Can Social Tagged Images Aid Concept-Based Video Search? A. T. Setz, C. G. M. Snoek In IEEE International Conference on Multimedia & Expo 2009. [bibtex] [pdf] [url]

This paper seeks to unravel whether commonly available social tagged images can be exploited as a training resource for concept-based video search. Since social tags are known to be ambiguous, overly personalized, and often error prone, we place special emphasis on the role of disambiguation. We present a systematic experimental study that evaluates concept detectors based on social tagged images, and their disambiguated versions, in three application scenarios: within-domain, cross-domain, and together with an interacting user. The results indicate that social tagged images can aid concept-based video search indeed, especially after disambiguation and when used in an interactive video retrieval setting. These results open-up interesting avenues for future research.

@InProceedings{SetzICME2009,
  author       = "Setz, A. T. and Snoek, C. G. M.",
  title        = "Can Social Tagged Images Aid Concept-Based Video Search?",
  booktitle    = "IEEE International Conference on Multimedia \& Expo",
  year         = "2009",
  url          = "https://ivi.fnwi.uva.nl/isis/publications/2009/SetzICME2009",
  pdf          = "https://ivi.fnwi.uva.nl/isis/publications/2009/SetzICME2009/SetzICME2009.pdf",
  has_image    = 1
}