# Online Multiple Pedestrians Tracking using Deep Temporal Appearance Matching Association

arXiv: https://arxiv.org/abs/1907.00831 · HTML: https://mlsanity.com/paper/1907.00831/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jul 2019.

## Built on by (most cited first, 9 of 9)

- [Simple Cues Lead to a Strong Multi-Object Tracker](https://mlsanity.com/paper/2206.04656/) (2022)
- [Tracking Pedestrian Heads in Dense Crowd](https://mlsanity.com/paper/2103.13516/) (2021)
- [Local Metrics for Multi-Object Tracking](https://mlsanity.com/paper/2104.02631/) (2021)
- [Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey](https://mlsanity.com/paper/2205.10766/) (2022)
- [Robust Multi-Object Tracking by Marginal Inference](https://mlsanity.com/paper/2208.03727/) (2022)
- [Can Deep Learning be Applied to Model-Based Multi-Object Tracking?](https://mlsanity.com/paper/2202.07909/) (2022)
- [Single-Shot and Multi-Shot Feature Learning for Multi-Object Tracking](https://mlsanity.com/paper/2311.10382/) (2023)
- [Transformer-Based Multi-Object Smoothing with Decoupled Data Association and Smoothing](https://mlsanity.com/paper/2312.17261/) (2023)
- [Development of a Realistic Crowd Simulation Environment for Fine-grained Validation of People Tracking Methods](https://mlsanity.com/paper/2304.13403/) (2023)

## Abstract (arXiv)

In online multi-target tracking, modeling of appearance and geometric similarities between pedestrians visual scenes is of great importance. The higher dimension of inherent information in the appearance model compared to the geometric model is problematic in many ways. However, due to the recent success of deep-learning-based methods, handling of high-dimensional appearance information becomes feasible. Among many deep neural networks, Siamese network with triplet loss has been widely adopted as an effective appearance feature extractor. Since the Siamese network can extract the features of each input independently, one can update and maintain target-specific features. However, it is not suitable for multi-target settings that require comparison with other inputs. To address this issue, we propose a novel track appearance model based on the joint-inference network. The proposed method enables a comparison of two inputs to be used for adaptive appearance modeling and contributes to the disambiguation of target-observation matching and to the consolidation of identity consistency. Diverse experimental results support the effectiveness of our method. Our work was recognized as the 3rd-best tracker in BMTT MOTChallenge 2019, held at CVPR2019. The code is available at https://github.com/yyc9268/Deep-TAMA.