Deep video compression based on Long-range Temporal Context Learning

K Wu, Z Li, Y Yang, Q Liu - Computer Vision and Image Understanding, 2024 - Elsevier
Video compression allows for efficient storage and transmission of data, benefiting imaging
and vision applications, eg computational imaging, photography, and displays by delivering …

End-to-end Deep Video Compression Based on Hierarchical Temporal Context Learning

K Wu, Z Li, Y Yang, Q Liu… - IEEE Transactions on …, 2025 - ieeexplore.ieee.org
Emerging learning-based video compression suffers from error propagation in long group of
pictures (GOP), yielding limited coding performance. To address this problem, a novel end …

Multi-scale Dynamic Fusion for Visible-Infrared Person Re-Identification

S Wang, Y Wang, R Qiao, K Wu, CW Lin, C Cai - ACM Transactions on … - dl.acm.org
Visible-infrared person re-identification (VI-ReID) aims to match persons across visible and
infrared modalities; however, its performance is prone to complex dynamic scenes, such as …