4 papers
DIME: Scaling Facial Representation Learning via Differential Masked Autoencoding
Hao Yu, Haoyu Chen, Hui Wei +3
Scaling up data and model capacity has driven substantial progress in visual representation learning. However, conventional pretext tasks exhibit diminishing returns on fine-graine…
Attentive Convolution: Unifying the Expressivity of Self-Attention with Convolutional Efficiency
Hao Yu, Haoyu Chen, Yan Jiang +4
Self-attention (SA) has become the cornerstone of modern vision backbones for its powerful expressivity over traditional Convolutions (Conv). However, its quadratic complexity rema…
MagicPortrait: Temporally Consistent Face Reenactment with 3D Geometric Guidance
Mengting Wei, Yante Li, Tuomas Varanka +2
In this study, we propose a method for video face reenactment that integrates a 3D face parametric model into a latent diffusion framework, aiming to improve shape consistency and…
From Laboratory to Real World: A New Benchmark Towards Privacy-Preserved Visible-Infrared Person Re-Identification
Yan Jiang, Hao Yu, Mengting Wei +4
Aiming to match pedestrian images captured under varying lighting conditions, visible-infrared person re-identification (VI-ReID) has drawn intensive research attention and achieve…