# Multi-object Tracking via End-to-end Tracklet Searching and Ranking

arXiv: https://arxiv.org/abs/2003.02795 · HTML: https://mlsanity.com/paper/2003.02795/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Mar 2020.

## Built on by (most cited first, 3 of 3)

- [Learning a Proposal Classifier for Multiple Object Tracking](https://mlsanity.com/paper/2103.07889/) (2021)
- [Joint Spatial-Temporal and Appearance Modeling with Transformer for Multiple Object Tracking](https://mlsanity.com/paper/2205.15495/) (2022)
- [The Graph Cut Kernel for Ranked Data](https://mlsanity.com/paper/2105.12356/) (2021)

## Abstract (arXiv)

Recent works in multiple object tracking use sequence model to calculate the similarity score between the detections and the previous tracklets. However, the forced exposure to ground-truth in the training stage leads to the training-inference discrepancy problem, i.e., exposure bias, where association error could accumulate in the inference and make the trajectories drift. In this paper, we propose a novel method for optimizing tracklet consistency, which directly takes the prediction errors into account by introducing an online, end-to-end tracklet search training process. Notably, our methods directly optimize the whole tracklet score instead of pairwise affinity. With sequence model as appearance encoders of tracklet, our tracker achieves remarkable performance gain from conventional tracklet association baseline. Our methods have also achieved state-of-the-art in MOT15~17 challenge benchmarks using public detection and online settings.