# Transferring Rich Feature Hierarchies for Robust Visual Tracking

arXiv: https://arxiv.org/abs/1501.04587 · HTML: https://mlsanity.com/paper/1501.04587/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jan 2015.

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

- [Learning Open-World Object Proposals without Learning to Classify](https://mlsanity.com/paper/2108.06753/) (2021)
- [Densely Connected Recurrent Residual (Dense R2UNet) Convolutional Neural Network for Segmentation of Lung CT Images](https://mlsanity.com/paper/2102.00663/) (2021)
- [Autonomous Deep Quality Monitoring in Streaming Environments](https://mlsanity.com/paper/2106.13955/) (2021)
- [Tunable Hybrid Proposal Networks for the Open World](https://mlsanity.com/paper/2208.11050/) (2022)
- [Visual Object Tracking across Diverse Data Modalities: A Review](https://mlsanity.com/paper/2412.09991/) (2024)
- [Continuity-Discrimination Convolutional Neural Network for Visual Object Tracking](https://mlsanity.com/paper/2104.08739/) (2021)
- [Computational models of object motion detectors accelerated using FPGA technology](https://mlsanity.com/paper/2310.06842/) (2023)
- [Object Tracking in a 360o View: A Novel Perspective on Bridging the Gap to Biomedical Advancements](https://mlsanity.com/paper/2412.01119/) (2024)

## Abstract (arXiv)

Convolutional neural network (CNN) models have demonstrated great success in various computer vision tasks including image classification and object detection. However, some equally important tasks such as visual tracking remain relatively unexplored. We believe that a major hurdle that hinders the application of CNN to visual tracking is the lack of properly labeled training data. While existing applications that liberate the power of CNN often need an enormous amount of training data in the order of millions, visual tracking applications typically have only one labeled example in the first frame of each video. We address this research issue here by pre-training a CNN offline and then transferring the rich feature hierarchies learned to online tracking. The CNN is also fine-tuned during online tracking to adapt to the appearance of the tracked target specified in the first video frame. To fit the characteristics of object tracking, we first pre-train the CNN to recognize what is an object, and then propose to generate a probability map instead of producing a simple class label. Using two challenging open benchmarks for performance evaluation, our proposed tracker has demonstrated substantial improvement over other state-of-the-art trackers.