Browse State-of-the-Art › Object Tracking
Object Tracking
767 papers with code · 10 benchmarks · 69 datasets archive 2025-07-28
Object tracking is the task of taking an initial set of object detections, creating a unique ID for each of the initial detections, and then tracking each of the objects as they move around frames in a video, maintaining the ID assignment. State-of-the-art methods involve fusing data from RGB and event-based cameras to produce more reliable object tracking. CNN-based models using only RGB images as input are also effective. The most popular benchmark is OTB. There are several evaluation metrics specific to object tracking, including HOTA, MOTA, IDF1, and Track-mAP.
( Image credit: Towards-Realtime-MOT )
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
10 leaderboard tables shown for this task, 10 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
69 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 69 until expanded.
Subtasks archive 2025-07-28
10 subtasks in the archive's task tree.
Most implemented papers archive 2025-07-28
30 shown of 767 papers with code (1,966 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.
-
21 Mar 2017 75 repositories listed Syntology ran 12 of 40 samples · 28 unverified · 7 pointer-only (licence)Simple Online and Realtime Tracking (SORT) is a pragmatic approach to multiple object tracking with a focus on simple, effective algorithms.
-
4 Apr 2020 33 repositories listed Syntology ran 8 of 53 samples · 45 unverifiedFormulating MOT as multi-task learning of object detection and re-ID in a single network is appealing since it allows joint optimization of the two tasks and enjoys high computation efficiency.
-
28 Feb 2022 14 repositories listed Syntology ran 3 of 20 samples · 17 unverified · 2 pointer-only (licence)As a result, the construction of a good baseline for a fair comparison is essential.
-
19 Jun 2020 13 repositories listed Syntology ran 7 of 22 samples · 15 unverifiedThree-dimensional objects are commonly represented as 3D boxes in a point-cloud.
-
13 Mar 2019 13 repositories listed Syntology ran 3 of 14 samples · 11 unverified · 2 pointer-only (licence)Therefore, we motivate our approach as a new tracking paradigm and point out promising future research directions.
-
27 Sep 2019 12 repositories listed Syntology ran 2 of 36 samples · 34 unverifiedIn this paper, we propose an MOT system that allows target detection and appearance embedding to be learned in a shared model.
-
17 May 2017 11 repositories listedRobust object tracking requires knowledge and understanding of the object being tracked: its appearance, its motion, and how it changes over time.
-
13 Oct 2021 10 repositories listed Syntology ran 1 of 12 samples · 11 unverifiedByteTrack also achieves state-of-the-art performance on MOT20, HiEve and BDD100K tracking benchmarks.
-
30 Jun 2016 10 repositories listed Syntology ran 0 of 1 samples · 1 unverifiedThe problem of arbitrary object tracking has traditionally been tackled by learning a model of the object's appearance exclusively online, using as sole training data the video itself.
-
2 Mar 2016 8 repositories listed Syntology ran 11 of 38 samples · 27 unverified · 1 pointer-only (licence)Recently, a new benchmark for Multiple Object Tracking, MOTChallenge, was launched with the goal of collecting existing and new data and creating a framework for the standardized evaluation of multiple object tracking…
-
5 Oct 2022 7 repositories listedThe SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team.
-
29 Jun 2022 7 repositories listed Syntology ran 4 of 10 samples · 6 unverified · 1 pointer-only (licence)The goal of multi-object tracking (MOT) is detecting and tracking all the objects in a scene, while keeping a unique identifier for each object.
-
27 Mar 2022 7 repositories listed Syntology ran 15 of 31 samples · 16 unverified · 2 pointer-only (licence)Instead of relying only on the linear state estimate (i.
-
8 Mar 2022 6 repositories listedJoint detection and embedding (JDE) based methods usually estimate bounding boxes and embedding features of objects with a single network in Multi-Object Tracking (MOT).
-
23 May 2024 5 repositories listedTo leverage more modalities, some recent efforts have been made to learn a unified visual object tracking model for any modality.
-
17 Nov 2021 5 repositories listedMulti-Object Tracking (MOT) has achieved aggressive progress and derived many excellent deep learning trackers.
-
31 Mar 2021 5 repositories listed Syntology ran 1 of 1 samples · 0 unverifiedTo learn generalizable representation for correspondence in large-scale, a variety of self-supervised pretext tasks are proposed to explicitly perform object-level or patch-level similarity learning.
-
1 Dec 2020 5 repositories listed Syntology ran 1 of 1 samples · 0 unverifiedWe propose a method that, given a single image with its estimated background, outputs the object's appearance and position in a series of sub-frames as if captured by a high-speed camera (i.
-
16 Sep 2020 5 repositories listed Syntology ran 2 of 10 samples · 8 unverifiedMulti-Object Tracking (MOT) has been notoriously difficult to evaluate.
-
1 Jun 2018 5 repositories listedVisual object tracking has been a fundamental topic in recent years and many deep learning based trackers have achieved state-of-the-art performance on multiple benchmarks.
-
13 Apr 2017 5 repositories listedIn this work, we present an end-to-end lightweight network architecture, namely DCFNet, to learn the convolutional features and perform the correlation tracking process simultaneously.
-
9 Mar 2024 4 repositories listedCurrent event-/frame-event based trackers undergo evaluation on short-term tracking datasets, however, the tracking of real-world scenarios involves long-term tracking, and the performance of existing tracking…
-
26 Sep 2023 4 repositories listed Syntology ran 9 of 9 samples · 0 unverified · 9 pointer-only (licence)Tracking using bio-inspired event cameras has drawn more and more attention in recent years.
-
17 Nov 2022 4 repositories listedIn this paper, we propose MOTRv2, a simple yet effective pipeline to bootstrap end-to-end multi-object tracking with a pretrained object detector.
-
27 Oct 2022 4 repositories listedExisting Visual Object Tracking (VOT) only takes the target area in the first frame as a template.
-
5 Jan 2022 4 repositories listedIn the second approach, although DeepSORT only processes a quarter of all frames due to hardware and time limitations, our model with DeepSORT (42.
-
10 Mar 2021 4 repositories listedThe code and protocols for our benchmark and algorithm are available at https://github.
-
18 Jan 2021 4 repositories listedThe decoder part is inspired by the Cascaded Partial Decoder, known for fast and accurate salient object detection.
-
23 Oct 2020 4 repositories listed Syntology ran 2 of 15 samples · 13 unverifiedHowever, the inherent differences and relations between detection and re-identification (ReID) are unconsciously overlooked because of treating them as two isolated tasks in the one-shot tracking paradigm.
-
23 Aug 2019 4 repositories listedBecause of the LiDAR sensors' nature, rapidly changing ambient lighting will not affect the detection of a LiDARTag; hence, the proposed fiducial marker can operate in a completely dark environment.
Syntology lines on 16 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.
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