Datasets › VidSTG

VidSTG

Introduced by Zhu Zhang et al. in Where Does It Exist: Spatio-Temporal Video Grounding for Multi-Form Sentences archive 2025-07-28

The VidSTG dataset is a spatio-temporal video grounding dataset constructed based on the video relation dataset VidOR. VidOR contains 7,000, 835 and 2,165 videos for training, validation and testing, respectively. The goal of the Spatio-Temporal Video Grounding task (STVG) is to localize the spatio-temporal section of an untrimmed video that matches a given sentence depicting an object. VidSTG contains 5,563, 618, and 743 videos for training, validation, and testing, respectively.

Source: https://github.com/Guaranteer/VidSTG-Dataset Image Source: https://github.com/Guaranteer/VidSTG-Dataset

Benchmarks archive 2025-07-28

All 1 leaderboard 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
Spatio-Temporal Video Grounding VidSTG TA-STVG Declarative m_vIoU 34.4 Knowing Your Target: Target-Aware Transformer Makes... HengLan/TA-STVG 3 Compare

Papers archive 2025-07-28

3 shown of 3 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 29. 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
Knowing Your Target: Target-Aware Transformer Makes Better Spatio-Temporal Video Grounding 1 1 16 Feb 2025 not harvested
Context-Guided Spatio-Temporal Video Grounding 2 1 3 Jan 2024 ran 21 of 34 samples (13 unverified; 34 pointer-only for licence)
TubeDETR: Spatio-Temporal Video Grounding with Transformers 1 1 30 Mar 2022 ran 3 of 3 samples (0 unverified)

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

No licence recorded in the archive. Absence here is not a statement about the dataset's terms.

Modalities archive 2025-07-28

No modality tagged.

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • VidSTG

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