Synthetic CCTV Retail Shoplifting Detection Dataset with YOLO and VLM Annotations

Synthetic CCTV Retail Shoplifting Dataset with YOLO & VLM annotations. The dataset is designed for computer vision tasks in retail security. Its origin, size, and creation details are unspecified.

Use Cases

• Train YOLO-based object detection models based on the YOLO annotations mentioned in the description.
• Fine-tune Vision-Language Models (VLMs) based on the VLM annotations mentioned in the description.
• Benchmark model performance on synthetic retail surveillance scenarios based on the described content.
• Develop multi-modal systems for retail security based on the combined image and annotation data.

Strengths

• Annotations are provided for two popular computer vision frameworks: YOLO and Vision-Language Models.
• The dataset is synthetic, which likely allows for controlled scenario generation and privacy compliance.

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.

Provenance

Source

kaggle

Collection Method

Synthetically generated.