7 papers · 1 filter
MotionGRPO: Overcoming Low Intra-Group Diversity in GRPO-Based Egocentric Motion Recovery
Nanjie Yao, Junlong Ren, Wenhao Shen +1
This paper studies full-body 3D human motion recovery from head-mounted device signals. Existing diffusion-based methods often rely on global distribution matching, leading to loca…
FastAnimate: Towards Learnable Template Construction and Pose Deformation for Fast 3D Human Avatar Animation
Jian Shu, Nanjie Yao, Gangjian Zhang +3
3D human avatar animation aims at transforming a human avatar from an arbitrary initial pose to a specified target pose using deformation algorithms. Existing approaches typically…
Enhanced Partially Relevant Video Retrieval through Inter- and Intra-Sample Analysis with Coherence Prediction
Junlong Ren, Gangjian Zhang, Yu Hu +3
Partially Relevant Video Retrieval (PRVR) aims to retrieve the target video that is partially relevant to the text query. The primary challenge in PRVR arises from the semantic asy…
WaMo: Wavelet-Enhanced Multi-Frequency Trajectory Analysis for Fine-Grained Text-Motion Retrieval
Junlong Ren, Gangjian Zhang, Honghao Fu +2
Text-Motion Retrieval (TMR) aims to retrieve 3D motion sequences semantically relevant to text descriptions. However, matching 3D motions with text remains highly challenging, prim…
Enhanced Cross-modal 3D Retrieval via Tri-modal Reconstruction
Junlong Ren, Hao Wang
Cross-modal 3D retrieval is a critical yet challenging task, aiming to achieve bi-directional retrieval between 3D and text modalities. Current methods predominantly rely on a cert…
SCA3D: Enhancing Cross-modal 3D Retrieval via 3D Shape and Caption Paired Data Augmentation
Junlong Ren, Hao Wu, Hui Xiong +1
The cross-modal 3D retrieval task aims to achieve mutual matching between text descriptions and 3D shapes. This has the potential to enhance the interaction between natural languag…