CAMELTrack: Context-Aware Multi-cue ExpLoitation for Online Multi-Object Tracking

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Somers, Vladimir, Standaert, Baptiste, Joos, Victor, Alahi, Alexandre, De Vleeschouwer, Christophe
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913816346886144
author Somers, Vladimir
Standaert, Baptiste
Joos, Victor
Alahi, Alexandre
De Vleeschouwer, Christophe
author_facet Somers, Vladimir
Standaert, Baptiste
Joos, Victor
Alahi, Alexandre
De Vleeschouwer, Christophe
contents Online multi-object tracking has been recently dominated by tracking-by-detection (TbD) methods, where recent advances rely on increasingly sophisticated heuristics for tracklet representation, feature fusion, and multi-stage matching. The key strength of TbD lies in its modular design, enabling the integration of specialized off-the-shelf models like motion predictors and re-identification. However, the extensive usage of human-crafted rules for temporal associations makes these methods inherently limited in their ability to capture the complex interplay between various tracking cues. In this work, we introduce CAMEL, a novel association module for Context-Aware Multi-Cue ExpLoitation, that learns resilient association strategies directly from data, breaking free from hand-crafted heuristics while maintaining TbD's valuable modularity. At its core, CAMEL employs two transformer-based modules and relies on a novel association-centric training scheme to effectively model the complex interactions between tracked targets and their various association cues. Unlike end-to-end detection-by-tracking approaches, our method remains lightweight and fast to train while being able to leverage external off-the-shelf models. Our proposed online tracking pipeline, CAMELTrack, achieves state-of-the-art performance on multiple tracking benchmarks. Our code is available at https://github.com/TrackingLaboratory/CAMELTrack.
format Preprint
id arxiv_https___arxiv_org_abs_2505_01257
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CAMELTrack: Context-Aware Multi-cue ExpLoitation for Online Multi-Object Tracking
Somers, Vladimir
Standaert, Baptiste
Joos, Victor
Alahi, Alexandre
De Vleeschouwer, Christophe
Computer Vision and Pattern Recognition
Machine Learning
Online multi-object tracking has been recently dominated by tracking-by-detection (TbD) methods, where recent advances rely on increasingly sophisticated heuristics for tracklet representation, feature fusion, and multi-stage matching. The key strength of TbD lies in its modular design, enabling the integration of specialized off-the-shelf models like motion predictors and re-identification. However, the extensive usage of human-crafted rules for temporal associations makes these methods inherently limited in their ability to capture the complex interplay between various tracking cues. In this work, we introduce CAMEL, a novel association module for Context-Aware Multi-Cue ExpLoitation, that learns resilient association strategies directly from data, breaking free from hand-crafted heuristics while maintaining TbD's valuable modularity. At its core, CAMEL employs two transformer-based modules and relies on a novel association-centric training scheme to effectively model the complex interactions between tracked targets and their various association cues. Unlike end-to-end detection-by-tracking approaches, our method remains lightweight and fast to train while being able to leverage external off-the-shelf models. Our proposed online tracking pipeline, CAMELTrack, achieves state-of-the-art performance on multiple tracking benchmarks. Our code is available at https://github.com/TrackingLaboratory/CAMELTrack.
title CAMELTrack: Context-Aware Multi-cue ExpLoitation for Online Multi-Object Tracking
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2505.01257