Research map / Video / Video segmentation and tracking
Viewport Proposal CNN for 360deg Video Quality Assessment
Chen Li, Mai Xu, Lai Jiang, Shanyi Zhang, Xiaoming Tao
Check your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use viewport proposals and viewport saliency prediction to assess 360° video | V-CNN · VQA-ODV test set | PLCC: 0.7821 -> 0.8740 | Improved |
| Use viewport proposals and viewport saliency prediction to assess 360° video | V-CNN · VQA-ODV test set | SROCC: 0.7953 -> 0.8962 | Improved |
| Use viewport proposals and viewport saliency prediction to assess 360° video | V-CNN · VQA-ODV test set | KROCC: 0.5902 -> 0.7137 | Improved |
| Use viewport proposals and viewport saliency prediction to assess 360° video | V-CNN · VQA-ODV test set | RMSE: 7.3817 -> 5.7551 | Improved |
| Use viewport proposals and viewport saliency prediction to assess 360° video | V-CNN · VQA-ODV test set | MAE: 5.7793 -> 4.4893 | Improved |
| Replace proposed viewports with ground-truth viewports (ablation) | V-CNN · VQA-ODV | VQA error | No clear effect |
| Use random viewports instead of proposed viewports (ablation) | V-CNN · VQA-ODV | VQA error | Hurt |
| Remove viewport selection and use a resized whole frame (ablation) | V-CNN · VQA-ODV | VQA error | Hurt |
| Remove saliency prediction supervision (λM = 0) (ablation) | V-CNN · VQA-ODV | VQA error | Hurt |
| Set saliency loss weight below or above the selected weight (ablation) | V-CNN · VQA-ODV | VQA error | Hurt |
| Use ground-truth saliency instead of predicted saliency (ablation) | V-CNN · VQA-ODV | VQA error | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- DeepVS — DeepVS: A Deep Learning Based Video Saliency Prediction Approach (ECCV 2018) · better on 1 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Viewport-based CNN: A Multi-task Approach for Assessing 360° Video Quality (TPAMI 2020 · similarity 0.94)
- KVQ: Boosting Video Quality Assessment via Saliency-guided Local Perception (CVPR 2025 · similarity 0.85)
- Modular Blind Video Quality Assessment (CVPR 2024 · similarity 0.85)
- PTM-VQA: Efficient Video Quality Assessment Leveraging Diverse PreTrained Models from the Wild (CVPR 2024 · similarity 0.83)
- AIGV-Assessor: Benchmarking and Evaluating the Perceptual Quality of Text-to-Video Generation with LMM (CVPR 2025 · similarity 0.83)
- Multi-Frame Deformable Look-Up Table for Compressed Video Quality Enhancement (AAAI 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
