8 papers
IRG-MotionLLM: Interleaving Motion Generation, Assessment and Refinement for Text-to-Motion Generation
Yuan-Ming Li, Qize Yang, Nan Lei +5
Recent advances in motion-aware large language models have shown remarkable promise for jointly learning motion understanding and generation knowledge. However, these models typica…
Temporal Continual Learning with Prior Compensation for Human Motion Prediction
Jianwei Tang, Jiangxin Sun, Xiaotong Lin +3
Human Motion Prediction (HMP) aims to predict future poses at different moments according to past motion sequences. Previous approaches have treated the prediction of various momen…
Modeling Multiple Normal Action Representations for Error Detection in Procedural Tasks
Wei-Jin Huang, Yuan-Ming Li, Zhi-Wei Xia +4
Error detection in procedural activities is essential for consistent and correct outcomes in AR-assisted and robotic systems. Existing methods often focus on temporal ordering erro…
Progressive Human Motion Generation Based on Text and Few Motion Frames
Ling-An Zeng, Gaojie Wu, Ancong Wu +2
Although existing text-to-motion (T2M) methods can produce realistic human motion from text description, it is still difficult to align the generated motion with the desired postur…
TechCoach: Towards Technical-Point-Aware Descriptive Action Coaching
Yuan-Ming Li, An-Lan Wang, Kun-Yu Lin +4
To guide a learner in mastering action skills, it is crucial for a coach to 1) reason through the learner's action execution and technical points (TechPoints), and 2) provide detai…
Panorama Generation From NFoV Image Done Right
Dian Zheng, Cheng Zhang, Xiao-Ming Wu +4
Generating 360-degree panoramas from narrow field of view (NFoV) image is a promising computer vision task for Virtual Reality (VR) applications. Existing methods mostly assess the…