Detect Any Shadow: Segment Anything for Video Shadow Detection von Wang, Yonghui, Zhou, Wengang, Mao, Yunyao, Li, Houqiang

Volltext

MASA: Motion-Aware Masked Autoencoder With Semantic Alignment for Sign Language Recognition von Zhao, Weichao, Hu, Hezhen, Zhou, Wengang, Mao, Yunyao, Wang, Min, Li, Houqiang

Volltext

CMD: Self-supervised 3D Action Representation Learning with Cross-Modal Mutual Distillation von Mao, Yunyao, Zhou, Wengang, Lu, Zhenbo, Deng, Jiajun, Li, Houqiang

Volltext

CMT: Context-Matching-Guided Transformer for 3D Tracking in Point Clouds von Guo, Zhiyang, Mao, Yunyao, Zhou, Wengang, Wang, Min, Li, Houqiang

Volltext

MotionRL: Align Text-to-Motion Generation to Human Preferences with Multi-Reward Reinforcement Learning von Liu, Xiaoyang, Mao, Yunyao, Zhou, Wengang, Li, Houqiang

Volltext bestellen

Learning Generalizable Human Motion Generator with Reinforcement Learning von Mao, Yunyao, Liu, Xiaoyang, Zhou, Wengang, Lu, Zhenbo, Li, Houqiang

Volltext bestellen

Detect Any Shadow: Segment Anything for Video Shadow Detection von Wang, Yonghui, Zhou, Wengang, Mao, Yunyao, Li, Houqiang

Volltext bestellen

Hyper-Connections von Zhu, Defa, Huang, Hongzhi, Huang, Zihao, Zeng, Yutao, Mao, Yunyao, Wu, Banggu, Min, Qiyang, Zhou, Xun

Volltext bestellen

MASA: Motion-aware Masked Autoencoder with Semantic Alignment for Sign Language Recognition von Zhao, Weichao, Hu, Hezhen, Zhou, Wengang, Mao, Yunyao, Wang, Min, Li, Houqiang

Volltext bestellen

CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillation von Mao, Yunyao, Zhou, Wengang, Lu, Zhenbo, Deng, Jiajun, Li, Houqiang

Volltext bestellen

I$^2$MD: 3D Action Representation Learning with Inter- and Intra-modal Mutual Distillation von Mao, Yunyao, Deng, Jiajun, Zhou, Wengang, Lu, Zhenbo, Ouyang, Wanli, Li, Houqiang

Volltext bestellen

Masked Motion Predictors are Strong 3D Action Representation Learners von Mao, Yunyao, Deng, Jiajun, Zhou, Wengang, Fang, Yao, Ouyang, Wanli, Li, Houqiang

Volltext bestellen

Joint Inductive and Transductive Learning for Video Object Segmentation von Mao, Yunyao, Wang, Ning, Zhou, Wengang, Li, Houqiang

Volltext bestellen

MotionRL: Align Text-to-Motion Generation to Human Preferences with Multi-Reward Reinforcement Learning von Liu, Xiaoyang, Mao, Yunyao, Zhou, Wengang, Li, Houqiang

Volltext

Detect Any Shadow: Segment Anything for Video Shadow Detection von Wang, Yonghui, Zhou, Wengang, Mao, Yunyao, Li, Houqiang

Volltext

CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillation von Mao, Yunyao, Zhou, Wengang, Lu, Zhenbo, Deng, Jiajun, Li, Houqiang

Volltext

Hyper-Connections von Zhu, Defa, Huang, Hongzhi, Huang, Zihao, Zeng, Yutao, Mao, Yunyao, Wu, Banggu, Min, Qiyang, Zhou, Xun

Volltext

MASA: Motion-aware Masked Autoencoder with Semantic Alignment for Sign Language Recognition von Zhao, Weichao, Hu, Hezhen, Zhou, Wengang, Mao, Yunyao, Wang, Min, Li, Houqiang

Volltext

I\(^2\)MD: 3D Action Representation Learning with Inter- and Intra-modal Mutual Distillation von Mao, Yunyao, Deng, Jiajun, Zhou, Wengang, Lu, Zhenbo, Ouyang, Wanli, Li, Houqiang

Volltext

Masked Motion Predictors are Strong 3D Action Representation Learners von Mao, Yunyao, Deng, Jiajun, Zhou, Wengang, Yao, Fang, Ouyang, Wanli, Li, Houqiang

Volltext