A decade of object detection papers, one markdown file

What it does It collects and categorizes influential object detection papers—from R-CNN through YOLO and SSD variants—linking each to arXiv preprints, official repositories, and third-party reimplementations in PyTorch, TensorFlow, MXNet, and others. The list also branches into specialized areas such as 3D detection, zero-shot learning, and weakly supervised methods.

The interesting bit The real value is not novelty but thoroughness: for popular models like Faster R-CNN or YOLO, the maintainer has aggregated numerous framework ports, turning a literature search into a one-stop comparison shop. It also surfaces survey papers up front, which is rare for a raw awesome-list.

Key highlights

• Organized by model family (R-CNN, YOLO, SSD, RetinaNet, etc.) and by technique (one-shot, zero-shot, 3D).
• Links directly to arXiv, GitHub repos, slides, and blog notes for most entries.
• Multiple framework implementations listed side-by-side where available.
• Includes a chronological index via Date.md for time-based reading.
• Derived from and expands upon handong1587’s earlier deep-learning compilation.

Caveats

• Coverage appears to taper off around 2019; don’t expect the latest transformers or foundation-model detectors.
• The format is a flat, very long markdown file—no search, tags, or interactive filtering.
• Some entries are just paper titles and links with minimal context or curation notes.

Verdict Ideal for graduate students or engineers entering computer vision who need a historical map of the field and its reference implementations. Skip it if you want a queryable database or state-of-the-art results from the last few years.