Liangtao Shi

attention mechanism (1) visual object tracking (1) multimodal learning (1) object tracking (1) parameter-efficient transfer learning (1) visual tracking (1) autoregressive model (1) multimodal alignment (1) multi-scale feature (1) visual-language alignment (1) referring expression comprehension (1) transformer encoder (1) parameter efficient tuning (1) visual language (1) multi-scale information (1) spatio-temporal transformer (1) autoregressive queries (1) dynamic prior adapter (1) spatio-temporal token (1) template update (1)