FANVID: Face and License Plate Recognition in Low-Resolution Surveillance Videos

FANVID is a benchmark dataset designed for face detection, face matching, and license plate recognition under challenging low-resolution surveillance video conditions. The dataset, created by kv1388, features faces and license plates that are unrecognizable in individual frames, encouraging models to leverage temporal context across video sequences. The dataset page was last updated on March 1, 2026.

Use Cases

• Train face detection models based on low-resolution video sequences mentioned in the description
• Benchmark license plate recognition algorithms based on temporal context across frames
• Develop video understanding models for surveillance applications based on the described challenging conditions

Strengths

• Dataset is specifically designed for a challenging and relevant computer vision task: recognition in low-resolution videos.
• The description indicates a focus on temporal context, a feature not present in many static image datasets.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count and dataset size are unknown, which may limit suitability assessment.
• Data may reflect bias inherent to the unspecified source of the surveillance videos.

Provenance

Source

huggingface, author kv1388

Freshness

Last updated 2026-03-01 17:42:13; freshness should be verified.