cs.CVNov 12, 2026

HiVE-VQA: Hierarchical Interaction via Volumetric Embedding for Video Quality Assessment

Authors: Robbie Hamilton, Fan Zhang, David Bull

Organizations: Visual Information Laboratory, University of Bristol, Bristol, UK

Abstract

The proliferation of user-generated video content has made accurate and robust no-reference video quality assessment (NR-VQA) a highly important challenge. Existing research increasingly relies on architecturally complex multi-branch pipelines or computationally intensive fine-tuning of single-branch backbones. In this paper, we investigate whether a single frozen video foundation model can serve as an effective NR-VQA backbone, and propose HiVE-VQA, the first framework (to our knowledge) to apply a JEPA-based video encoder to this task. HiVE-VQA extracts token grids from multiple depths of a pre-trained V-JEPA 2.1 encoder and stacks them into a hierarchical spatio-temporal volume, which a compact 3D convolutional head fuses across its layer, spatial, and temporal axes, combining low-level distortion cues from shallow layers with the semantic and temporal context captured at greater depths. The encoder remains frozen throughout, so only the head is trained: 5.2M parameters (5.7% of the total), with no auxiliary multi-modal models and an inference cost that is invariant to video resolution. Trained solely on LSVQ and evaluated without any fine-tuning, HiVE-VQA outperforms 17 state-of-the-art (SOTA) methods in SROCC and PLCC on both intra-dataset (LSVQ-test, LSVQ-1080p) and cross-dataset (KoNViD-1k, LIVE-VQC) benchmarks. These results indicate that hierarchical, depth-wise fusion of features from a single frozen video foundation model provides a more effective and efficient basis for NR-VQA than task-specific multi-network fusion. Code and model checkpoints are available at https://github.com/RobHam99/HiVE-VQA.

Figures & tables

Explore similar work

CardsList
  1. High-Fidelity Video Quality Assessment with VQA-Specific Saliency

    Sep 15, 2026Hakan Emre Gedik, Shashank Gupta, Alan BovikVideo Quality Assessmentreference-free video quality assessment

  2. CompressedVQA-AEV: Full-Reference and No-Reference Quality Assessment Models for Asymmetric Encoded Videos

    Jul 6, 2026Wei Sun, Xingwei Liu, Dandan Zhu +3Video Quality Assessmentreference-free video quality assessment

  3. FGSVQA: Frequency-Guided Short-form Video Quality Assessment

    May 19, 2026Xinyi Wang, Angeliki Katsenou, Junxiao Shen +1Frequency-Domain AnalysisVideo Quality Assessment