# yizt/cv-papers

计算机视觉相关论文整理、记录、分享;  包括图像分类、目标检测、视觉跟踪/目标跟踪、人脸识别/人脸验证、OCR/场景文本检测及识别等领域。欢迎加星,欢迎指正错误,同时也期待能够共同参与！！! 持续更新中... ...

Repository: https://github.com/yizt/cv-papers
Canonical: https://ross.abutalabs.com/products/cv-papers
License: Apache-2.0
License Family: permissive
Topics: yolo, ssd, insightface, cv-papers, r-cnn, retinanet, deep-learning, faster-rcnn, machine-learning
Last push: 2021-07-28T04:00:08+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3064, "days_push": 1862, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1091, forks 257 (observed 2026-08-28T04:03:32.954894+00:00)

## What it is
A curated collection of computer vision paper summaries, translations, and notes written in Chinese Markdown documents. It covers image classification, object detection (R-CNN series, YOLO, SSD), visual tracking, face recognition, OCR/scene text detection, and related topics.

## Use cases
- learn object detection papers like faster r-cnn and yolo
- understand face recognition algorithms like facenet
- study scene text detection and OCR papers like CRNN and CTPN
- find summaries of classic computer vision papers
- learn visual tracking algorithms like GOTURN and SiameseFC
- review deep learning backbone networks like DenseNet and ResNeXt

## When to choose
- you want Chinese-language explanations of classic CV papers with math derivations
- you need a structured reading list covering detection, tracking, face recognition, and OCR
- you prefer reading Markdown notes offline in an editor like Typora

## When to avoid
- you need up-to-date coverage of recent state-of-the-art papers (last release 2021)
- you only read English and cannot use Chinese-language notes
- you need runnable code rather than paper explanations

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: nlp, computer-vision, ocr, image-processing
- domain: computer-vision, deep-learning, machine-learning, tutorials
- platform: cross-platform
- tags: paper-notes, object-detection, face-recognition, visual-tracking, scene-text-detection, chinese-language, yolo, faster-rcnn

## Member repositories
- yizt/cv-papers (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:32.954894+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:49:10.826122+00:00, confidence not recorded.
  - readme: https://github.com/yizt/cv-papers (fetched 2026-08-28T04:03:32.954894+00:00, sha 9b13416dbc22)
- Data as of 2026-08-30T08:39:29.467469+00:00.