5 papers
Emerging Standards for Machine-to-Machine Video Coding
Md Eimran Hossain Eimon, Velibor Adzic, Hari Kalva +1
Machines are increasingly becoming the primary consumers of visual data, yet most deployments of machine-to-machine systems still rely on remote inference where pixel-based video i…
Feature Coding for Scalable Machine Vision
Md Eimran Hossain Eimon, Juan Merlos, Ashan Perera +3
Deep neural networks (DNNs) drive modern machine vision but are challenging to deploy on edge devices due to high compute demands. Traditional approaches-running the full model on-…
ROI-Packing: Efficient Region-Based Compression for Machine Vision
Md Eimran Hossain Eimon, Alena Krause, Ashan Perera +4
This paper introduces ROI-Packing, an efficient image compression method tailored specifically for machine vision. By prioritizing regions of interest (ROI) critical to end-task ac…
Efficient Feature Compression for Machines with Global Statistics Preservation
Md Eimran Hossain Eimon, Hyomin Choi, Fabien Racapé +4
The split-inference paradigm divides an artificial intelligence (AI) model into two parts. This necessitates the transfer of intermediate feature data between the two halves. Here,…
Enabling Next-Generation Consumer Experience with Feature Coding for Machines
Md Eimran Hossain Eimon, Juan Merlos, Ashan Perera +3
As consumer devices become increasingly intelligent and interconnected, efficient data transfer solutions for machine tasks have become essential. This paper presents an overview o…