# Re3 : Real-Time Recurrent Regression Networks for Visual Tracking of Generic Objects

## TL;DR

Re3 is a real-time deep learning-based object tracker that efficiently adapts to new observations, tracks at 150 FPS, and handles occlusion better than comparable methods by incorporating temporal information and updating its model on the fly.

## Contribution

The paper introduces Re3, a lightweight, generic, and real-time object tracker that updates its appearance model efficiently during tracking, unlike prior methods that are limited to specific objects or require retraining.

## Key findings

- Tracks at 150 FPS in real-time.
- Achieves competitive results on benchmark datasets.
- Handles temporary occlusion more effectively than other trackers.

## Abstract

Robust object tracking requires knowledge and understanding of the object being tracked: its appearance, its motion, and how it changes over time. A tracker must be able to modify its underlying model and adapt to new observations. We present Re3, a real-time deep object tracker capable of incorporating temporal information into its model. Rather than focusing on a limited set of objects or training a model at test-time to track a specific instance, we pretrain our generic tracker on a large variety of objects and efficiently update on the fly; Re3 simultaneously tracks and updates the appearance model with a single forward pass. This lightweight model is capable of tracking objects at 150 FPS, while attaining competitive results on challenging benchmarks. We also show that our method handles temporary occlusion better than other comparable trackers using experiments that directly measure performance on sequences with occlusion.