mlsanityData to 7 Oct 2026

Multilevel Semantic-Aware Model for AI-Generated Video Quality Assessment

arXiv 2501.02706 ↗First posted 6 Jan 2025cs.CVcited by 2

On the map: Diffusion models → Video generation

Abstract (arXiv)

The rapid development of diffusion models has greatly advanced AI-generated videos in terms of length and consistency recently, yet assessing AI-generated videos still remains challenging. Previous approaches have often focused on User-Generated Content(UGC), but few have targeted AI-Generated Video Quality Assessment methods. In this work, we introduce MSA-VQA, a Multilevel Semantic-Aware Model for AI-Generated Video Quality Assessment, which leverages CLIP-based semantic supervision and cross-attention mechanisms. Our hierarchical framework analyzes video content at three levels: frame, segment, and video. We propose a Prompt Semantic Supervision Module using text encoder of CLIP to ensure semantic consistency between videos and conditional prompts. Additionally, we propose the Semantic Mutation-aware Module to capture subtle variations between frames. Extensive experiments demonstrate our method achieves state-of-the-art results.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Video generation, one of 14 directions in Diffusion models. Builds on 28 of its 38 references that are in the map. First posted on arXiv 6 Jan 2025.

Builds on

28 of 38 references.

Closest ancestors · 6

Same direction, newest first

  1. 2023Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation27 Sep
  2. 2023ModelScope Text-to-Video Technical Report12 Aug
  3. 2023AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning10 Jul
  4. 2023Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators23 Mar
  5. 2023VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation15 Mar
  6. 2022Latent Video Diffusion Models for High-Fidelity Long Video Generation23 Nov

Other references · 22

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,310
  6. 2021Video Swin Transformercited by 1,090
  7. 2023ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generationcited by 1,010
  8. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 974
  9. 2023Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levelscited by 489
  10. 2023InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generationcited by 488
  11. 2022FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Samplingcited by 179
  12. 2022A Deep Learning based No-reference Quality Assessment Model for UGC Videoscited by 128
10 more
  1. 2018Large-Scale Study of Perceptual Video Qualitycited by 127
  2. 2023FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generationcited by 119
  3. 2021Blindly Assess Quality of In-the-Wild Videos via Quality-aware Pre-training and Motion Perceptioncited by 97
  4. 2022Neighbourhood Representative Sampling for Efficient End-to-end Video Quality Assessmentcited by 50
  5. 2024Subjective-Aligned Dataset and Metric for Text-to-Video Quality Assessmentcited by 39
  6. 2023Exploring Opinion-unaware Video Quality Assessment with Semantic Affinity Criterioncited by 23
  7. 2023Zoom-VQA: Patches, Frames and Clips Integration for Video Quality Assessmentcited by 21
  8. 2024NTIRE 2024 Quality Assessment of AI-Generated Content Challengecited by 20
  9. 2022FAVER: Blind Quality Prediction of Variable Frame Rate Videoscited by 10
  10. 2021Image Quality Assessment in the Modern Agecited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Federated Joint Learning for Domain and Class Generalizationcited by 0
  2. 2026HALLELUAI: A Hallucination-Aware AI System for Ultra-Realistic Image-to-Video Generation at Scalecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025VQ-Insight: Teaching VLMs for AI-Generated Video Quality Understanding via Progressive Visual Reinforcement Learning
  2. 2025Towards Holistic Visual Quality Assessment of AI-Generated Videos: A LLM-Based Multi-Dimensional Evaluation Model
  3. 2025Q-CLIP: Unleashing the Power of Vision-Language Models for Video Quality Assessment through Unified Cross-Modal Adaptation
  4. 2026VQQA: An Agentic Approach for Video Evaluation and Quality Improvement
  5. 2025Score2Instruct: Scaling Up Video Quality-Centric Instructions via Automated Dimension Scoring
  6. 2025CAMP-VQA: Caption-Embedded Multimodal Perception for No-Reference Quality Assessment of Compressed Video
  7. 2025VideoScore2: Think before You Score in Generative Video Evaluation
  8. 2026Multi-Dimensional Quality Assessment for AI-Generated Human-Centric Videos: Dataset and Model