# Context-aware Deep Feature Compression for High-speed Visual Tracking

arXiv: https://arxiv.org/abs/1803.10537 · HTML: https://mlsanity.com/paper/1803.10537/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Mar 2018.

## Built on by (most cited first, 8 of 8)

- [Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlook](https://mlsanity.com/paper/2112.02838/) (2021)
- [Towards Real-World Visual Tracking with Temporal Contexts](https://mlsanity.com/paper/2308.10330/) (2023)
- [Prototype-based Cross-Modal Object Tracking](https://mlsanity.com/paper/2312.14471/) (2023)
- [Distilling Channels for Efficient Deep Tracking](https://mlsanity.com/paper/2409.11785/) (2024)
- [MFST: Multi-Features Siamese Tracker](https://mlsanity.com/paper/2103.00810/) (2021)
- [Multiple Convolutional Features in Siamese Networks for Object Tracking](https://mlsanity.com/paper/2103.01222/) (2021)
- [ParaDiS: Parallelly Distributable Slimmable Neural Networks](https://mlsanity.com/paper/2110.02724/) (2021)
- [Physics-Informed Tracking (PIT)](https://mlsanity.com/paper/2604.16895/) (2026)

## Abstract (arXiv)

We propose a new context-aware correlation filter based tracking framework to achieve both high computational speed and state-of-the-art performance among real-time trackers. The major contribution to the high computational speed lies in the proposed deep feature compression that is achieved by a context-aware scheme utilizing multiple expert auto-encoders; a context in our framework refers to the coarse category of the tracking target according to appearance patterns. In the pre-training phase, one expert auto-encoder is trained per category. In the tracking phase, the best expert auto-encoder is selected for a given target, and only this auto-encoder is used. To achieve high tracking performance with the compressed feature map, we introduce extrinsic denoising processes and a new orthogonality loss term for pre-training and fine-tuning of the expert auto-encoders. We validate the proposed context-aware framework through a number of experiments, where our method achieves a comparable performance to state-of-the-art trackers which cannot run in real-time, while running at a significantly fast speed of over 100 fps.