MCL-V: A streaming video quality assessment database

• We build a new VQA database called MCL-V.
• The video sources are selected with representative and diversified contents.
• The distortion types are designed according to streaming video services.
• An improved pairwise comparison is adopted to save evaluation time.
• We evaluate several IQA and VQA algorithms against the MCL-V database.

A high-definition video quality assessment (VQA) database that captures two typical video distortion types in video services (namely, “compression” and “compression followed by scaling”) is presented in this work. The VQA database, called MCL-V, contains 12 source video clips and 96 distorted video clips with subjective assessment scores. The source video clips are selected from a large pool of public-domain high-definition (HD) video sequences with representative and diversified contents. Both distortion types are perceptually adjusted to yield distinguishable distortion levels. An improved pairwise comparison method is adopted for subjective evaluation to save evaluation time. Several existing image and video quality assessment (IQA and VQA) algorithms are evaluated against the MCL-V database. The MCL-V database is publicly accessible in the link – http://mcl.usc.edu/mcl-v-database/ to facilitate future video quality assessment research of the community.