1 code implementation • 17 Apr 2024 • Lianyu Hu, Wei Feng, Liqing Gao, Zekang Liu, Liang Wan
In specific, CorrNet+ employs a correlation module and an identification module to build human body trajectories.
2 code implementations • 12 Apr 2024 • Lianyu Hu, Tongkai Shi, Liqing Gao, Zekang Liu, Wei Feng
Besides, fully fine-tuning the model easily forgets the generic essential knowledge acquired in the pretraining stage and overfits the downstream data.
1 code implementation • 19 Mar 2024 • Lianyu Hu, Liqing Gao, Zekang Liu, Wei Feng
Current methods utilize spatial graph modules and temporal modules to capture spatial and temporal features, respectively.
1 code implementation • 30 Dec 2023 • Lianyu Hu, Liqing Gao, Zekang Liu, Chi-Man Pun, Wei Feng
First, the prompts of the vision and language branches in these methods are usually separated or uni-directionally correlated.
1 code implementation • 16 Aug 2023 • Lianyu Hu, Liqing Gao, Zekang Liu, Chi-Man Pun, Wei Feng
Then these features are fed into a policy network to intelligently select a subsequence to process.
Ranked #8 on Sign Language Recognition on CSL-Daily
3 code implementations • CVPR 2023 • Lianyu Hu, Liqing Gao, Zekang Liu, Wei Feng
Visualizations demonstrate the effects of CorrNet on emphasizing human body trajectories across adjacent frames.
2 code implementations • 30 Nov 2022 • Lianyu Hu, Liqing Gao, Zekang Liu, Wei Feng
To relieve this problem, we propose a self-emphasizing network (SEN) to emphasize informative spatial regions in a self-motivated way, with few extra computations and without additional expensive supervision.
Ranked #9 on Sign Language Recognition on CSL-Daily
1 code implementation • 18 Jul 2022 • Lianyu Hu, Liqing Gao, Zekang Liu, Wei Feng
In this paper, we derive temporal lift pooling (TLP) from the Lifting Scheme in signal processing to intelligently downsample features of different temporal hierarchies.