SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2206.04656 · 2022

Simple Cues Lead to a Strong Multi-Object Tracker

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

For a long time, the most common paradigm in Multi-Object Tracking was tracking-by-detection (TbD), where objects are first detected and then associated over video frames. For association, most models resourced to motion and appearance cues, e.g., re-identification networks. Recent approaches based on attention propose to learn the cues in a data-driven manner, showing impressive results. In this paper, we ask ourselves whether simple good old TbD methods are also capable of achieving the performance of end-to-end models. To this end, we propose two key ingredients that allow a standard re-identification network to excel at appearance-based tracking. We extensively analyse its failure cases, and show that a combination of our appearance features with a simple motion model leads to strong tracking results. Our tracker generalizes to four public datasets, namely MOT17, MOT20, BDD100k, and DanceTrack, achieving state-of-the-art performance. https://github.com/dvl-tum/GHOST.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2206.04656")
get_code_for_paper("2206.04656")
have("2206.04656")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2206.04656.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2206.04656.svg)](https://syntology.ai/paper/2206.04656)

Connect an agent — have() is free.