3 papers
cs.CV2024
City Scene Super-Resolution via Geometric Error Minimization
Zhengyang Lu, Feng Wang
Super-resolution techniques are crucial in improving image granularity, particularly in complex urban scenes, where preserving geometric structures is vital for data-informed cultu…
cs.CV2023
Butterfly: Multiple Reference Frames Feature Propagation Mechanism for Neural Video Compression
Feng Wang, Haihang Ruan, Fei Xiong +3
Using more reference frames can significantly improve the compression efficiency in neural video compression. However, in low-latency scenarios, most existing neural video compress…
cs.CR2021
Tracing Text Provenance via Context-Aware Lexical Substitution
Xi Yang, Jie Zhang, Kejiang Chen +4
Text content created by humans or language models is often stolen or misused by adversaries. Tracing text provenance can help claim the ownership of text content or identify the ma…