DAWN: Dual Augmented Memory Network for Unsupervised Video Object Tracking

by   Zhenmei Shi, et al.

Psychological studies have found that human visual tracking system involves learning, memory, and planning. Despite recent successes, not many works have focused on memory and planning in deep learning based tracking. We are thus interested in memory augmented network, where an external memory remembers the evolving appearance of the target (foreground) object without backpropagation for updating weights. Our Dual Augmented Memory Network (DAWN) is unique in remembering both target and background, and using an improved attention LSTM memory to guide the focus on memorized features. DAWN is effective in unsupervised tracking in handling total occlusion, severe motion blur, abrupt changes in target appearance, multiple object instances, and similar foreground and background features. We present extensive quantitative and qualitative experimental comparison with state-of-the-art methods including top contenders in recent VOT challenges. Notably, despite the straightforward implementation, DAWN is ranked third in both VOT2016 and VOT2017 challenges with excellent success rate among all VOT fast trackers running at fps > 10 in unsupervised tracking in both challenges. We propose DAWN-RPN, where we simply augment our memory and attention LSTM modules to the state-of-the-art SiamRPN, and report immediate performance gain, thus demonstrating DAWN can work well with and directly benefit other models to handle difficult cases as well.


page 1

page 7

page 8


MAVOT: Memory-Augmented Video Object Tracking

We introduce a one-shot learning approach for video object tracking. The...

UHP-SOT: An Unsupervised High-Performance Single Object Tracker

An unsupervised online object tracking method that exploits both foregro...

Learning Dynamic Memory Networks for Object Tracking

Template-matching methods for visual tracking have gained popularity rec...

Unified Graph based Multi-Cue Feature Fusion for Robust Visual Tracking

Visual Tracking is a complex problem due to unconstrained appearance var...

DMV: Visual Object Tracking via Part-level Dense Memory and Voting-based Retrieval

We propose a novel memory-based tracker via part-level dense memory and ...

Multiple-Vehicle Tracking in the Highway Using Appearance Model and Visual Object Tracking

In recent decades, due to the groundbreaking improvements in machine vis...

PeTra: A Sparsely Supervised Memory Model for People Tracking

We propose PeTra, a memory-augmented neural network designed to track en...

Please sign up or login with your details

Forgot password? Click here to reset