4 papers
Temporal Prototyping and Hierarchical Alignment for Unsupervised Video-based Visible-Infrared Person Re-Identification
Zhiyong Li, Wei Jiang, Haojie Liu +3
Visible-infrared person re-identification (VI-ReID) enables cross-modality identity matching for all-day surveillance, yet existing methods predominantly focus on the image level o…
InterDyad: Interactive Dyadic Speech-to-Video Generation by Querying Intermediate Visual Guidance
Dongwei Pan, Longwei Guo, Jiazhi Guan +7
Despite progress in speech-to-video synthesis, existing methods often struggle to capture cross-individual dependencies and provide fine-grained control over reactive behaviors in…
Distilling the Past: Information-Dense and Style-Aware Replay for Lifelong Person Re-Identification
Mingyu Wang, Wei Jiang, Haojie Liu +2
Lifelong person re-identification (LReID) aims to continuously adapt to new domains while mitigating catastrophic forgetting. While replay-based methods effectively alleviate forge…
HumanCM: One Step Human Motion Prediction
Liu Haojie, Gao Suixiang
We present HumanCM, a one-step human motion prediction framework built upon consistency models. Instead of relying on multi-step denoising as in diffusion-based methods, HumanCM pe…