Exploring video quality assessment on user generated contents from aesthetic and technical perspectives
The rapid increase in user-generated content (UGC) videos calls for the development of effective video quality assessment (VQA) algorithms. However, the objective of the UGC-VQA problem is still ambiguous and can be viewed from two perspectives: the technical perspective, measuring the perception of...
| Main Authors: | , , , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Language: | English |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/178458 |
| _version_ | 1826129329209212928 |
|---|---|
| author | Wu, Haoning Zhang, Erli Liao, Liang Chen, Chaofeng Hou, Jingwen Wang, Annan Sun, Wenxiu Yan, Qiong Lin, Weisi |
| author2 | College of Computing and Data Science |
| author_facet | College of Computing and Data Science Wu, Haoning Zhang, Erli Liao, Liang Chen, Chaofeng Hou, Jingwen Wang, Annan Sun, Wenxiu Yan, Qiong Lin, Weisi |
| author_sort | Wu, Haoning |
| collection | NTU |
| description | The rapid increase in user-generated content (UGC) videos calls for the development of effective video quality assessment (VQA) algorithms. However, the objective of the UGC-VQA problem is still ambiguous and can be viewed from two perspectives: the technical perspective, measuring the perception of distortions; and the aesthetic perspective, which relates to preference and recommendation on contents. To understand how these two perspectives affect overall subjective opinions in UGC-VQA, we conduct a large-scale subjective study to collect human quality opinions on the overall quality of videos as well as perceptions from aesthetic and technical perspectives. The collected Disentangled Video Quality Database (DIVIDE-3k) confirms that human quality opinions on UGC videos are universally and inevitably affected by both aesthetic and technical perspectives. In light of this, we propose the Disentangled Objective Video Quality Evaluator (DOVER) to learn the quality of UGC videos based on the two perspectives. The DOVER proves state-of-the-art performance in UGC-VQA under very high efficiency. With perspective opinions in DIVIDE-3k, we further propose DOVER++, the first approach to provide reliable clear-cut quality evaluations from a single aesthetic or technical perspective. Code at https://github.com/VQAssessment/DOVER. |
| first_indexed | 2024-10-01T07:38:48Z |
| format | Conference Paper |
| id | ntu-10356/178458 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:38:48Z |
| publishDate | 2024 |
| record_format | dspace |
| spelling | ntu-10356/1784582024-09-26T07:37:58Z Exploring video quality assessment on user generated contents from aesthetic and technical perspectives Wu, Haoning Zhang, Erli Liao, Liang Chen, Chaofeng Hou, Jingwen Wang, Annan Sun, Wenxiu Yan, Qiong Lin, Weisi College of Computing and Data Science School of Computer Science and Engineering 2023 IEEE/CVF International Conference on Computer Vision (ICCV) S-Lab Computer and Information Science Computer vision Codes The rapid increase in user-generated content (UGC) videos calls for the development of effective video quality assessment (VQA) algorithms. However, the objective of the UGC-VQA problem is still ambiguous and can be viewed from two perspectives: the technical perspective, measuring the perception of distortions; and the aesthetic perspective, which relates to preference and recommendation on contents. To understand how these two perspectives affect overall subjective opinions in UGC-VQA, we conduct a large-scale subjective study to collect human quality opinions on the overall quality of videos as well as perceptions from aesthetic and technical perspectives. The collected Disentangled Video Quality Database (DIVIDE-3k) confirms that human quality opinions on UGC videos are universally and inevitably affected by both aesthetic and technical perspectives. In light of this, we propose the Disentangled Objective Video Quality Evaluator (DOVER) to learn the quality of UGC videos based on the two perspectives. The DOVER proves state-of-the-art performance in UGC-VQA under very high efficiency. With perspective opinions in DIVIDE-3k, we further propose DOVER++, the first approach to provide reliable clear-cut quality evaluations from a single aesthetic or technical perspective. Code at https://github.com/VQAssessment/DOVER. This study is supported under the RIE2020 Industry Alignment Fund – Industry Collaboration Projects (IAFICP) Funding Initiative, as well as cash and in-kind contribution from the industry partner(s). 2024-06-21T01:17:07Z 2024-06-21T01:17:07Z 2023 Conference Paper Wu, H., Zhang, E., Liao, L., Chen, C., Hou, J., Wang, A., Sun, W., Yan, Q. & Lin, W. (2023). Exploring video quality assessment on user generated contents from aesthetic and technical perspectives. 2023 IEEE/CVF International Conference on Computer Vision (ICCV), 20087-20097. https://dx.doi.org/10.1109/ICCV51070.2023.01843 9798350307184 https://hdl.handle.net/10356/178458 10.1109/ICCV51070.2023.01843 2-s2.0-85185867695 20087 20097 en 10.21979/N9/ELWDPE © 2023 IEEE. All rights reserved. This article may be downloaded for personal use only. Any other use requires prior permission of the copyright holder. The Version of Record is available online at http://doi.org/10.1109/ICCV51070.2023.01843. application/pdf |
| spellingShingle | Computer and Information Science Computer vision Codes Wu, Haoning Zhang, Erli Liao, Liang Chen, Chaofeng Hou, Jingwen Wang, Annan Sun, Wenxiu Yan, Qiong Lin, Weisi Exploring video quality assessment on user generated contents from aesthetic and technical perspectives |
| title | Exploring video quality assessment on user generated contents from aesthetic and technical perspectives |
| title_full | Exploring video quality assessment on user generated contents from aesthetic and technical perspectives |
| title_fullStr | Exploring video quality assessment on user generated contents from aesthetic and technical perspectives |
| title_full_unstemmed | Exploring video quality assessment on user generated contents from aesthetic and technical perspectives |
| title_short | Exploring video quality assessment on user generated contents from aesthetic and technical perspectives |
| title_sort | exploring video quality assessment on user generated contents from aesthetic and technical perspectives |
| topic | Computer and Information Science Computer vision Codes |
| url | https://hdl.handle.net/10356/178458 |
| work_keys_str_mv | AT wuhaoning exploringvideoqualityassessmentonusergeneratedcontentsfromaestheticandtechnicalperspectives AT zhangerli exploringvideoqualityassessmentonusergeneratedcontentsfromaestheticandtechnicalperspectives AT liaoliang exploringvideoqualityassessmentonusergeneratedcontentsfromaestheticandtechnicalperspectives AT chenchaofeng exploringvideoqualityassessmentonusergeneratedcontentsfromaestheticandtechnicalperspectives AT houjingwen exploringvideoqualityassessmentonusergeneratedcontentsfromaestheticandtechnicalperspectives AT wangannan exploringvideoqualityassessmentonusergeneratedcontentsfromaestheticandtechnicalperspectives AT sunwenxiu exploringvideoqualityassessmentonusergeneratedcontentsfromaestheticandtechnicalperspectives AT yanqiong exploringvideoqualityassessmentonusergeneratedcontentsfromaestheticandtechnicalperspectives AT linweisi exploringvideoqualityassessmentonusergeneratedcontentsfromaestheticandtechnicalperspectives |