Preprint
Aug 2026
Pre-Decoding Acoustic Triage for Budgeted Vision-Language Captioning of Untrimmed Egocentric Video
This work proposes audio-first triage: select windows using the lightest modality, scored before any video frame is decoded, so the approach composes naturally with token compression or quantization.
Masoud Jalayer, Changyi Li, Yu Xiao
· 0 citations