C
Chao-Ju Chen
Publications - 9
Citations - 35
Chao-Ju Chen is an academic researcher. The author has contributed to research in topics: Computer science & Engineering. The author has an hindex of 1, co-authored 1 publications receiving 1 citations.
Papers
More filters
Proceedings ArticleDOI
Exploring the Effectiveness of Video Perceptual Representation in Blind Video Quality Assessment
TL;DR: Wang et al. as mentioned in this paper proposed a temporal perceptual quality index (TPQI) to measure the temporal distortion by describing the graphic morphology of the representation, which can be applied to any dataset without parameter tuning.
Journal ArticleDOI
Neighbourhood Representative Sampling for Efficient End-to-end Video Quality Assessment
TL;DR: This work proposes a novel scheme, spatial-temporal grid mini-cube sampling (St-GMS) to get a novel type of sample, named fragments, and designs the Fragment Attention Network (FANet), a network architecture tailored specifically for fragments.
Journal ArticleDOI
Disentangling Aesthetic and Technical Effects for Video Quality Assessment of User Generated Content
TL;DR: Li et al. as mentioned in this paper proposed the Disentangled Objective Video Quality Evaluator (DOVER) to disentangle the effects of aesthetic quality issues and technical quality issues risen by the complicated video generation processes in UGC-VQA problem.
Journal ArticleDOI
Exploring Opinion-unaware Video Quality Assessment with Semantic Affinity Criterion
Haoning Wu,Liang Liao,Jingwen Hou,Chao-Ju Chen,Erli Zhang,Annan Wang,Wenxiu Sun,Qiong Yan,Weisi Lin +8 more
TL;DR: This article proposed a blind unified opinion-unaware video quality assessment (BUONA-VISTA) using text-prompts in contrastive language-image pre-training (CLIP) model.
Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives
Haoning Wu,Erli Zhang,Liang Liao,Chao-Ju Chen,Jingwen Hou,Annan Wang,Wenxiu Sun,Qiong Yan,Weisi Lin +8 more
TL;DR: In this article , a large-scale subjective study was conducted to collect human quality opinions on overall quality of videos as well as perceptions from aesthetic and technical perspectives, and the Disentangled Objective Video Quality Evaluator (DOVER) was proposed to learn the quality of UGC videos based on the two perspectives.