Llava Stvg Data: A Vision-Language Dataset for Spatio-Temporal Video Grounding

Published on huggingface by author zaiquan and last updated on 2025-12-04. The dataset likely contains multimodal data for spatio-temporal video grounding tasks, which involve linking language queries to specific objects and time segments in videos. Its specific content, scale, and collection methodology require verification after download.

Use Cases

• Train a model for spatio-temporal video grounding (inferred from domain, verify after download)
• Benchmark video-language understanding systems (inferred from domain, verify after download)
• Fine-tune large vision-language models on video-text alignment tasks (inferred from domain, verify after download)

Strengths

• Published on the huggingface platform, a major hub for AI datasets and models.
• Last updated on 2025-12-04, indicating recent maintenance.

Limitations

• Metadata is minimal; actual content requires verification after download.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count, file formats, and license are unknown, which may limit suitability assessment.

Provenance

Source

huggingface

Freshness

Last updated 2025-12-04 20:29:37