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

arXiv: https://arxiv.org/abs/2609.39832 · HTML: https://mlsanity.com/paper/2609.39832/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 14 references that are in the map.
- First posted on arXiv 30 Sep 2026.

## Builds on (most cited first, 10 of 10)

- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [ByteTrack: Multi-Object Tracking by Associating Every Detection Box](https://mlsanity.com/paper/2110.06864/) (2021)
- [SelectiveNet: A Deep Neural Network with an Integrated Reject Option](https://mlsanity.com/paper/1901.09192/) (2019)
- [TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement](https://mlsanity.com/paper/2306.08637/) (2023)
- [Mask Scoring R-CNN](https://mlsanity.com/paper/1903.00241/) (2019)
- [TAP-Vid: A Benchmark for Tracking Any Point in a Video](https://mlsanity.com/paper/2211.03726/) (2022)
- [TrackNet: A Deep Learning Network for Tracking High-speed and Tiny Objects in Sports Applications](https://mlsanity.com/paper/1907.03698/) (2019)
- [When AUC meets DRO: Optimizing Partial AUC for Deep Learning with Non-Convex Convergence Guarantee](https://mlsanity.com/paper/2203.00176/) (2022)
- [MFTIQ: Multi-Flow Tracker with Independent Matching Quality Estimation](https://mlsanity.com/paper/2411.09551/) (2024)
- [RacketVision: A Multiple Racket Sports Benchmark for Unified Ball and Racket Analysis](https://mlsanity.com/paper/2511.17045/) (2025)

## Abstract (arXiv)

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.