Adaptation of Word Vectors using Tree Structure for Visual Semantics

@inproceedings{Inoue2016AdaptationOW,
  title={Adaptation of Word Vectors using Tree Structure for Visual Semantics},
  author={Nakamasa Inoue and Koichi Shinoda},
  booktitle={ACM Multimedia},
  year={2016}
}
We propose a framework of word-vector adaptation, which makes vectors of visually similar concepts close to each other. Here, word vectors are real-valued vector representation of words, e.g., word2vec representation. Our basic idea is to assume that each concept has some hypernyms that are important to determine its visual features. For example, for a concept Swallow with hypernyms Bird, Animal and Entity, we believe Bird is the most important since birds have common visual features with their… CONTINUE READING