Tag: computer-vision

All the articles with the tag "computer-vision".

• Implementing Spatially-Grounded Document Retrieval via Patch-to-Region Propagation

  2 Dec, 2025

  A deep dive into my recent research on spatially-grounded document retrieval using ColPali models and OCR bounding boxes, enabling precise region-level retrieval during inference time and without additional training.

• Mapping Worlds into Graphs with Qdrant, Neo4j, RF-DETR, BLIP-2 and Kung Fu

  29 Apr, 2025

  Diving deeper into the GraphRAG rabbit hole, I explore how to transform real-world video data into knowledge graphs using RF-DETR for object detection and BLIP-2 for intelligent entity description - setting the foundation for context-aware retrieval systems.