AI Paper Atlas

Research map / Benchmarks / MOT17

MOT17 leaderboard

58 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on MOT17. Best MOTA: 82 (MOTE, ICML 2025).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

MOT17 · MOTA

41 papers, each with its best reported number for its own method; higher is better.

31 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

MOT17 · IDF1

38 papers, each with its best reported number for its own method; higher is better.

28 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

MOT17 · HOTA

28 papers, each with its best reported number for its own method; higher is better.

18 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

MOT17 · MOTA (val)

10 papers, each with its best reported number for its own method; higher is better.

#MOTA ↑MethodPaperTopic
190.2FDTracker
ByteTrack with YOLOX-m
Foundation Model Driven Appearance Extraction for Robust Multiple Object Tracking
AAAI 2025 · Table 4
Tracking
278.6SMILEtrack with SLM, SMC, and GF
PRB-Net
SMILEtrack: SiMIlarity LEarning for Occlusion-Aware Multiple Object Tracking
AAAI 2024 · Ablation analysis table
Tracking
377.1ByteTrack* + BUSCA
ByteTrack
Lost and Found: Overcoming Detector Failures in Online Multi-Object Tracking
ECCV 2024 · Table 1
Tracking
474.3TGFormer full updater
MeMOTR
TGFormer: Transformer with Track Query Group for Multi-Object Tracking
AAAI 2025 · Table 4
Tracking
572.1LTrack
MOTR
Generalizing Multiple Object Tracking to Unseen Domains by Introducing Natural Language Representation
AAAI 2023 · Table 1
Human and embodied modeling
671.5STLC
FairMOT
Multiple Object Tracking With Correlation Learning
CVPR 2021 · Table: Evaluation of correlati
Tracking
768.2TraDeS
Baseline+CVA+MFW
Track To Detect and Segment: An Online Multi-Object Tracker
CVPR 2021 · Ablation studies table
Tracking
864Time+Pos+CNNLearning a Neural Solver for Multiple Object Tracking
CVPR 2020 · Edge Features ablation table
Tracking
960.66DeepMOT loss (dMOTA+dMOTP)
Tracktor + ReIDhead
How to Train Your Deep Multi-Object Tracker
CVPR 2020 · Loss ablation table
Tracking
1051.54L2Learning of Global Objective for Network Flow in Multi-Object Tracking
CVPR 2022 · MOT17 validation tracking tabl
Tracking

MOT17 · IDF1 (val)

10 papers, each with its best reported number for its own method; higher is better.

#IDF1 ↑MethodPaperTopic
186.1FDTracker
ByteTrack with YOLOX-m
Foundation Model Driven Appearance Extraction for Robust Multiple Object Tracking
AAAI 2025 · Table 4
Tracking
283.7Baseline+I+RMotionTrack: Learning Robust Short-Term and Long-Term Motions for Multi-Object Tracking
CVPR 2023 · Ablation Study, Effect of Each
Tracking
380.8SMILEtrack with SLM, SMC, and GF
PRB-Net
SMILEtrack: SiMIlarity LEarning for Occlusion-Aware Multiple Object Tracking
AAAI 2024 · Ablation analysis table
Tracking
476.1STLC
FairMOT
Multiple Object Tracking With Correlation Learning
CVPR 2021 · Table: Evaluation of correlati
Tracking
573GMTracker with interpolationLearnable Graph Matching: Incorporating Graph Partitioning With Deep Feature Learning for Multiple Object Tracking
CVPR 2021 · Table: Ablation studies on dif
Graph algorithms and clustering
671.7TraDeS
Baseline+CVA+MFW
Track To Detect and Segment: An Online Multi-Object Tracker
CVPR 2021 · Ablation studies table
Tracking
770Time-aware MPNLearning a Neural Solver for Multiple Object Tracking
CVPR 2020 · Ablation Study table
Tracking
869.1LTrack
MOTR
Generalizing Multiple Object Tracking to Unseen Domains by Introducing Natural Language Representation
AAAI 2023 · Table 1
Human and embodied modeling
967.9TGFormer full updater
MeMOTR
TGFormer: Transformer with Track Query Group for Multi-Object Tracking
AAAI 2025 · Table 4
Tracking
1060.15L2Learning of Global Objective for Network Flow in Multi-Object Tracking
CVPR 2022 · MOT17 validation tracking tabl
Tracking

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.