3 papers
eess.AS2026
Benchmarking Neural Speech Compression from a Rate-Distortion Perspective
Jun Xu, Zhengxue Cheng, Fengxi Zhang +3
Learning-based speech compression has achieved promising low-bitrate performance, but many neural speech codecs still describe quantized latents with preset-rate discrete symbols o…
cs.CV2026
Lightweight High-Fidelity Low-Bitrate Talking Face Compression for 3D Video Conference
Jianglong Li, Jun Xu, Bingcong Lu +4
The demand for immersive and interactive communication has driven advancements in 3D video conferencing, yet achieving high-fidelity 3D talking face representation at low bitrates…
cs.CV2024
In-Context Translation: Towards Unifying Image Recognition, Processing, and Generation
Han Xue, Qianru Sun, Li Song +2
We propose In-Context Translation (ICT), a general learning framework to unify visual recognition (e.g., semantic segmentation), low-level image processing (e.g., denoising), and c…