# Tracking Holistic Object Representations

arXiv: https://arxiv.org/abs/1907.12920 · HTML: https://mlsanity.com/paper/1907.12920/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jul 2019.

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

- [Dynamic Attention guided Multi-Trajectory Analysis for Single Object Tracking](https://mlsanity.com/paper/2103.16086/) (2021)
- [MambaEVT: Event Stream based Visual Object Tracking using State Space Model](https://mlsanity.com/paper/2408.10487/) (2024)
- [Long-Term Visual Object Tracking with Event Cameras: An Associative Memory Augmented Tracker and A Benchmark Dataset](https://mlsanity.com/paper/2403.05839/) (2024)
- [Tracking by Joint Local and Global Search: A Target-aware Attention based Approach](https://mlsanity.com/paper/2106.04840/) (2021)
- [Beyond Greedy Search: Tracking by Multi-Agent Reinforcement Learning-based Beam Search](https://mlsanity.com/paper/2205.09676/) (2022)
- [Deep 6-DoF Tracking of Unknown Objects for Reactive Grasping](https://mlsanity.com/paper/2103.05401/) (2021)
- [Rank-based verification for long-term face tracking in crowded scenes](https://mlsanity.com/paper/2107.13273/) (2021)
- [READMem: Robust Embedding Association for a Diverse Memory in Unconstrained Video Object Segmentation](https://mlsanity.com/paper/2305.12823/) (2023)
- [Sparse Regularized Correlation Filter for UAV Object Tracking with adaptive Contextual Learning and Keyfilter Selection](https://mlsanity.com/paper/2205.03627/) (2022)

## Abstract (arXiv)

Recent advances in visual tracking are based on siamese feature extractors and template matching. For this category of trackers, latest research focuses on better feature embeddings and similarity measures. In this work, we focus on building holistic object representations for tracking. We propose a framework that is designed to be used on top of previous trackers without any need for further training of the siamese network. The framework leverages the idea of obtaining additional object templates during the tracking process. Since the number of stored templates is limited, our method only keeps the most diverse ones. We achieve this by providing a new diversity measure in the space of siamese features. The obtained representation contains information beyond the ground truth object location provided to the system. It is then useful for tracking itself but also for further tasks which require a visual understanding of objects. Strong empirical results on tracking benchmarks indicate that our method can improve the performance and robustness of the underlying trackers while barely reducing their speed. In addition, our method is able to match current state-of-the-art results, while using a simpler and older network architecture and running three times faster.