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 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. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

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

Most implemented papers archive 2025-07-28

30 shown of 30 papers with code (56 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• PP-YOLOE: An evolved version of YOLO
  30 Mar 2022 8 repositories listed Syntology ran 5 of 27 samples · 22 unverified
  In this report, we present PP-YOLOE, an industrial state-of-the-art object detector with high performance and friendly deployment.
• Real-time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-Identification
  12 Sep 2018 3 repositories listed Syntology ran 0 of 6 samples · 6 unverified
  Online multi-object tracking is a fundamental problem in time-critical video analysis applications.
• No Blind Spots: Full-Surround Multi-Object Tracking for Autonomous Vehicles using Cameras & LiDARs
  23 Feb 2018 3 repositories listed
  In 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…
• Hybrid-SORT: Weak Cues Matter for Online Multi-Object Tracking
  1 Aug 2023 2 repositories listed
  Also, our method shows strong generalization for diverse trackers and scenarios in a plug-and-play and training-free manner.
• Large-Scale Pre-training for Person Re-identification with Noisy Labels
  30 Mar 2022 2 repositories listed Syntology ran 5 of 5 samples · 0 unverified · 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…
• GCNNMatch: Graph Convolutional Neural Networks for Multi-Object Tracking via Sinkhorn Normalization
  30 Sep 2020 2 repositories listed
  This 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.
• Online Multi-Object Tracking Framework with the GMPHD Filter and Occlusion Group Management
  31 Jul 2019 2 repositories listed
  In 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…
• Focusing on Tracks for Online Multi-Object Tracking
  15 Jun 2025 1 repository listed
  Multi-object tracking (MOT) is a critical task in computer vision, requiring the accurate identification and continuous tracking of multiple objects across video frames.
• CAMELTrack: Context-Aware Multi-cue ExpLoitation for Online Multi-Object Tracking
  2 May 2025 1 repository listed
  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.
• Lost and Found: Overcoming Detector Failures in Online Multi-Object Tracking
  14 Jul 2024 1 repository listed
  Multi-object tracking (MOT) endeavors to precisely estimate the positions and identities of multiple objects over time.
• PuTR: A Pure Transformer for Decoupled and Online Multi-Object Tracking
  23 May 2024 1 repository listed
  Although 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.
• SFSORT: Scene Features-based Simple Online Real-Time Tracker
  11 Apr 2024 1 repository listed
  This paper introduces SFSORT, the world's fastest multi-object tracking system based on experiments conducted on MOT Challenge datasets.
• Detection Recovery in Online Multi-Object Tracking with Sparse Graph Tracker
  2 May 2022 1 repository listed
  The strong edge features allow SGT to track targets with tracking candidates selected by top-K scored detections with large K.
• Real-time Online Multi-Object Tracking in Compressed Domain
  5 Apr 2022 1 repository listed
  Recent online Multi-Object Tracking (MOT) methods have achieved desirable tracking performance.
• Do Different Tracking Tasks Require Different Appearance Models?
  5 Jul 2021 1 repository listed Syntology ran 6 of 17 samples · 11 unverified
  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…
• SiamMOT: Siamese Multi-Object Tracking
  25 May 2021 1 repository listed Syntology ran 0 of 1 samples · 1 unverified
  In this paper, we focus on improving online multi-object tracking (MOT).
• Learnable Graph Matching: Incorporating Graph Partitioning with Deep Feature Learning for Multiple Object Tracking
  30 Mar 2021 1 repository listed Syntology ran 10 of 12 samples · 2 unverified · 12 pointer-only (licence)
  Then the association problem turns into a general graph matching between tracklet graph and detection graph.
• Looking Beyond Two Frames: End-to-End Multi-Object Tracking Using Spatial and Temporal Transformers
  27 Mar 2021 1 repository listed
  Tracking a time-varying indefinite number of objects in a video sequence over time remains a challenge despite recent advances in the field.
• Learning to Track with Object Permanence
  26 Mar 2021 1 repository listed Syntology ran 1 of 1 samples · 0 unverified
  In this work, we introduce an end-to-end trainable approach for joint object detection and tracking that is capable of such reasoning.
• Track to Detect and Segment: An Online Multi-Object Tracker
  16 Mar 2021 1 repository listed Syntology ran 4 of 4 samples · 0 unverified
  Most online multi-object trackers perform object detection stand-alone in a neural net without any input from tracking.
• Online Multi-Object Tracking and Segmentation with GMPHD Filter and Mask-based Affinity Fusion
  31 Aug 2020 1 repository listed
  One 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…
• Segment as Points for Efficient Online Multi-Object Tracking and Segmentation
  3 Jul 2020 1 repository listed
  The resulting online MOTS framework, named PointTrack, surpasses all the state-of-the-art methods including 3D tracking methods by large margins (5.
• PointTrack++ for Effective Online Multi-Object Tracking and Segmentation
  3 Jul 2020 1 repository listed
  In this work, we present PointTrack++, an effective on-line framework for MOTS, which remarkably extends our recently proposed PointTrack framework.
• A Unified Object Motion and Affinity Model for Online Multi-Object Tracking
  25 Mar 2020 1 repository listed
  In 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…
• FANTrack: 3D Multi-Object Tracking with Feature Association Network
  7 May 2019 1 repository listed
  Instead, we exploit the power of deep learning to formulate the data association problem as inference in a CNN.
• Online Multi-Object Tracking with Dual Matching Attention Networks
  2 Feb 2019 1 repository listed
  In 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…
• Joint Monocular 3D Vehicle Detection and Tracking
  26 Nov 2018 1 repository listed Syntology ran 1 of 3 samples · 2 unverified
  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.
• Tracking by Animation: Unsupervised Learning of Multi-Object Attentive Trackers
  10 Sep 2018 1 repository listed
  To 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…
• Beyond Pixels: Leveraging Geometry and Shape Cues for Online Multi-Object Tracking
  26 Feb 2018 1 repository listed
  This paper introduces geometry and object shape and pose costs for multi-object tracking in urban driving scenarios.
• Online multi-object tracking via robust collaborative model and sample selection
  1 Jan 2017 1 repository listed
  For 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.

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. Read from the graph 2026-09-24.