Deep attributes and decisions fusion for no-reference video quality analysis
Video Quality Assessment (VQA) is a critical component of various technologies, including automated video broadcasting through displaying technologies. Moreover, determining visual quality necessitates a balanced examination of visual features and functionality. Previous research has also shown that...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
REA Press
2023-09-01
|
| Series: | Big Data and Computing Visions |
| Subjects: | |
| Online Access: | https://www.bidacv.com/article_189314_c7555c86e1c77fa6447486b5bb4b547c.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832579299789504512 |
|---|---|
| author | Adil Baig |
| author_facet | Adil Baig |
| author_sort | Adil Baig |
| collection | DOAJ |
| description | Video Quality Assessment (VQA) is a critical component of various technologies, including automated video broadcasting through displaying technologies. Moreover, determining visual quality necessitates a balanced examination of visual features and functionality. Previous research has also shown that features derived from pre-trained models of Convolutional Neural Networks (CNNs) are extremely useful in various image analysis and computer vision activities. Based on characteristics collected from pre-trained models of deep neural networks, transfer learning, periodic pooling, and regression, we created a unique architecture for No Reference Video Quality Assessment (NR-VQA) in this research. We were able to get results by solely employing dynamically pooled deep features and avoiding the use of manually produced features. This study describes a novel, deep learning-based strategy for NR-VQA that uses several pre-trained deep neural networks to characterize probable image and video distortions across parallel. A set of pre-trained CNNs extract spatially pooling and intensity-adjusted video-level feature representations, which are then individually mapped onto subjective peer assessments. Ultimately, the perceived quality of a video series is calculated by combining the quality standards from the various regressors. Numerous researches demonstrate that the suggested approach on two large baseline video quality analysis datasets with realistic aberrations sets a new state-of-the-art. Furthermore, the findings show that combining the decisions of different deep networks can greatly improve NR-VQA. |
| format | Article |
| id | doaj-art-9031410cfd634d40977bb8fc888fb07b |
| institution | Kabale University |
| issn | 2783-4956 2821-014X |
| language | English |
| publishDate | 2023-09-01 |
| publisher | REA Press |
| record_format | Article |
| series | Big Data and Computing Visions |
| spelling | doaj-art-9031410cfd634d40977bb8fc888fb07b2025-01-30T12:23:01ZengREA PressBig Data and Computing Visions2783-49562821-014X2023-09-01339110310.22105/bdcv.2023.415895.1165189314Deep attributes and decisions fusion for no-reference video quality analysisAdil Baig0University of Agriculture, Pakistan.Video Quality Assessment (VQA) is a critical component of various technologies, including automated video broadcasting through displaying technologies. Moreover, determining visual quality necessitates a balanced examination of visual features and functionality. Previous research has also shown that features derived from pre-trained models of Convolutional Neural Networks (CNNs) are extremely useful in various image analysis and computer vision activities. Based on characteristics collected from pre-trained models of deep neural networks, transfer learning, periodic pooling, and regression, we created a unique architecture for No Reference Video Quality Assessment (NR-VQA) in this research. We were able to get results by solely employing dynamically pooled deep features and avoiding the use of manually produced features. This study describes a novel, deep learning-based strategy for NR-VQA that uses several pre-trained deep neural networks to characterize probable image and video distortions across parallel. A set of pre-trained CNNs extract spatially pooling and intensity-adjusted video-level feature representations, which are then individually mapped onto subjective peer assessments. Ultimately, the perceived quality of a video series is calculated by combining the quality standards from the various regressors. Numerous researches demonstrate that the suggested approach on two large baseline video quality analysis datasets with realistic aberrations sets a new state-of-the-art. Furthermore, the findings show that combining the decisions of different deep networks can greatly improve NR-VQA.https://www.bidacv.com/article_189314_c7555c86e1c77fa6447486b5bb4b547c.pdfvideo quality assessmentno reference video quality assessmentdeep neural networks |
| spellingShingle | Adil Baig Deep attributes and decisions fusion for no-reference video quality analysis Big Data and Computing Visions video quality assessment no reference video quality assessment deep neural networks |
| title | Deep attributes and decisions fusion for no-reference video quality analysis |
| title_full | Deep attributes and decisions fusion for no-reference video quality analysis |
| title_fullStr | Deep attributes and decisions fusion for no-reference video quality analysis |
| title_full_unstemmed | Deep attributes and decisions fusion for no-reference video quality analysis |
| title_short | Deep attributes and decisions fusion for no-reference video quality analysis |
| title_sort | deep attributes and decisions fusion for no reference video quality analysis |
| topic | video quality assessment no reference video quality assessment deep neural networks |
| url | https://www.bidacv.com/article_189314_c7555c86e1c77fa6447486b5bb4b547c.pdf |
| work_keys_str_mv | AT adilbaig deepattributesanddecisionsfusionfornoreferencevideoqualityanalysis |