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!
|
| Summary: | 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.
|
|---|---|
| ISSN: | 1225-6463 2233-7326 |