# Post-Hoc MOTS: Exploring the Capabilities of Time-Symmetric Multi-Object Tracking

arXiv: https://arxiv.org/abs/2412.08313 · HTML: https://mlsanity.com/paper/2412.08313/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 28 references that are in the map.
- First posted on arXiv 11 Dec 2024.

## Builds on (most cited first, 4 of 4)

- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Neural Kalman Filtering](https://mlsanity.com/paper/2102.10021/) (2021)
- [Enhancing Cell Tracking with a Time-Symmetric Deep Learning Approach](https://mlsanity.com/paper/2308.03887/) (2023)

## Abstract (arXiv)

Temporal forward-tracking has been the dominant approach for multi-object segmentation and tracking (MOTS). However, a novel time-symmetric tracking methodology has recently been introduced for the detection, segmentation, and tracking of budding yeast cells in pre-recorded samples. Although this architecture has demonstrated a unique perspective on stable and consistent tracking, as well as missed instance re-interpolation, its evaluation has so far been largely confined to settings related to videomicroscopic environments. In this work, we aim to reveal the broader capabilities, advantages, and potential challenges of this architecture across various specifically designed scenarios, including a pedestrian tracking dataset. We also conduct an ablation study comparing the model against its restricted variants and the widely used Kalman filter. Furthermore, we present an attention analysis of the tracking architecture for both pretrained and non-pretrained models