5 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…
Frozen History: When Temporal Losses Stop Accumulation in Learned Real-Time Supersampling
Hao Yu, Guoying Zhao
Learned real-time supersampling accumulates jittered low-resolution samples along motion vectors. Many methods use a temporal consistency loss to reduce flicker. We show that with…
Face De-Identification: A Domain-Centric Survey from Capture to Processing
Hui Wei, Hao Yu, Guoying Zhao
Face de-identification (De-ID) aims to remove or conceal personally identifiable facial features in images or videos to prevent identity recognition while preserving utility for do…
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…
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…