1st Place Solution to ECCV-TAO-2020: Detect and Represent Any Object for Tracking

by   Fei Du, et al.

We extend the classical tracking-by-detection paradigm to this tracking-any-object task. Solid detection results are first extracted from TAO dataset. Some state-of-the-art techniques like BAlanced-Group Softmax (BAGS<cit.>) and DetectoRS<cit.> are integrated during detection. Then we learned appearance features to represent any object by training feature learning networks. We ensemble several models for improving detection and feature representation. Simple linking strategies with most similar appearance features and tracklet-level post association module are finally applied to generate final tracking results. Our method is submitted as AOA on the challenge website.


page 1

page 2

page 3

page 4


Learning to associate detections for real-time multiple object tracking

With the recent advances in the object detection research field, trackin...

POI: Multiple Object Tracking with High Performance Detection and Appearance Feature

Detection and learning based appearance feature play the central role in...

Joint Detection and Multi-Object Tracking with Graph Neural Networks

Object detection and data association are critical components in multi-o...

1st Place Solutions for Waymo Open Dataset Challenges – 2D and 3D Tracking

This technical report presents the online and real-time 2D and 3D multi-...

DEFT: Detection Embeddings for Tracking

Most modern multiple object tracking (MOT) systems follow the tracking-b...

Dense Scene Multiple Object Tracking with Box-Plane Matching

Multiple Object Tracking (MOT) is an important task in computer vision. ...

Ocean Eddy Identification and Tracking using Neural Networks

Global climate change plays an essential role in our daily life and is n...

Code Repositories


1st Place Solution to ECCV-TAO-2020: Detect and Represent Any Object for Tracking

view repo