1 citations · 2 across the 11 of their papers we have counts for
7 papers · 1 filter
ULIFLOW: Unified Latent Human-Object Interaction Flow
Wenqi Cai, Chunzhi Gu, Weichen Zhou +5
Text-conditioned 3D human--object interaction (HOI) generation remains challenging because individually plausible human and object motions do not necessarily form a coherent intera…
ProMoDD: Dataset Distillation for 3D Human Motion via Prototype-Conditioned Diffusion Models
Yijin Wei, Yawen Zou, Wenqi Cai +5
Dataset distillation (DD) aims to retain the training utility of a large dataset in a much smaller set of examples. For skeleton-based action recognition, this requires capturing d…
Dataset Distillation Based on Saliency-Driven Prototype Alignment
Yawen Zou, Wenqi Cai, Guang Li +3
Dataset distillation aims to synthesize compact datasets that can approximate the performance of full-data training while significantly reducing computational and storage costs. Ho…
Learning Emotion from Motion: Kinetic Multi-Stream Skeleton Modeling with Metadata-Conditioned Weak Label Distributions
Sosuke Suzuki, Yijin Wei, Koichiro Kamide +3
Skeleton-based emotion recognition from body motion remains challenging because emotional expressions are often characterized by subtle dynamic and relational motion cues, and hard…
Understanding Geometric Representations in Self-Supervised Vision Transformers via Subspace Intervention
Weichen Zhou, Yawen Zou, Chunzhi Gu +3
We introduce a controlled subspace intervention framework to investigate how self-supervised Vision Transformers (ViTs) encode dense geometric information. While linear probing is…
EVLF: Early Vision-Language Fusion for Generative Dataset Distillation
Wenqi Cai, Yawen Zou, Guang Li +2
Dataset distillation (DD) aims to synthesize compact training sets that enable models to achieve high accuracy with significantly fewer samples. Recent diffusion-based DD methods c…
Does Semantic Noise Initialization Transfer from Images to Videos? A Paired Diagnostic Study
Yixiao Jing, Chaoyu Zhang, Zixuan Zhong +1
Semantic noise initialization has been reported to improve robustness and controllability in image diffusion models. Whether these gains transfer to text-to-video (T2V) generation…