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

Jinhui Tang, Shiyu Chang, Guo-Jun Qi, Qi Tian, Yong Rui, Thomas S. Huang
2017 IEEE Transactions on Image Processing  
Recent advances in Multimedia ontology have resulted in a number of concept models, e.g., LSCOM 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 LEGO 1 -MM, which can seamlessly integrate
more » ... th 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 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 existing state-of-the-art methods, which build new concept models from scratch. Index Terms-LEGO-MM, Concept recycling, Model warehouse, Probabilistic logic ontology tree, Logical operations.
doi:10.1109/tip.2016.2612825 pmid:28113970 fatcat:sqfkjdpcgzeu3eyza74zt2o3se