Algorithms for canvas-based attention scheduling with resizing

• Main Authors: HU, Yigong, GOKARN, Ila, LIU, Shengzhong, MISRA, Archan, ADBELZAHER, Tarek
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Quantization (signal); Limiting; Scheduling algorithms; Pipelines; Streaming media; Real-time systems; Scheduling; Artificial Intelligence and Robotics; Theory and Algorithms
• Online Access: https://ink.library.smu.edu.sg/sis_research/9226; https://ink.library.smu.edu.sg/context/sis_research/article/10229/viewcontent/RTAS2024_CanvasReisizing_CameraReady.pdf
• Institution: Singapore Management University

Canvas-based attention scheduling was recently pro-posed to improve the efficiency of real-time machine perception systems. This framework introduces a notion of focus locales, referring to those areas where the attention of the inference system should “allocate its attention”. Data from these local...