</> Code with Papers by Syntology

Datasets › TNL2K

TNL2K (Tracking by natural language)

Introduced by Xiao Wang et al. in Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark31 Mar 2021 archive 2025-07-28

Tracking by Natural Language (TNL2K) is constructed for the evaluation of tracking by natural language specification. TNL2K features:

  • Large-scale: 2,000 sequences, contains 1,244,340 frames, 663 words, 1300 / 700 for the train / testing respectively

  • High-quality: Manual annotation with careful inspection in each frame

  • Multi-modal: Providing visual and language annotation for each sequence

  • Adversarial-samples: Randomly adding adversarial samples for research on adversarial attack and defence

  • Significant-appearance-variation: Containing videos with cloth/face change for pedestrian

  • Heterogeneous: Containing RGB, thermal, Cartoon, Synthetic data

  • Multiple-baseline: Tracking-by-BBox, Tracking-by-Language, Tracking-by-Joint-BBox-Language

Source: Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark

HomepageBenchmarksPapers JSON

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 TNL2K MCITrack-L384 AUC 65.3 Exploring Enhanced Contextual Information for... kangben258/MCITrack 16 Compare
Visual Tracking TNL2K ARTrack-L AUC 60.3 Autoregressive Visual Tracking miv-xjtu/artrack 6 Compare

Papers archive 2025-07-28

14 shown of 14 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 62. 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
RTracker: Recoverable Tracking via PN Tree Structured Memory 1 1 28 Mar 2024 not harvested
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
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
Joint Visual Grounding and Tracking with Natural Language Specification 1 1 21 Mar 2023 ran 1 of 4 samples (3 unverified)
Universal Instance Perception as Object Discovery and Retrieval 1 1 12 Mar 2023 ran 3 of 4 samples (1 unverified)
Autoregressive Visual Tracking 1 2 1 Jan 2023 not harvested
Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework 1 1 22 Mar 2022 ran 0 of 1 samples (1 unverified)
Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark 2 2 31 Mar 2021 not harvested
Transformer Tracking 1 1 29 Mar 2021 ran 1 of 3 samples (2 unverified; 3 pointer-only for licence)

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

Visual Object TrackingVisual Tracking

License archive 2025-07-28

Custom

Modalities archive 2025-07-28

No modality tagged.

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • TNL2K

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