SOURCE-LINKED INTELLIGENCE

Continuous Token-Level Spatio-Temporal Context Modeling for Visual Object Tracking

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Spatio-temporal context has become increasingly crucial for visual tracking. However, most existing approaches extract spatio-temporal cues via discrete sampling strategies, which inherently deviate from the continuity of spatio-temporal context, thereby deteriorating tracking performance. To address this challenge, we propose TLCTrack, a novel tracking framework that models token-level spatio-temporal context through continuously updated salient tokens, enabling more accurate target representation. Specifically, TLCTrack incorporates three components: Masked Unidirectional Attention (MUA), Sp

Read original source ↗ Open in workspace

recordType

paper

region

Global