Adaptive relevance feedback for fusion of text and visual features

Kaliciak L., Myrhaug H., Goker A., Song D.

18th International Conference on Information Fusion, Fusion 2015, Washington, Amerika Birleşik Devletleri, 6 - 09 Temmuz 2015, ss.1322-1329, (Tam Metin Bildiri) identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Basıldığı Şehir: Washington
  • Basıldığı Ülke: Amerika Birleşik Devletleri
  • Sayfa Sayıları: ss.1322-1329
  • Anahtar Kelimeler: Adaptive Weighting Scheme, Early Fusion, Hybrid Relevance Feedback, Late Fusion, Re-Ranking, Textual Features, Visual Features
  • Çanakkale Onsekiz Mart Üniversitesi Adresli: Hayır

Özet

It has been shown that query can be correlated with its context to a different extent; in this case the feedback images. We introduce an adaptive weighting scheme where the respective weights are automatically modified, depending on the relationship strength between visual query and its visual context and textual query and its textual context; the number of terms or visual terms (mid-level visual features) co-occurring between current query and its context. The user simulation experiment has shown that this kind of adaptation can indeed further improve the effectiveness of hybrid CBIR models.