LEGO-MM: LEarning Structured Model by Probabilistic loGic Ontology Tree for MultiMedia.
LEGO-MM: LEarning Structured Model by Probabilistic loGic Ontology Tree for MultiMedia.
复制标题
DOI：
10.1109/tip.2016.2612825
复制
发表时间：
2017-01
期刊：
影响因子：
--
通讯作者：
Jinhui Tang;Shiyu Chang;Guo-jun Qi;Qi Tian;Yong Rui;Thomas S. Huang
中科院分区：
文献类型：
--
作者：
Jinhui Tang;Shiyu Chang;Guo-jun Qi;Qi Tian;Yong Rui;Thomas S. Huang
多媒体本体的最新进展已经产生了许多概念模型，例如，多媒体和Mediamill 101的大规模概念，可供其他研究人员访问和公开。然而，目前大多数的研究工作仍然集中在从头开始构建新的概念，很少有工作探索适当的方法来构建新的概念，在现有的模型已经在仓库中。为了解决这个问题，我们提出了一个新的框架，在本文中，称为学习结构化模型的概率本体树多媒体（LEGO 1 -MM），它可以无缝地集成新的目标训练的例子和现有的原始概念模型，以推断更复杂的概念模型。LEGO-MM将原始概念模型视为乐高玩具，以潜在地构建新概念的无限词汇表。具体来说，我们首先制定的逻辑操作是乐高连接器联合收割机结合现有的概念模型层次的概率逻辑本体树。然后，我们同时结合新的目标训练信息，以有效地消除底层逻辑树的歧义并纠正错误传播。在ImageNet的大型车辆域数据集上进行了广泛的实验。结果表明，LEGO-MM具有显着优于现有的国家的最先进的方法，从头开始建立新的概念模型的上级性能。
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.