2 papers
eess.IV2026
CI-ICM: Channel Importance-driven Learned Image Coding for Machines
Yun Zhang, Junle Liu, Huan Zhang +3
Traditional human vision-centric image compression methods are suboptimal for machine vision centric compression due to different visual properties and feature characteristics. To…
cs.CV2025
Multiscale Feature Importance-based Bit Allocation for End-to-End Feature Coding for Machines
Junle Liu, Yun Zhang, Zixi Guo
Feature Coding for Machines (FCM) aims to compress intermediate features effectively for remote intelligent analytics, which is crucial for future intelligent visual applications.…