Publications (9)
Balanced Representation Learning for Long-tailed Skeleton-based Action Recognition
Hongda Liu, Yunlong Wang, Min Ren +4
Skeleton-based action recognition has recently made significant progress. However, data imbalance is still a great challenge in real-world scenarios. The performance of current act…
Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition
Hongda Liu, Yunfan Liu, Min Ren +3
In skeleton-based action recognition, a key challenge is distinguishing between actions with similar trajectories of joints due to the lack of image-level details in skeletal repre…
NTIRE 2024 Challenge on Stereo Image Super-Resolution: Methods and Results
Longguang Wang, Yulan Guo, Juncheng Li +6
This paper summarizes the 3rd NTIRE challenge on stereo image super-resolution (SR) with a focus on new solutions and results. The task of this challenge is to super-resolve a low-…
Preserving Full Degradation Details for Blind Image Super-Resolution
Hongda Liu, Longguang Wang, Ye Zhang +3
The performance of image super-resolution relies heavily on the accuracy of degradation information, especially under blind settings. Due to the absence of true degradation models…
SaMam: Style-aware State Space Model for Arbitrary Image Style Transfer
Hongda Liu, Longguang Wang, Ye Zhang +2
Global effective receptive field plays a crucial role for image style transfer (ST) to obtain high-quality stylized results. However, existing ST backbones (e.g., CNNs and Transfor…
Deploying Large AI Models on Resource-Limited Devices with Split Federated Learning
Xianke Qiang, Hongda Liu, Xinran Zhang +2
Large Artificial Intelligence Models (LAMs) powered by massive datasets, extensive parameter scales, and extensive computational resources, leading to significant transformations a…