P-SRM: Selective Recovery of Rejected Predictions in Visual Tracking

2026-09-30

AI Summary

This study addresses the loss of valid information in visual tracking caused by rejection mechanisms erroneously discarding correct candidate bounding boxes. To mitigate this, we propose P-SRM, a method that introduces a novel post-rejection verification mechanism. By integrating spatial response analysis, historical state modeling, and decision margin assessment for multimodal re-ranking, P-SRM selectively recovers and reuses rejected candidates, thereby overcoming the limitations of conventional unidirectional filtering. Extensive experiments demonstrate that P-SRM significantly improves both the ranking quality of rejected candidates and overall tracking accuracy across six trackers and four benchmark datasets, validating the generalizability and effectiveness of the proposed framework.

Abstract

Many visual tracking methods use rejection mechanisms to suppress unreliable predictions. However, these mechanisms can also reject correctly localized candidates, leaving useful information unused. We investigate how to identify and recover these candidates while preserving native accepted outputs and candidate coordinates. To this end, we propose P-SRM (Post-rejection Selective Recovery Method), which combines spatial responses, past accepted states, and native decision margins to reassess candidates and selectively restore reliable predictions. We evaluate P-SRM on six trackers and four datasets spanning category-specific, point, and generic object tracking. Across all nine configurations, P-SRM improves rejected-candidate ranking and overall tracking performance. These results show that post-rejection verification can identify and recover useful predictions discarded by native rejection, demonstrating the value of reusing rejected information. Project repository: https://github.com/PalestyHR/P-SRM.

Problem

• Visual Tracking
• Rejection Mechanism
• Candidate Recovery
• Post-rejection Verification

Innovation

• Visual Tracking
• Rejection Mechanism
• Selective Recovery
• Post-rejection Verification
• Candidate Reassessment