Skip to Main content Skip to Navigation
Journal articles

Dreamed about training, verifying and validating your QoE model on a million videos?

Abstract : Training, verification, and validation of objective prediction models require well-chosen test stimuli. The measured prediction performance depends largely on the congruence of stimulus selection in the three steps training, verification, and validation. Different stimulus selection criteria are discussed: extracting a representative set of stimuli from the scope of application, spreading the range of application scope with equidistant stimuli, or using stressful stimuli for the prediction algorithm. Nowadays, most databases are too small to sufficiently cover even one of these evaluation types; a large-scale database may solve the problem but requires new statistical methods and understanding of quality evaluation.
Complete list of metadata
Contributor : Harold Mouchère Connect in order to contact the contributor
Submitted on : Monday, May 11, 2015 - 11:46:02 AM
Last modification on : Wednesday, April 27, 2022 - 4:41:56 AM
Long-term archiving on: : Monday, September 14, 2015 - 10:05:57 PM


Publisher files allowed on an open archive


  • HAL Id : hal-01150434, version 1


Glenn van Wallendael, Nicolas Staelens, Enrico Masala, Lucjan Janowski, Kongfeng Berger, et al.. Dreamed about training, verifying and validating your QoE model on a million videos?. VQEG eLetter, Video Quality Expert Group, 2014, Verification and Validation, 1 (2), pp.19-29. ⟨hal-01150434⟩



Record views


Files downloads