mlsanityData to 14 Oct 2026

VQualA 2025 Challenge on Engagement Prediction for Short Videos: Methods and Results

arXiv 2509.02969 ↗First posted 3 Sep 2025cs.CV cs.MM cs.SIcited by 6

Not on the map. Why?

Abstract (arXiv)

This paper presents an overview of the VQualA 2025 Challenge on Engagement Prediction for Short Videos, held in conjunction with ICCV 2025. The challenge focuses on understanding and modeling the popularity of user-generated content (UGC) short videos on social media platforms. To support this goal, the challenge uses a new short-form UGC dataset featuring engagement metrics derived from real-world user interactions. This objective of the Challenge is to promote robust modeling strategies that capture the complex factors influencing user engagement. Participants explored a variety of multi-modal features, including visual content, audio, and metadata provided by creators. The challenge attracted 97 participants and received 15 valid test submissions, contributing significantly to progress in short-form UGC video engagement prediction.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 40 of its 58 references that are in the map. First posted on arXiv 3 Sep 2025.

Builds on

40 of 58 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  5. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  6. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  7. 2025Qwen2.5-VL Technical Reportcited by 5,587
  8. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  9. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,135
  10. 2024VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMscited by 771
  11. 2017Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?cited by 551
  12. 2023Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levelscited by 503
28 more
  1. 2022BEATs: Audio Pre-Training with Acoustic Tokenizerscited by 388
  2. 2022Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectivescited by 320
  3. 2019Quality Assessment of In-the-Wild Videoscited by 164
  4. 2023mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Videocited by 154
  5. 2023Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Modelscited by 152
  6. 2020Patch-VQ: 'Patching Up' the Video Quality Problemcited by 147
  7. 2020UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Contentcited by 140
  8. 2022A Deep Learning based No-reference Quality Assessment Model for UGC Videoscited by 129
  9. 2018Large-Scale Study of Perceptual Video Qualitycited by 127
  10. 2019MeLU: Meta-Learned User Preference Estimator for Cold-Start Recommendationcited by 121
  11. 2022A Simple Baseline for Video Restoration with Grouped Spatial-temporal Shiftcited by 68
  12. 2019Warm Up Cold-start Advertisements: Improving CTR Predictions via Learning to Learn ID Embeddingscited by 66
  13. 2020Learning Generalized Spatial-Temporal Deep Feature Representation for No-Reference Video Quality Assessmentcited by 50
  14. 2023MD-VQA: Multi-Dimensional Quality Assessment for UGC Live Videoscited by 46
  15. 2021Learning to Warm Up Cold Item Embeddings for Cold-start Recommendation with Meta Scaling and Shifting Networkscited by 37
  16. 2022Deconfounding Duration Bias in Watch-time Prediction for Video Recommendationcited by 37
  17. 2022Learning Degradation Representations for Image Deblurringcited by 35
  18. 2025Skywork-VL Reward: An Effective Reward Model for Multimodal Understanding and Reasoningcited by 32
  19. 2021Deep Learning based Full-reference and No-reference Quality Assessment Models for Compressed UGC Videoscited by 27
  20. 2022Efficient Burst Raw Denoising with Variance Stabilization and Multi-frequency Denoising Networkcited by 15
  21. 2020Subjective Quality Assessment for YouTube UGC Datasetcited by 11
  22. 2020VLEngagement: A Dataset of Scientific Video Lectures for Evaluating Population-based Engagementcited by 8
  23. 2024Video Quality Assessment Based on Swin TransformerV2 and Coarse to Fine Strategycited by 6
  24. 2025Q-Adapt: Adapting LMM for Visual Quality Assessment with Progressive Instruction Tuningcited by 6
  25. 2024Delving Deep into Engagement Prediction of Short Videoscited by 4
  26. 2025InternVQA: Advancing Compressed Video Quality Assessment with Distilling Large Foundation Modelcited by 4
  27. 2025Engagement Prediction of Short Videos with Large Multimodal Modelscited by 4
  28. 2025DiffVQA: Video Quality Assessment Using Diffusion Feature Extractorcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 3.

6 papers.

  1. 2025Is your VLM Sky-Ready? A Comprehensive Spatial Intelligence Benchmark for UAV Navigationcited by 10
  2. 2025VQualA 2025 Challenge on Image Super-Resolution Generated Content Quality Assessment: Methods and Resultscited by 5
  3. 2026SEF-MAP: Subspace-Decomposed Expert Fusion for Robust Multimodal HD Map Predictioncited by 2
  4. 2026Bounded-Compute Multimodal Regression for Product-Rating Predictioncited by 1
  5. 2026EpiCon: Collective Agent Learning through Co-Evolving Multimodal Memorycited by 1
  6. 2025VQualA 2025 Challenge on Visual Quality Comparison for Large Multimodal Models: Methods and Resultscited by 0