Datasets › TrackingNet

TrackingNet

Introduced by Matthias Müller et al. in TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild1 Jan 2018 archive 2025-07-28

TrackingNet is a large-scale tracking dataset consisting of videos in the wild. It has a total of 30,643 videos split into 30,132 training videos and 511 testing videos, with an average of 470,9 frames.

Source: Learning the Model Update for Siamese Trackers Image Source: https://arxiv.org/abs/1803.10794

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.

First row (archive order)PaperCode
Visual Object Tracking TrackingNet MCITrack-L384 Accuracy 87.9 Exploring Enhanced Contextual Information for... kangben258/MCITrack 40 Compare
Visual Tracking TrackingNet TATrack-L ACCURACY 0.85 Target-Aware Tracking with Long-term Context Attention hekaijie123/TATrack 1 Compare

Papers archive 2025-07-28

30 shown of 34 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 210. 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
SPMTrack: Spatio-Temporal Parameter-Efficient Fine-Tuning with Mixture of Experts for Scalable Visual Tracking 1 3 24 Mar 2025 ran 0 of 1 samples (1 unverified)
Exploring Enhanced Contextual Information for Video-Level Object Tracking 1 2 15 Dec 2024 not harvested
SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory 1 1 18 Nov 2024 ran 1 of 1 samples (0 unverified)
Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance 1 2 8 Mar 2024 ran 3 of 5 samples (2 unverified)
ODTrack: Online Dense Temporal Token Learning for Visual Tracking 1 2 3 Jan 2024 ran 1 of 1 samples (0 unverified)
ARTrackV2: Prompting Autoregressive Tracker Where to Look and How to Describe 1 1 28 Dec 2023 not harvested
HIPTrack: Visual Tracking with Historical Prompts 1 1 3 Nov 2023 not harvested
Integrating Boxes and Masks: A Multi-Object Framework for Unified Visual Tracking and Segmentation 1 1 25 Aug 2023 not harvested
Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking 1 1 27 Apr 2023 not harvested
DropMAE: Masked Autoencoders with Spatial-Attention Dropout for Tracking Tasks 1 1 2 Apr 2023 not harvested
Universal Instance Perception as Object Discovery and Retrieval 1 1 12 Mar 2023 ran 3 of 4 samples (1 unverified)
Target-Aware Tracking with Long-term Context Attention 1 2 27 Feb 2023 ran 0 of 2 samples (2 unverified)
MixFormer: End-to-End Tracking with Iterative Mixed Attention 1 1 6 Feb 2023 not harvested
Autoregressive Visual Tracking 1 1 1 Jan 2023 not harvested
NeighborTrack: Improving Single Object Tracking by Bipartite Matching with Neighbor Tracklets 1 1 12 Nov 2022 not harvested
Towards Sequence-Level Training for Visual Tracking 2 1 11 Aug 2022 ran 3 of 5 samples (2 unverified; 5 pointer-only for licence)
AiATrack: Attention in Attention for Transformer Visual Tracking 1 1 20 Jul 2022 ran 1 of 3 samples (2 unverified)
Towards Grand Unification of Object Tracking 1 1 14 Jul 2022 ran 6 of 6 samples (0 unverified; 1 pointer-only for licence)
Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework 1 1 22 Mar 2022 ran 0 of 1 samples (1 unverified)
MixFormer: End-to-End Tracking with Iterative Mixed Attention 1 1 21 Mar 2022 ran 1 of 1 samples (0 unverified)
SwinTrack: A Simple and Strong Baseline for Transformer Tracking 1 1 2 Dec 2021 ran 0 of 2 samples (2 unverified)
Target Transformed Regression for Accurate Tracking 1 1 1 Apr 2021 not harvested
Learning Spatio-Temporal Transformer for Visual Tracking 1 1 31 Mar 2021 ran 2 of 2 samples (0 unverified)
Learning to Fuse Asymmetric Feature Maps in Siamese Trackers 1 1 4 Dec 2020 not harvested
How to Train Your Energy-Based Model for Regression 2 1 4 May 2020 ran 0 of 3 samples (3 unverified)
Siam R-CNN: Visual Tracking by Re-Detection 1 1 28 Nov 2019 ran 0 of 4 samples (4 unverified)
SiamFC++: Towards Robust and Accurate Visual Tracking with Target Estimation Guidelines 6 1 14 Nov 2019 ran 4 of 5 samples (1 unverified; 5 pointer-only for licence)
Energy-Based Models for Deep Probabilistic Regression 2 1 26 Sep 2019 not harvested
Joint Group Feature Selection and Discriminative Filter Learning for Robust Visual Object Tracking 1 1 30 Jul 2019 not harvested
Learning Discriminative Model Prediction for Tracking 2 1 15 Apr 2019 not harvested

The full list of 34 is in the JSON twin.

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

License archive 2025-07-28

Apache 2.0

Modalities archive 2025-07-28

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • TrackingNet

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