar 2005
TL;DR: This work presents a novel approach where the annotations may be entered at coarser spatial granularity while the concept may still be learnt at finer granularity, which can speed up annotation significantly.
14