Low-resolution activity recognition using super-resolution and model ensemble networks
In real-world video super-resolution, the complexity and diversity of degrada-tions pose substantial challenges during both training and inference. Videos captured in real-world settings often depict activities at varying resolutions. Typically, these activities are filmed from a distance that reduc...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Electronics and Telecommunications Research Institute (ETRI)
2025-04-01
|
| Series: | ETRI Journal |
| Subjects: | |
| Online Access: | https://doi.org/10.4218/etrij.2023-0523 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849725988058955776 |
|---|---|
| author | Tinglong Liu Haiyan Wang |
| author_facet | Tinglong Liu Haiyan Wang |
| author_sort | Tinglong Liu |
| collection | DOAJ |
| description | In real-world video super-resolution, the complexity and diversity of degrada-tions pose substantial challenges during both training and inference. Videos captured in real-world settings often depict activities at varying resolutions. Typically, these activities are filmed from a distance that reduces the resolu-tion of imagery, which thus lacks discriminative features. To address this prob-lem, we introduce an activity recognition solution. First, a unique integration of data transformation and attention-based average discriminator are employed for super-resolution feature augmentation. This approach mitigates the lack of discriminative cues in low-resolution videos. Subsequently, high-resolution features extracted from the recovered data are directly fed into a model ensemble for activity recognition. We evaluate the resulting method on the TinyVIRAT-v2 and HMDB51 datasets, achieving improved visual quality by leveraging the super-resolution and model ensemble strategy. The proposed method enhances the quality of textures and boosts activity recognition in low-resolution videos.
|
| format | Article |
| id | doaj-art-89b124ee159a4e9fa1d21beb870b50cc |
| institution | DOAJ |
| issn | 1225-6463 2233-7326 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | Electronics and Telecommunications Research Institute (ETRI) |
| record_format | Article |
| series | ETRI Journal |
| spelling | doaj-art-89b124ee159a4e9fa1d21beb870b50cc2025-08-20T03:10:20ZengElectronics and Telecommunications Research Institute (ETRI)ETRI Journal1225-64632233-73262025-04-0147230331110.4218/etrij.2023-0523Low-resolution activity recognition using super-resolution and model ensemble networks Tinglong LiuHaiyan WangIn real-world video super-resolution, the complexity and diversity of degrada-tions pose substantial challenges during both training and inference. Videos captured in real-world settings often depict activities at varying resolutions. Typically, these activities are filmed from a distance that reduces the resolu-tion of imagery, which thus lacks discriminative features. To address this prob-lem, we introduce an activity recognition solution. First, a unique integration of data transformation and attention-based average discriminator are employed for super-resolution feature augmentation. This approach mitigates the lack of discriminative cues in low-resolution videos. Subsequently, high-resolution features extracted from the recovered data are directly fed into a model ensemble for activity recognition. We evaluate the resulting method on the TinyVIRAT-v2 and HMDB51 datasets, achieving improved visual quality by leveraging the super-resolution and model ensemble strategy. The proposed method enhances the quality of textures and boosts activity recognition in low-resolution videos. https://doi.org/10.4218/etrij.2023-0523activity recognitionattention mechanismlow-resolution videomodel ensemblesuper-resolution |
| spellingShingle | Tinglong Liu Haiyan Wang Low-resolution activity recognition using super-resolution and model ensemble networks ETRI Journal activity recognition attention mechanism low-resolution video model ensemble super-resolution |
| title | Low-resolution activity recognition using super-resolution and model ensemble networks |
| title_full | Low-resolution activity recognition using super-resolution and model ensemble networks |
| title_fullStr | Low-resolution activity recognition using super-resolution and model ensemble networks |
| title_full_unstemmed | Low-resolution activity recognition using super-resolution and model ensemble networks |
| title_short | Low-resolution activity recognition using super-resolution and model ensemble networks |
| title_sort | low resolution activity recognition using super resolution and model ensemble networks |
| topic | activity recognition attention mechanism low-resolution video model ensemble super-resolution |
| url | https://doi.org/10.4218/etrij.2023-0523 |
| work_keys_str_mv | AT tinglongliu lowresolutionactivityrecognitionusingsuperresolutionandmodelensemblenetworks AT haiyanwang lowresolutionactivityrecognitionusingsuperresolutionandmodelensemblenetworks |