Adaptive Bitrate
Adaptive bitrate (ABR) technology dynamically adjusts the data rate of digital media streams (video, audio, images) to optimize quality and resource utilization based on network conditions and device capabilities. Current research focuses on improving ABR algorithms through reinforcement learning, neural network architectures (like VQGAN and transformers), and novel approaches such as prompt streaming for video. These advancements aim to enhance user experience by reducing buffering, improving perceptual quality, and increasing energy efficiency in various applications, from mobile video streaming to high-resolution content delivery.
Papers
Adapting Learned Image Codecs to Screen Content via Adjustable Transformations
H. Burak Dogaroglu, A. Burakhan Koyuncu, Atanas Boev, Elena Alshina, Eckehard Steinbach
Bit Rate Matching Algorithm Optimization in JPEG-AI Verification Model
Panqi Jia, A. Burakhan Koyuncu, Jue Mao, Ze Cui, Yi Ma, Tiansheng Guo, Timofey Solovyev, Alexander Karabutov, Yin Zhao, Jing Wang, Elena Alshina, Andre Kaup