| --- |
| license: apache-2.0 |
| arxiv: 2505.01257 |
| --- |
| |
| # CAMELTrack |
| ## Context-Aware Multi-cue ExpLoitation for Online Multi-Object Tracking |
|
|
| [](https://arxiv.org/abs/2505.01257) |
| [](https://paperswithcode.com/sota/multi-object-tracking-on-dancetrack?p=cameltrack-context-aware-multi-cue-1) |
| [](https://paperswithcode.com/sota/multi-object-tracking-on-sportsmot?p=cameltrack-context-aware-multi-cue-1) |
| [](https://paperswithcode.com/sota/multi-object-tracking-on-mot17?p=cameltrack-context-aware-multi-cue-1) |
| <!--- |
| Add PoseTrack21 & BEE24 |
| ---> |
|
|
| >**[CAMELTrack: Context-Aware Multi-cue ExpLoitation for Online Multi-Object Tracking](https://arxiv.org/abs/2505.01257)** |
| > |
| >Vladimir Somers, Baptiste Standaert, Victor Joos, Alexandre Alahi, Christophe De Vleeschouwer |
| > |
| >[*arxiv 2505.01257*](https://arxiv.org/abs/2505.01257) |
|
|
| **CAMELTrack** is an **Online Multi-Object Tracker** that learns to associate detections without hand-crafted heuristics. |
| It combines multiple tracking cues through a lightweight, fully trainable module and achieves state-of-the-art performance while |
| staying modular and fast. |
|
|
|  |
|
|
| ## 📄 Abstract |
| **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. |
