Browse State-of-the-Art › Online Multi-Object Tracking
Online Multi-Object Tracking
30 papers with code · 6 benchmarks · 10 datasets archive 2025-07-28
The goal of Online Multi-Object Tracking is to estimate the spatio-temporal trajectories of multiple objects in an online video stream (i.e., the video is provided frame-by-frame), which is a fundamental problem for numerous real-time applications, such as video surveillance, autonomous driving, and robot navigation.
Source: A Hybrid Data Association Framework for Robust Online Multi-Object Tracking
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
6 leaderboard tables shown for this task, 6 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
Syntology 1 newer paper was judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): SportsMOT (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
10 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 56 · with a code link: 30 · where Syntology ran a sample: 9 (9 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (9 of 56 tagged: 9 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 56 of 56, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
30 Mar 2022 8 repositories listed Syntology official (archive's flag): 2 ran · 22 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 2 honoured, 0 violated, 17 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified (of 27 harvested samples) · 1 pointer-only (licence)In this report, we present PP-YOLOE, an industrial state-of-the-art object detector with high performance and friendly deployment.
-
12 Sep 2018 3 repositories listed Syntology official (archive's flag): 5 ran · 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 6 harvested samples)Online multi-object tracking is a fundamental problem in time-critical video analysis applications.
-
23 Feb 2018 3 repositories listedIn this paper, we present a modular framework for tracking multiple objects (vehicles), capable of accepting object proposals from different sensor modalities (vision and range) and a variable number of sensors, to…
-
1 Aug 2023 2 repositories listedAlso, our method shows strong generalization for diverse trackers and scenarios in a plug-and-play and training-free manner.
-
30 Mar 2022 2 repositories listed Syntology official (archive's flag): 2 ran · 5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples) · 4 pointer-only (licence)Since theses ID labels automatically derived from tracklets inevitably contain noises, we develop a large-scale Pre-training framework utilizing Noisy Labels (PNL), which consists of three learning modules: supervised…
-
30 Sep 2020 2 repositories listedThis new paradigm enables the network to leverage the "context" information of the geometry of objects and allows us to model the interactions among the features of multiple objects.
-
31 Jul 2019 2 repositories listedIn this paper, we propose an efficient online multi-object tracking framework based on the GMPHD filter and occlusion group management scheme where the GMPHD filter utilizes hierarchical data association to reduce the…
-
15 Jun 2025 1 repository listedMulti-object tracking (MOT) is a critical task in computer vision, requiring the accurate identification and continuous tracking of multiple objects across video frames.
-
2 May 2025 1 repository listedHowever, 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.
-
14 Jul 2024 1 repository listedMulti-object tracking (MOT) endeavors to precisely estimate the positions and identities of multiple objects over time.
-
23 May 2024 1 repository listedAlthough graph-based approaches can address this issue by modeling trajectories as a graph in the decoupled manner, their non-online nature poses obstacles for real-time applications.
-
11 Apr 2024 1 repository listedThis paper introduces SFSORT, the world's fastest multi-object tracking system based on experiments conducted on MOT Challenge datasets.
-
2 May 2022 1 repository listedThe strong edge features allow SGT to track targets with tracking candidates selected by top-K scored detections with large K.
-
5 Apr 2022 1 repository listedRecent online Multi-Object Tracking (MOT) methods have achieved desirable tracking performance.
-
5 Jul 2021 1 repository listed Syntology official (archive's flag): 6 ran · 6 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 11 unverified (of 17 harvested samples)We show how most tracking tasks can be solved within this framework, and that the same appearance model can be successfully used to obtain results that are competitive against specialised methods for most of the tasks…
-
25 May 2021 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)In this paper, we focus on improving online multi-object tracking (MOT).
-
30 Mar 2021 1 repository listed Syntology official (archive's flag): 9 ran · 10 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified (of 12 harvested samples) · 12 pointer-only (licence)Then the association problem turns into a general graph matching between tracklet graph and detection graph.
-
27 Mar 2021 1 repository listedTracking a time-varying indefinite number of objects in a video sequence over time remains a challenge despite recent advances in the field.
-
26 Mar 2021 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result (of 1 harvested sample)In this work, we introduce an end-to-end trainable approach for joint object detection and tracking that is capable of such reasoning.
-
16 Mar 2021 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples)Most online multi-object trackers perform object detection stand-alone in a neural net without any input from tracking.
-
31 Aug 2020 1 repository listedOne affinity, for position and motion, is computed by using the GMPHD filter, and the other affinity, for appearance is computed by using the responses from a single object tracker such as a kernalized correlation…
-
3 Jul 2020 1 repository listedIn this work, we present PointTrack++, an effective on-line framework for MOTS, which remarkably extends our recently proposed PointTrack framework.
-
3 Jul 2020 1 repository listedThe resulting online MOTS framework, named PointTrack, surpasses all the state-of-the-art methods including 3D tracking methods by large margins (5.
-
25 Mar 2020 1 repository listedIn this paper, we propose a novel MOT framework that unifies object motion and affinity model into a single network, named UMA, in order to learn a compact feature that is discriminative for both object motion and…
-
7 May 2019 1 repository listedInstead, we exploit the power of deep learning to formulate the data association problem as inference in a CNN.
-
2 Feb 2019 1 repository listedIn this paper, we propose an online Multi-Object Tracking (MOT) approach which integrates the merits of single object tracking and data association methods in a unified framework to handle noisy detections and frequent…
-
26 Nov 2018 1 repository listed Syntology 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)The framework can not only associate detections of vehicles in motion over time, but also estimate their complete 3D bounding box information from a sequence of 2D images captured on a moving platform.
-
10 Sep 2018 1 repository listedTo achieve both label-free and end-to-end learning of MOT, we propose a Tracking-by-Animation framework, where a differentiable neural model first tracks objects from input frames and then animates these objects into…
-
26 Feb 2018 1 repository listedThis paper introduces geometry and object shape and pose costs for multi-object tracking in urban driving scenarios.
-
1 Jan 2017 1 repository listedFor each frame, we construct an association between detections and trackers, and treat each detected image region as a key sample, for online update, if it is associated to a tracker.
-
17 Jun 2024 0 repositories listed
-
19 Aug 2023 0 repositories listed
-
An End-to-End Framework of Road User Detection, Tracking, and Prediction from Monocular Images9 Aug 2023 0 repositories listed
-
Focus On Details: Online Multi-object Tracking with Diverse Fine-grained Representation28 Feb 2023 0 repositories listed
-
Towards Discriminative Representation: Multi-view Trajectory Contrastive Learning for Online Multi-object Tracking27 Mar 2022 0 repositories listed
-
STURE: Spatial-Temporal Mutual Representation Learning for Robust Data Association in Online Multi-Object Tracking18 Jan 2022 0 repositories listed
-
4 Jan 2022 0 repositories listed
-
On the detection-to-track association for online multi-object tracking1 Jul 2021 0 repositories listed
-
1 Apr 2021 0 repositories listed
-
Multi-object Tracking with a Hierarchical Single-branch Network6 Jan 2021 0 repositories listed
-
A CRF-based Framework for Tracklet Inactivation in Online Multi-Object Tracking30 Nov 2020 0 repositories listed
-
Online Multi-Object Tracking with delta-GLMB Filter based on Occlusion and Identity Switch Handling19 Nov 2020 0 repositories listed
-
Refinements in Motion and Appearance for Online Multi-Object Tracking16 Mar 2020 0 repositories listed
-
Online Multi-Object Tracking with Instance-Aware Tracker and Dynamic Model Refreshment21 Feb 2019 0 repositories listed
-
Multi-object Tracking with Neural Gating Using Bilinear LSTM1 Sep 2018 0 repositories listed
-
Deep Continuous Conditional Random Fields with Asymmetric Inter-object Constraints for Online Multi-object Tracking4 Jun 2018 0 repositories listed
-
Online Multi-Object Tracking with Historical Appearance Matching and Scene Adaptive Detection Filtering28 May 2018 0 repositories listed
-
Heuristic Search for Structural Constraints in Data Association8 Nov 2017 0 repositories listed
-
Recurrent Autoregressive Networks for Online Multi-Object Tracking7 Nov 2017 0 repositories listed
-
Online Multi-Object Tracking Using CNN-based Single Object Tracker with Spatial-Temporal Attention Mechanism9 Aug 2017 0 repositories listed
-
Track Everything: Limiting Prior Knowledge in Online Multi-Object Recognition21 Apr 2017 0 repositories listed
-
A Hybrid Data Association Framework for Robust Online Multi-Object Tracking31 Mar 2017 0 repositories listed
-
1 Jun 2016 0 repositories listed
-
1 Dec 2015 0 repositories listed
-
Occlusion Geodesics for Online Multi-Object Tracking1 Jun 2014 0 repositories listed
-
Robust Online Multi-Object Tracking based on Tracklet Confidence and Online Discriminative Appearance Learning1 Jun 2014 0 repositories listed
Syntology lines on 9 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections