AI RESEARCH

COAL: Counterfactual and Observation-Enhanced Alignment Learning for Discriminative Referring Multi-Object Tracking

arXiv CS.CV

ArXi:2605.14795v1 Announce Type: new Referring Multi-Object Tracking (RMOT) faces a fundamental structural contradiction between the high-discriminability demand and the sparse semantic supervision. This mismatch is particularly acute in highly homogeneous scenarios that require fine-grained discrimination over complex compositional semantics. However, under sparse supervision, models overfit to salient yet insufficient cues, thereby encouraging shortcut learning and semantic collapse.