Format

Send to

Choose Destination
  • PMID: 27705858 was deleted because it is a duplicate of PMID: 28113970
IEEE Trans Image Process. 2017 Jan;26(1):196-207. doi: 10.1109/TIP.2016.2612825. Epub 2016 Sep 22.

LEGO-MM: LEarning Structured Model by Probabilistic loGic Ontology Tree for MultiMedia.

Abstract

Recent advances in multimedia ontology have resulted in a number of concept models, e.g., large-scale concept for multimedia and Mediamill 101, which are accessible and public to other researchers. However, most current research effort still focuses on building new concepts from scratch, very few work explores the appropriate method to construct new concepts upon the existing models already in the warehouse. To address this issue, we propose a new framework in this paper, termed LEarning Structured Model by Probabilistic loGic Ontology Tree for MultiM edia (LEGO 1 -MM), which can seamlessly integrate both the new target training examples and the existing primitive concept models to infer the more complex concept models. LEGO-MM treats the primitive concept models as the lego toy to potentially construct an unlimited vocabulary of new concepts. Specifically, we first formulate the logic operations to be the lego connectors to combine the existing concept models hierarchically in probabilistic logic ontology trees. Then, we incorporate new target training information simultaneously to efficiently disambiguate the underlying logic tree and correct the error propagation. Extensive experiments are conducted on a large vehicle domain data set from ImageNet. The results demonstrate that LEGO-MM has significantly superior performance over the existing state-of-the-art methods, which build new concept models from scratch.

PMID:
28113970
DOI:
10.1109/TIP.2016.2612825

Supplemental Content

Loading ...
Support Center