AI RESEARCH

Probing Deep into Temporal Profile Makes the Infrared Small Target Detector Much Better

arXiv CS.CV

ArXi:2506.12766v5 Announce Type: replace Infrared small target (IRST) detection is challenging in simultaneously achieving precise, robust, and efficient performance due to extremely dim targets and strong interference. Current learning-based methods attempt to leverage ``more" information from both the spatial and the short-term temporal domains, but suffer from unreliable performance under complex conditions while incurring computational redundancy. In this paper, we explore the `` essential" information from a crucial domain for the detection.