3 papers
cs.CV2026
ByteAction: Byte-space Action Recognition Foundation Model
Fangcheng Li, Zhen Yu, Kejun Wu +2
Byte-space Action Recognition (BAR) aims to recognize human actions directly from compressed image bitstreams without any pixel decoding. By operating entirely in byte space, BAR i…
cs.CV2026
Towards Bitstream-corrupted Harsh Visual Understanding: Through Bitstream Language Modeling as Robust Semantic Priors
Chaoran Huang, Fangcheng Li, Tianyi Liu +2
Bitstream-corrupted Harsh Visual Understanding (BcHVU) aims to understand harshly degraded videos originally decoded from a severely corrupted bitstream in real-world multimedia co…
cs.CV2026
Bitstream Action Recognition is Byte Modeling
Fangcheng Li, Chaoran Huang, Tianyi Liu +5
Conventional action recognition typically relies on successful pixel decoding of the bitstream. However, bitstream corruption during storage or transmission may cause severe visual…