Blindly Assess Quality of In-the-Wild Videos via Quality-aware Pre-training and Motion Perception

19 Aug 2021  ·  Bowen Li, Weixia Zhang, Meng Tian, Guangtao Zhai, Xianpei Wang ·

Perceptual quality assessment of the videos acquired in the wilds is of vital importance for quality assurance of video services. The inaccessibility of reference videos with pristine quality and the complexity of authentic distortions pose great challenges for this kind of blind video quality assessment (BVQA) task. Although model-based transfer learning is an effective and efficient paradigm for the BVQA task, it remains to be a challenge to explore what and how to bridge the domain shifts for better video representation. In this work, we propose to transfer knowledge from image quality assessment (IQA) databases with authentic distortions and large-scale action recognition with rich motion patterns. We rely on both groups of data to learn the feature extractor. We train the proposed model on the target VQA databases using a mixed list-wise ranking loss function. Extensive experiments on six databases demonstrate that our method performs very competitively under both individual database and mixed database training settings. We also verify the rationality of each component of the proposed method and explore a simple manner for further improvement.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Video Quality Assessment KoNViD-1k BVQA-2022 PLCC 0.834 # 10
Video Quality Assessment LIVE-FB LSVQ BVQA-2022 PLCC 0.854 # 8
Video Quality Assessment LIVE-VQC BVQA-2022 PLCC 0.839 # 8
Video Quality Assessment MSU NR VQA Database LI SRCC 0.9131 # 4
PLCC 0.9270 # 2
KLCC 0.7640 # 4
Type NR # 1
Video Quality Assessment YouTube-UGC BVQA-2022 PLCC 0.8178 # 7


No methods listed for this paper. Add relevant methods here