Lune

CVPR Findings2026

Pioneering Perceptual Video Fluency Assessment: A Novel Task with Benchmark Dataset and Baseline

Qizhi Xie, Kun Yuan, Yunpeng Qu, Ming Sun, Chao Zhou, Jihong Zhu

Abstract

Accurately estimating humans' subjective feedback on video fluency, e.g., motion consistency and frame continuity, is crucial for various applications like streaming and gaming. Yet, it has long been overlooked, as prior arts have focused on solving it in the video quality assessment (VQA) task, merely as a sub-dimension of overall quality. In this work, we conduct pilot experiments and reveal that current VQA predictions largely underrepresent fluency, thereby limiting their applicability. To this end, we pioneer Video Fluency Assessment (VFA) as a standalone perceptual task focused on the temporal dimension. To advance VFA research, 1) we construct a fluency-oriented dataset, FluVid, comprising 4,606 in-the-wild videos with balanced fluency distribution, featuring the first-ever scoring criteria and human study for VFA. 2) We develop a large-scale benchmark of 23 methods, the most comprehensive one thus far on FluVid, gathering insights for VFA-tailored model designs.

  1. We propose a baseline model called FluNet, which deploys temporal permuted self-attention (T-PSA) to enrich input fluency information and enhance long-range interframe interactions. Our work not only achieves state-ofthe-art performance but, more importantly, offers the community a roadmap to explore solutions for VFA. Both Flu-Vid and FluNet will be available at https://github. com/KeiChiTse/VFA.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Video Swin Transformer cites Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
  • Video Swin Transformer cites SlowFast Networks for Video Recognition
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on33

  1. Swin Transformer: Hierarchical Vision Transformer using Shifted WindowsZe Liu, Yutong Lin, Yue Cao, Han Hu et al.ICCV 2021 · 31,683 citations
  2. SlowFast Networks for Video RecognitionChristoph Feichtenhofer, Haoqi Fan, Jitendra Malik, Kaiming HeICCV 2019 · 4,104 citations
  3. Video Swin TransformerZe Liu, Jia Ning, Yue Cao, Yixuan Wei et al.CVPR 2022 · 1,847 citations
  4. VideoBERT: A Joint Model for Video and Language Representation LearningChen Sun, Austin Myers, Carl Vondrick, Kevin Murphy et al.ICCV 2019 · 1,396 citations
  5. Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined LevelsHaoning Wu, Zicheng Zhang, Weixia Zhang, Chaofeng Chen et al.ICML 2024 · 499 citations

Related papers

  1. Exploring the Effectiveness of Video Perceptual Representation in Blind Video Quality AssessmentLiang Liao, Kangmin Xu, Haoning Wu, Chaofeng Chen et al.ACM MM 2022 · 39 citations
  2. Semantic-Aware and Quality-Aware Interaction Network for Blind Video Quality AssessmentJianjun Xiang, Yuanjie Dang, Peng Chen, Ronghua Liang et al.ACM MM 2024
  3. Patch-VQ: 'Patching Up' the Video Quality ProblemZhenqiang Ying, Maniratnam Mandal, Deepti Ghadiyaram, Alan C. BovikCVPR 2021
  4. RIRNet: Recurrent-In-Recurrent Network for Video Quality AssessmentPengfei Chen, Leida Li, Lei Ma, Jinjian Wu et al.ACM MM 2020 · 94 citations
  5. KVQ: Boosting Video Quality Assessment via Saliency-guided Local PerceptionYunpeng Qu, Kun Yuan, Qizhi Xie, Ming Sun et al.CVPR 2025
Dusk over the sea between two cliffs drawn in fine vertical lines