Learning Contextualized Semantics from Co-occurring Terms via a Siamese Architecture

@article{Sandouk2016LearningCS,
  title={Learning Contextualized Semantics from Co-occurring Terms via a Siamese Architecture},
  author={Ubai Sandouk and Ke Chen},
  journal={Neural networks : the official journal of the International Neural Network Society},
  year={2016},
  volume={76},
  pages={
          65-96
        }
}
  • Ubai Sandouk, Ke Chen
  • Published 2016
  • Computer Science, Medicine
  • Neural networks : the official journal of the International Neural Network Society
  • One of the biggest challenges in Multimedia information retrieval and understanding is to bridge the semantic gap by properly modeling concept semantics in context. The presence of out of vocabulary (OOV) concepts exacerbates this difficulty. To address the semantic gap issues, we formulate a problem on learning contextualized semantics from descriptive terms and propose a novel Siamese architecture to model the contextualized semantics from descriptive terms. By means of pattern aggregation… CONTINUE READING
    Learning Contextualized Music Semantics from Tags via a Siamese Network
    1
    Multi-Label Zero-Shot Learning via Concept Embedding
    15
    Inductive Zero-Shot Image Annotation via Embedding Graph
    1
    Multi-Label Zero-Shot Human Action Recognition via Joint Latent Embedding
    7

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 76 REFERENCES
    A Generative Context Model for Semantic Music Annotation and Retrieval
    40
    Evaluating similarity measures for emergent semantics of social tagging
    325
    Multi-Tasking with Joint Semantic Spaces for Large-Scale Music Annotation and Retrieval
    43
    Holistic Context Models for Visual Recognition
    62
    Towards musical query-by-semantic-description using the CAL500 data set
    156
    Learning Latent Semantic Models for Music from Social Tags
    67