mlsanityData to 14 Oct 2026

Contrastive learning-based video quality assessment-jointed video vision transformer for video recognition

arXiv 2603.10965 ↗First posted 11 Mar 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Video quality significantly affects video classification. We found this problem when we classified Mild Cognitive Impairment well from clear videos, but worse from blurred ones. From then, we realized that referring to Video Quality Assessment (VQA) may improve video classification. This paper proposed Self-Supervised Learning-based Video Vision Transformer combined with No-reference VQA for video classification (SSL-V3) to fulfill the goal. SSL-V3 leverages Combined-SSL mechanism to join VQA into video classification and address the label shortage of VQA, which commonly occurs in video datasets, making it impossible to provide an accurate Video Quality Score. In brief, Combined-SSL takes video quality score as a factor to directly tune the feature map of the video classification. Then, the score, as an intersected point, links VQA and classification, using the supervised classification task to tune the parameters of VQA. SSL-V3 achieved robust experimental results on two datasets. For example, it reached an accuracy of 94.87% on some interview videos in the I-CONECT (a facial video-involved healthcare dataset), verifying SSL-V3's effectiveness.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 55 references that are in the map. First posted on arXiv 11 Mar 2026.

Builds on

19 of 55 references.

References · 19

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  3. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
  4. 2021ViViT: A Video Vision Transformercited by 1,620
  5. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,616
  6. 2021A Large-Scale Study on Unsupervised Spatiotemporal Representation Learningcited by 214
  7. 2020Face Image Quality Assessment: A Literature Surveycited by 80
  8. 2021Deep Learning based Full-reference and No-reference Quality Assessment Models for Compressed UGC Videoscited by 27
  9. 2021Auto-Encoding Score Distribution Regression for Action Quality Assessmentcited by 18
  10. 2020Video-based Facial Expression Recognition using Graph Convolutional Networkscited by 13
  11. 2021Efficient Two-Stream Network for Violence Detection Using Separable Convolutional LSTMcited by 12
  12. 2023MC-ViViT: Multi-branch Classifier-ViViT to detect Mild Cognitive Impairment in older adults using facial videoscited by 11
7 more
  1. 2023GAMIVAL: Video Quality Prediction on Mobile Cloud Gaming Contentcited by 6
  2. 2021XnODR and XnIDR: Two Accurate and Fast Fully Connected Layers For Convolutional Neural Networkscited by 5
  3. 2022Multiview Contrastive Learning for Completely Blind Video Quality Assessment of User Generated Contentcited by 5
  4. 2023Detection of Mild Cognitive Impairment Using Facial Features in Video Conversationscited by 5
  5. 2024A Review of Deep Learning Approaches for Non-Invasive Cognitive Impairment Detectioncited by 5
  6. 2024Data Quality Matters: Suicide Intention Detection on Social Media Posts Using RoBERTa-CNNcited by 2
  7. 2024SE-GCL: An Event-Based Simple and Effective Graph Contrastive Learning for Text Representationcited by 1

Built on by

Not cited yet.