Drift-Resilient Temporal Priors for Visual Tracking

arXiv cs.CV / 4/6/2026

💬 OpinionSignals & Early TrendsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper proposes DTPTrack, a lightweight module to make multi-frame visual trackers more resilient to model drift caused by naive aggregation of noisy historical predictions.
DTPTrack uses a Temporal Reliability Calibrator (TRC) to learn per-frame reliability scores for historical states, filtering noise while anchoring to the ground-truth template.
It also introduces a Temporal Guidance Synthesizer (TGS) that converts the calibrated history into a compact set of dynamic temporal priors to guide future predictions.
Experiments show DTPTrack provides consistent, significant gains when integrated into multiple existing architectures (OSTrack, ODTrack, and LoRAT), including a new best model that achieves 77.5% Success on LaSOT and 80.3% AO on GOT-10k.

Abstract

Temporal information is crucial for visual tracking, but existing multi-frame trackers are vulnerable to model drift caused by naively aggregating noisy historical predictions. In this paper, we introduce DTPTrack, a lightweight and generalizable module designed to be seamlessly integrated into existing trackers to suppress drift. Our framework consists of two core components: (1) a Temporal Reliability Calibrator (TRC) mechanism that learns to assign a per-frame reliability score to historical states, filtering out noise while anchoring on the ground-truth template; and (2) a Temporal Guidance Synthesizer (TGS) module that synthesizes this calibrated history into a compact set of dynamic temporal priors to provide predictive guidance. To demonstrate its versatility, we integrate DTPTrack into three diverse tracking architectures--OSTrack, ODTrack, and LoRAT-and show consistent, significant performance gains across all baselines. Our best-performing model, built upon an extended LoRATv2 backbone, sets a new state-of-the-art on several benchmarks, achieving a 77.5% Success rate on LaSOT and an 80.3% AO on GOT-10k.