Most video compression methods aim to improve the decoded video visual quality, instead
of particularly guaranteeing the semantic-completeness, which deteriorates downstream …

Prior research on deep video compression (DVC) for machine tasks typically necessitates
training a unique codec for each specific task mandating a dedicated decoder per task. In …

Recently, the field of Image Coding for Machines (ICM) has garnered heightened interest
and significant advances thanks to the rapid progress of learning-based techniques for …

Image compression techniques typically focus on compressing rectangular images for
human consumption, however, resulting in transmitting redundant content for downstream …

Image compression for machine and human vision (ICMH) has gained increasing attention
in recent years. Existing ICMH methods are limited by high training and storage overheads …

Unsupervised video semantic compression (UVSC), ie, compressing videos to better
support various analysis tasks, has recently garnered attention. However, the semantic …

Recently, more and more images are compressed and sent to the back-end devices for
machine analysis tasks (eg, object detection) instead of being purely watched by humans …

Video compression is indispensable to most video analysis systems. Despite saving the
transportation bandwidth, it also deteriorates downstream video understanding tasks …

Most video compression methods focus on human visual perception, neglecting semantic
preservation. This leads to severe semantic loss during the compression, hampering …