Search Results for author:
Found 6 papers, 2 papers with code
NTIRE 2024 Quality Assessment of AI-Generated Content Challenge
A total of 196 participants have registered in the video track.
Temporal Relations of Informative Frames in Action Recognition
This paper presents a simple approach leveraging temporal learning on informative frames for action recognition.
Ranked #1 on
Action Recognition
on KTH
Compressed image quality assessment using stacking
Moreover, the results of the Full-Reference (FR) and No-Reference (NR) models are aggregated to improve the proposed Full-Reference method for compressed image quality evaluation.
NTIRE 2023 Quality Assessment of Video Enhancement Challenge
61 participating teams submitted their prediction results during the development phase, with a total of 3168 submissions.
Adaptive frame selection in two dimensional convolutional neural network action recognition
We presented a technique in this research for dynamic frame selection to achieve robust features.
Ranked #1 on
Action Recognition
on UCF101
(Accuracy 20%Test metric)
Speeding Up Action Recognition Using Dynamic Accumulation of Residuals in Compressed Domain
Most of the existing methods mainly focused on increasing accuracy by exploring consecutive frames, which is laborious and cannot be considered for real-time applications.
