Pocket-STVG: lightweight architecture for Spatio-Temporal Video Grounding
Pocket-STVG is presented, a lightweight cascade architecture that addresses STVG by combining efficient pre-trained components instead of large end-to-end models and establishing a favorable performance-efficiency trade-off for STVG.
Alberto Presta, Michal Byra, Grzegorz Stefański et al.
· 0 citations