Datasets › MOT17

MOT17 (Multiple Object Tracking 17)

Introduced by Anton Milan et al. in MOT16: A Benchmark for Multi-Object Tracking2 Mar 2016 archive 2025-07-28

The Multiple Object Tracking 17 (MOT17) dataset is a dataset for multiple object tracking. Similar to its previous version MOT16, this challenge contains seven different indoor and outdoor scenes of public places with pedestrians as the objects of interest. A video for each scene is divided into two clips, one for training and the other for testing. The dataset provides detections of objects in the video frames with three detectors, namely SDP, Faster-RCNN and DPM. The challenge accepts both on-line and off-line tracking approaches, where the latter are allowed to use the future video frames to predict tracks.

Source: Deep Affinity Network for Multiple Object Tracking Image Source: https://www.researchgate.net/figure/Visualization-of-selected-sequences-from-the-MOT17-benchmark-dataset_fig4_337133502

Benchmarks archive 2025-07-28

All 2 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

Papers archive 2025-07-28

30 shown of 49 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 291. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
Focusing on Tracks for Online Multi-Object Tracking 1 1 15 Jun 2025 not harvested
CAMELTrack: Context-Aware Multi-cue ExpLoitation for Online Multi-Object Tracking 1 1 2 May 2025 not harvested
AdapTrack: Adaptive Thresholding-Based Matching For Multi-object Tracking 1 1 27 Sep 2024 not harvested
A Confidence-Aware Matching Strategy For Generalized Multi-Object Tracking 1 1 27 Sep 2024 not harvested
When to Extract ReID Features: A Selective Approach for Improved Multiple Object Tracking 2 1 10 Sep 2024 not harvested
One Homography is All You Need: IMM-based Joint Homography and Multiple Object State Estimation 1 1 4 Sep 2024 not harvested
BoostTrack++: using tracklet information to detect more objects in multiple object tracking 2 1 23 Aug 2024 not harvested
FeatureSORT: Essential Features for Effective Tracking 0 1 5 Jul 2024 not harvested
BoostTrack: boosting the similarity measure and detection confidence for improved multiple object tracking 1 1 12 Apr 2024 not harvested
SFSORT: Scene Features-based Simple Online Real-Time Tracker 1 1 11 Apr 2024 not harvested
Multiple Object Tracking as ID Prediction 1 1 25 Mar 2024 ran 10 of 10 samples (0 unverified)
Learning Data Association for Multi-Object Tracking using Only Coordinates 1 1 12 Mar 2024 not harvested
UCMCTrack: Multi-Object Tracking with Uniform Camera Motion Compensation 1 1 14 Dec 2023 not harvested
Contrastive Learning for Multi-Object Tracking with Transformers 1 1 14 Nov 2023 not harvested
SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depth 2 1 8 Jun 2023 not harvested
Bridging the Gap Between End-to-end and Non-End-to-end Multi-Object Tracking 2 1 22 May 2023 not harvested
Deep OC-SORT: Multi-Pedestrian Tracking by Adaptive Re-Identification 3 1 23 Feb 2023 ran 2 of 10 samples (8 unverified)
SMILEtrack: SiMIlarity LEarning for Occlusion-Aware Multiple Object Tracking 2 1 16 Nov 2022 not harvested
Multiple Object Tracking from appearance by hierarchically clustering tracklets 1 1 7 Oct 2022 not harvested
LMOT: Efficient Light-Weight Detection and Tracking in Crowds 1 1 8 Aug 2022 not harvested
Transformer-based assignment decision network for multiple object tracking 1 2 6 Aug 2022 not harvested
Towards Grand Unification of Object Tracking 1 1 14 Jul 2022 ran 6 of 6 samples (0 unverified; 1 pointer-only for licence)
BoT-SORT: Robust Associations Multi-Pedestrian Tracking 7 1 29 Jun 2022 ran 4 of 10 samples (6 unverified; 1 pointer-only for licence)
Detection Recovery in Online Multi-Object Tracking with Sparse Graph Tracker 1 1 2 May 2022 not harvested
Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking 7 1 27 Mar 2022 ran 15 of 31 samples (16 unverified; 2 pointer-only for licence)
Global Tracking Transformers 1 1 24 Mar 2022 ran 4 of 5 samples (1 unverified; 5 pointer-only for licence)
SimpleTrack: Rethinking and Improving the JDE Approach for Multi-Object Tracking 6 1 8 Mar 2022 not harvested
StrongSORT: Make DeepSORT Great Again 14 1 28 Feb 2022 ran 3 of 20 samples (17 unverified; 2 pointer-only for licence)
Online Multi-Object Tracking with Unsupervised Re-Identification Learning and Occlusion Estimation 0 1 4 Jan 2022 not harvested
ByteTrack: Multi-Object Tracking by Associating Every Detection Box 10 1 13 Oct 2021 ran 1 of 12 samples (11 unverified)

The full list of 49 is in the JSON twin.

Dataset loaders archive 2025-07-28

1 loader as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

CC BY-NC-SA 3.0

Modalities archive 2025-07-28

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • MOT17

1 variant name, as the archive lists them.

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