Learning Association via Track-Detection Matching for Multi-Object Tracking

• URL: http://arxiv.org/abs/2512.22105v1
• Date: Fri, 26 Dec 2025 18:19:39 GMT
• Title: Learning Association via Track-Detection Matching for Multi-Object Tracking
• Authors: Momir Adžemović,
• Abstract summary: Track-Detection Link Prediction (TDLP) is a tracking-by-detection method that performs per-frame association via link prediction between tracks and detections.<n>We show that TDLP consistently surpasses state-of-the-art performance across both tracking-by-detection and end-to-end methods.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-object tracking aims to maintain object identities over time by associating detections across video frames. Two dominant paradigms exist in literature: tracking-by-detection methods, which are computationally efficient but rely on handcrafted association heuristics, and end-to-end approaches, which learn association from data at the cost of higher computational complexity. We propose Track-Detection Link Prediction (TDLP), a tracking-by-detection method that performs per-frame association via link prediction between tracks and detections, i.e., by predicting the correct continuation of each track at every frame. TDLP is architecturally designed primarily for geometric features such as bounding boxes, while optionally incorporating additional cues, including pose and appearance. Unlike heuristic-based methods, TDLP learns association directly from data without handcrafted rules, while remaining modular and computationally efficient compared to end-to-end trackers. Extensive experiments on multiple benchmarks demonstrate that TDLP consistently surpasses state-of-the-art performance across both tracking-by-detection and end-to-end methods. Finally, we provide a detailed analysis comparing link prediction with metric learning-based association and show that link prediction is more effective, particularly when handling heterogeneous features such as detection bounding boxes. Our code is available at \href{https://github.com/Robotmurlock/TDLP}{https://github.com/Robotmurlock/TDLP}.

Related papers

• CoWTracker: Tracking by Warping instead of Correlation [53.834673070954494]
  We propose a dense point tracker that eschews cost volumes in favor of warping.<n>Inspired by recent advances in optical flow, our approach iteratively refines track estimates by warping features from the target frame to the query frame based on the current estimate.<n>Our model is simple and achieves state-of-the-art performance on standard dense point tracking benchmarks, including TAP-Vid-DAVIS, TAP-Vid-Kinetics, and Robo-TAP.
  arXiv  Detail & Related papers  (2026-02-04T18:58:59Z)
• CAMELTrack: Context-Aware Multi-cue ExpLoitation for Online Multi-Object Tracking [68.24998698508344]
  We introduce CAMEL, a novel association module for Context-Aware Multi-Cue ExpLoitation.<n>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.<n>Our proposed online tracking pipeline, CAMELTrack, achieves state-of-the-art performance on multiple tracking benchmarks.
  arXiv  Detail & Related papers  (2025-05-02T13:26:23Z)
• Tracking by Detection and Query: An Efficient End-to-End Framework for Multi-Object Tracking [23.800994163971502]
  Multi-object tracking (MOT) is dominated by two paradigms: tracking-by-detection (TBD) and tracking-by-query (TBQ)<n>We propose TBDQ-Net, a unified tracking-by-detection-and-query (TBDQ) framework that effectively combines the strengths of both paradigms.<n>Our method efficiently integrates pretrained, high-performance detectors with an MOT-tailored associator.
  arXiv  Detail & Related papers  (2024-11-09T14:38:08Z)
• Dense Optical Tracking: Connecting the Dots [82.79642869586587]
  DOT is a novel, simple and efficient method for solving the problem of point tracking in a video. We show that DOT is significantly more accurate than current optical flow techniques, outperforms sophisticated "universal trackers" like OmniMotion, and is on par with, or better than, the best point tracking algorithms like CoTracker.
  arXiv  Detail & Related papers  (2023-12-01T18:59:59Z)
• SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depth [84.64121608109087]
  We propose a pseudo-depth estimation method for obtaining the relative depth of targets from 2D images. Secondly, we design a depth cascading matching (DCM) algorithm, which can use the obtained depth information to convert a dense target set into multiple sparse target subsets. By integrating the pseudo-depth method and the DCM strategy into the data association process, we propose a new tracker, called SparseTrack.
  arXiv  Detail & Related papers  (2023-06-08T14:36:10Z)
• TR-MOT: Multi-Object Tracking by Reference [42.45614650498083]
  We propose a novel Reference Search (RS) module to provide a more reliable association based on the deformable transformer structure. Our method achieves competitive results on MOT17 and MOT20 datasets.
  arXiv  Detail & Related papers  (2022-03-30T19:07:26Z)
• Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework [76.70603443624012]
  We propose a novel one-stream tracking (OSTrack) framework that unifies feature learning and relation modeling. In this way, discriminative target-oriented features can be dynamically extracted by mutual guidance. OSTrack achieves state-of-the-art performance on multiple benchmarks, in particular, it shows impressive results on the one-shot tracking benchmark GOT-10k.
  arXiv  Detail & Related papers  (2022-03-22T18:37:11Z)
• On the detection-to-track association for online multi-object tracking [30.883165972525347]
  We propose a hybrid track association algorithm that models the historical appearance distances of a track with an incremental Gaussian mixture model (IGMM) Experimental results on three MOT benchmarks confirm that HTA effectively improves the target identification performance with a small compromise to the tracking speed.
  arXiv  Detail & Related papers  (2021-07-01T14:44:12Z)
• DEFT: Detection Embeddings for Tracking [3.326320568999945]
  We propose an efficient joint detection and tracking model named DEFT. Our approach relies on an appearance-based object matching network jointly-learned with an underlying object detection network. DEFT has comparable accuracy and speed to the top methods on 2D online tracking leaderboards.
  arXiv  Detail & Related papers  (2021-02-03T20:00:44Z)
• Learning to associate detections for real-time multiple object tracking [0.0]
  This study investigates the use of artificial neural networks to learn a similarity function that can be used among detections. The proposed tracker matches the results obtained by state-of-the-art methods, it has run 58% faster than a recent and similar method, used as baseline.
  arXiv  Detail & Related papers  (2020-07-12T17:08:41Z)
• Tracking Road Users using Constraint Programming [79.32806233778511]
  We present a constraint programming (CP) approach for the data association phase found in the tracking-by-detection paradigm of the multiple object tracking (MOT) problem. Our proposed method was tested on a motorized vehicles tracking dataset and produces results that outperform the top methods of the UA-DETRAC benchmark.
  arXiv  Detail & Related papers  (2020-03-10T00:04:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.