10 papers
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…
Label-Consistent Dataset Distillation with Detector-Guided Refinement
Yawen Zou, Guang Li, Zi Wang +2
Dataset distillation (DD) aims to generate a compact yet informative dataset that achieves performance comparable to the original dataset, thereby reducing demands on storage and c…