FCVSR is a frequency-aware deep model for compressed video super-resolution using MGAA and MFFR modules plus contrastive loss, achieving up to 0.14 dB PSNR gain on three public datasets.
Deformable convolutional networks
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3verdicts
UNVERDICTED 3representative citing papers
FDIM is a new hybrid feature-distance video quality metric trained on over 16k sequences that shows strong generalization and correlation with human judgments across ten unseen SDR/HDR datasets and diverse codecs.
DFIR-DETR augments RT-DETR with frequency-domain iterative refinement and dynamic feature aggregation, reporting 92.9% mAP50 on NEU-DET and 51.6% on VisDrone at 11.7M parameters and 47.2 GFLOPs.
citing papers explorer
-
FCVSR: A Frequency-aware Method for Compressed Video Super-Resolution
FCVSR is a frequency-aware deep model for compressed video super-resolution using MGAA and MFFR modules plus contrastive loss, achieving up to 0.14 dB PSNR gain on three public datasets.
-
FDIM: A Feature-distance-based Generic Video Quality Metric for Versatile Codecs
FDIM is a new hybrid feature-distance video quality metric trained on over 16k sequences that shows strong generalization and correlation with human judgments across ten unseen SDR/HDR datasets and diverse codecs.
-
DFIR-DETR: Frequency-Domain Iterative Refinement and Dynamic Feature Aggregation for Small Object Detection
DFIR-DETR augments RT-DETR with frequency-domain iterative refinement and dynamic feature aggregation, reporting 92.9% mAP50 on NEU-DET and 51.6% on VisDrone at 11.7M parameters and 47.2 GFLOPs.